CA1326299C - Speaker verification system using integrated circuit cards - Google Patents
Speaker verification system using integrated circuit cardsInfo
- Publication number
- CA1326299C CA1326299C CA000571878A CA571878A CA1326299C CA 1326299 C CA1326299 C CA 1326299C CA 000571878 A CA000571878 A CA 000571878A CA 571878 A CA571878 A CA 571878A CA 1326299 C CA1326299 C CA 1326299C
- Authority
- CA
- Canada
- Prior art keywords
- speech
- terminal
- card
- user
- template
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M3/00—Automatic or semi-automatic exchanges
- H04M3/38—Graded-service arrangements, i.e. some subscribers prevented from establishing certain connections
- H04M3/382—Graded-service arrangements, i.e. some subscribers prevented from establishing certain connections using authorisation codes or passwords
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/20—Individual registration on entry or exit involving the use of a pass
- G07C9/22—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder
- G07C9/25—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition
- G07C9/257—Individual registration on entry or exit involving the use of a pass in combination with an identity check of the pass holder using biometric data, e.g. fingerprints, iris scans or voice recognition electronically
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L17/00—Speaker identification or verification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M1/00—Substation equipment, e.g. for use by subscribers
- H04M1/26—Devices for calling a subscriber
- H04M1/27—Devices whereby a plurality of signals may be stored simultaneously
- H04M1/271—Devices whereby a plurality of signals may be stored simultaneously controlled by voice recognition
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04M—TELEPHONIC COMMUNICATION
- H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
- H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Acoustics & Sound (AREA)
- Multimedia (AREA)
- Computer Security & Cryptography (AREA)
- Financial Or Insurance-Related Operations Such As Payment And Settlement (AREA)
- Control Of Vending Devices And Auxiliary Devices For Vending Devices (AREA)
Abstract
Abstract of the Disclosure A speaker verification and voice command system utilizing speech templates stored in an integrated circuit card is disclosed. To verify the user's identity, a comparison is made between a plurality of reference speech templates stored in the user's integrated circuit card and a test template formed from a word or words spoken by the user.
Description
Field of the Invention The present invention relates to speaker verification and voice command at a terminal utilizing speech templates stored in an integrated circuit card.
Backaround of the Invention An integrated circuit card or a "smart card" is ~ a card which typically has a size similar to that of an - ordinary credit card and which contains an integrated - circuit such as a microprocessor and/or memory.
~iometric identity verification schemes are often associated with integrated circuit cards. However, such prior art biometric identity schemes are generally signature or fingerprint comparisons favored for financial services applications such as credit verification at point of sale. Voice verification and command is of qreater interest for the provision of communications services, - since it is natural in the telephony environment, is fast, and can be used conveniently in wall mounted, portable and mobile terminals. No complete system for speaker - 20 verification and voice command relying on storage of reference speech templates in integrated circuit cards has -~ been disclosed in the prior art. Accordingly, it is an object of the present invention to provide a complete system for speaker verification and voice command based on the storage of reference speech templates in an integrated ` circuit card.
.~
.,., .~
;::
Summarv of the Invention The present invention provides a scheme for verifying the claimed identity of an individual at a `~ 30 terminal such as a telephone or other communications ` terminal. It is intended to secure access to services and privileges for authorized users, ease and facilitate human-machine interaction, protect the privacy of personal information and deter fraud. The applications include fast personalization of non-proprietary communications -~ terminals and access to customized services and personal information such as data files and received messages.
The speaker verification system utilizes an integrated circuit ("smart") card assigned to the user, a smart card interfacing device built into or attached to the terminal, and circuitry or a body of software incorporating known algorithms for accomplishing speech feature extraction and comparison. The identity claim is made by data in the card and verified by analysis of a word or words spoken by the user after prompting by the terminal. This analysis includes a comparison of a test template formed using the spoken word or words with reference speech templates stored in the card.
Voice commands for controlling particular services subsequent to identity verification may also be recognized by speaker dependent recognition algorithms involving comparisons with reference speech templates stored in the card. Illustratively, the card stores a set of reference speech templates for each of a plurality of commands. An example of such a command is to order the dialing of a particular telephone number.
To use the verification scheme of the present invention, the following operational sequence - 25 illustratively takes place.
1. The user first inserts his assigned card into the smart card interfacing device built into the terminal. After the card receives power and after the execution of data communications handshaking protocols, an unprotected identity of the user (e.g. a name) is transmitted from the card to the terminal. The terminal -~ responds with a signaled, spoken or visual acknowledgement.
2. The terminal verifies itself to the card and - 35 the card verifies itself to the terminal. Prior art encryption techniques are available to accomplish this.
Backaround of the Invention An integrated circuit card or a "smart card" is ~ a card which typically has a size similar to that of an - ordinary credit card and which contains an integrated - circuit such as a microprocessor and/or memory.
~iometric identity verification schemes are often associated with integrated circuit cards. However, such prior art biometric identity schemes are generally signature or fingerprint comparisons favored for financial services applications such as credit verification at point of sale. Voice verification and command is of qreater interest for the provision of communications services, - since it is natural in the telephony environment, is fast, and can be used conveniently in wall mounted, portable and mobile terminals. No complete system for speaker - 20 verification and voice command relying on storage of reference speech templates in integrated circuit cards has -~ been disclosed in the prior art. Accordingly, it is an object of the present invention to provide a complete system for speaker verification and voice command based on the storage of reference speech templates in an integrated ` circuit card.
.~
.,., .~
;::
Summarv of the Invention The present invention provides a scheme for verifying the claimed identity of an individual at a `~ 30 terminal such as a telephone or other communications ` terminal. It is intended to secure access to services and privileges for authorized users, ease and facilitate human-machine interaction, protect the privacy of personal information and deter fraud. The applications include fast personalization of non-proprietary communications -~ terminals and access to customized services and personal information such as data files and received messages.
The speaker verification system utilizes an integrated circuit ("smart") card assigned to the user, a smart card interfacing device built into or attached to the terminal, and circuitry or a body of software incorporating known algorithms for accomplishing speech feature extraction and comparison. The identity claim is made by data in the card and verified by analysis of a word or words spoken by the user after prompting by the terminal. This analysis includes a comparison of a test template formed using the spoken word or words with reference speech templates stored in the card.
Voice commands for controlling particular services subsequent to identity verification may also be recognized by speaker dependent recognition algorithms involving comparisons with reference speech templates stored in the card. Illustratively, the card stores a set of reference speech templates for each of a plurality of commands. An example of such a command is to order the dialing of a particular telephone number.
To use the verification scheme of the present invention, the following operational sequence - 25 illustratively takes place.
1. The user first inserts his assigned card into the smart card interfacing device built into the terminal. After the card receives power and after the execution of data communications handshaking protocols, an unprotected identity of the user (e.g. a name) is transmitted from the card to the terminal. The terminal -~ responds with a signaled, spoken or visual acknowledgement.
2. The terminal verifies itself to the card and - 35 the card verifies itself to the terminal. Prior art encryption techniques are available to accomplish this.
3. Text or phonetic descriptors of one or more candidate verification words or phrases are transmitted from the card to the terminal. The terminal visually or aurally prompts the user to speak one of these candidates.
4. The word or phrase spoken by the user is digitized in the terminal and processed in accordance with known algorithms to form a test speech template. If the data derived from the spoken word or phrase is unsuitable because of ambient noise, equipment malfunction or other `detectable cause, the user is prompted to submit an ;~10 alternative verification, such as a keyed-in password or a keyed-in response to a personal question such as "what is your mother-in-law's name?"
5. If the data derived from the spoken word or phrase is technically satisfactory, the terminal instructs the card to transmit to it a multiplicity of previously stored reference speech templates (typically four or five) corresponding to the spoken word or phrase.
Alternatively, if the storage and processing capabilities of the card are adequate, the terminal can transmit the data derived from the spoken word or phrase into the card.
The reference templates stored in the card have been created previously by means of the same processing `algorithm used to form the test template. A reference template, in compressed form, will typically require 250 to 512 bytes of storage capacity.
Alternatively, if the storage and processing capabilities of the card are adequate, the terminal can transmit the data derived from the spoken word or phrase into the card.
The reference templates stored in the card have been created previously by means of the same processing `algorithm used to form the test template. A reference template, in compressed form, will typically require 250 to 512 bytes of storage capacity.
6. A closeness metric is computed in the terminal or the card, to compare the test template derived from the spoken word or phrase and each reference template for that word or phrase stored in the card. Based on this ;30 analysis, an "accept" or "reject" decision is reached.
7. If the decision is to "accept", an appropriate modification of the set of stored reference templates for the word or phrase used for verification is made, and the revised template set is stored in the card in place of the template set ~ust used. A typical revision would be to discard the oldest reference template stored in the card and substitute in its place the test template just used. A decision to accept is followed by access to protected memory locations in the card and to service privileges extended through the terminal, which are contingent on identity verification.
8. If the decision is to "reject", the user in particular embodiments will be offered another opportunity to speak the same word, be requested to speak a different word, or be prompted to use a backup password or other alternative identity verification means. A third decision category, "referral" to a local human or to an online human or mechanical verification authority may also be provided. The number of verification attempts allowed at each transaction is limited according to instructions in the card. An identity verification history is preferably stored in the card. Future accept/reject decisions may be functionally dependent on this history.
After the identity of the user is established, voice commands may be used to control particular service.
For this purpose, the card stores a set of reference templates, for each command in a list of valid commands.
; Illustratively, in a particular embodiment of the invention, a user may verbally request that a particular telephone number be dialed. In this case the verbal command is digitized in the terminal and processed in accordance with a known algorithm to form a test template.
This test template is then compared to the sets of command reference templates stored in the card to determine which command was spoken by the user. The speech processing algorithms used to form the reference and test templates in the verification and command processes are different since the purposes are different. In the case of - verification, a speech processing algorithm is used which can enable identification of the user. In the case of voice command, a speech processing algorithm is used which can enable identification of a particular command.
. . .
.
Brief Description of the Drawinq FIG. 1 schematically illustrates an integrated circuit card which stores speech templates and a terminal in which the card may be used, in accordance with an ~ 5 illustrative embodiment of the invention.
- FIG. 2 is a flow chart which illustrates the sequence of operations of the card and terminal of FIG. 1 when used for voice verification, in accordance with an illustrative embodiment of the present invention.
Detailed Description FIG. 1 illustrates a system comprising an integrated circuit or "smart" card 1 capable of storing speech templates and a terminal 2. The card may be used at the terminal for verifying the claimed identity of an individual and for implementing voice commands.
The card 1 comprises memory 7 and a microprocessing unit 4. The memory 7 comprises three fields: an open field 6, a protected field 5, and a secret field 3.
The card is received by the user from the issuer. The issuer initializes the card by writing the issuer identity, security codes, and user identity (e.g.
name and account number) into the card. The issuer ;` security code and a user password are stored in the secret field 3 of the card memory 7 and can be accessed only by computer programs executed within the card. Additional security information, such as the answer to a personal question (e.g. what is your mother-in-law's name?) can optionally be included. The issuer may also enter a payment authorization such as a credit restriction or prepaid balance and period of validity.
The card 1, once in the user's possession, is trained for speaker verification and voice command while inserted into the terminal 2. The user inserts the card 1 into the card read-write interface 21 of the terminal 2.
In the illustrative embodiment of the invention shown in FIG. 1, the connections between the card 1 and terminal 2 132~299 are electric. Thus, the processing unit 4 and other electronic circuitry in the card 1 receive power from the power supply 41 of the terminal 2 as does the electronic circuitry in the terminal 2. Serial data is transmitted between the card 1 and the interface 21 of the terminal 2 via bus 42. Lines 43 and 44 are provided for clock and enable signals. In an alternative embodiment of the invention the card and terminal may be optically connected.
lo After the user inserts card 1 into the read-write interface 21 of the terminal 2, under the control of programs stored in the card memory 3 and terminal memory 24, an automatic exchange is carried out in which the signaling protocol between the card and terminal is established and the card is recognized by the terminal.
The user's non-secret identity (e.g. name or identification number) is extracted from the open field 6 of the card memory 3 and displayed in a welcoming message on the terminal display device 33.
After this initial interchange between card and - terminal is completed, the terminal then prompts the user, ;~ visually and/or aurally, to speak a particular ; verification or command phase. Such prompting is carried out under control of a conventional program stored in terminal memory 24, which program is run on terminal CPU
22. A character string describing the verification phrase - is extracted from the terminal memory 24 and transmitted to a character generator and display 32, 33 and/or to a text-to-speech synthesizer 34 which can be used for the visual and/or aural prompting of the user, respectively.
The user's response is input via microphone 31 and analog- to-digital converter 40. The resulting digitized speech signal is routed to and analyzed in either speaker verifier 36 or speech recognizer 35 depending on whether the prompted phrase is for speaker verification or voice command. Alternatively, the speaker verifier and speech recognizer may be realized entirely in ~ _ 7 _ 132~299 software stored in terminal memory 24 and executed by terminal CPU 22.
When the card 1 is being "trained", the speaker verifier 36 or speech recognizer 35 is used to extract certain characteristic features from the digitized version of the spoken phrase, which extracted features are used to form a reference speech template. Examples of such features include cepstral coefficients. Cepstral coefficients are coefficients of a polynomial which models the spectrum of the speech signal during a particular time window. Thus, the cepstral coefficients vary from time window to time window. A template comprises a plurality of cepstral coefficient sets. Illustratively, a user verification reference template is formed as a result of processing in speaker verifier 36. A voice command reference template may be formed as a result of processing in the speech recognizer 35. The reason for this is that the voice command templates and the user verification templates are formed using different speech processing algorithms. For example, algorithms for verification and voice command may weight cepstral coefficients differently. In an alternative embodiment of the invention, filter bank outputs may be used to form the speech templates. Examples of such filter banks are disclosed in L.R. Rabiner and R.W. Schafer "Digital Processing of Speech Signals" Chapter 6, copyright 1978, Bell Telephone Laboratories.
Each reference speech template including a time stamp is stored in the protected field 5 of the card memory 7 via the terminal CPU 22, card read-write interface 21 and card CPU 4 under the control of interacting programs in the terminal memory 24 and card memory 3. Techniques for data transfers between the card and terminal are well known in the prior art. The character string or standard phonetic descriptor describing the words or phrase from which each reference template was derived is also stored in the card memory ~326299 along with a pointer (i.e. memory address) to the corresponding template. The acceptance of a spoken phrase is signaled to the user by passing an appropriate notification message from memory 24 to display 33 and/or text-to- speech synthesizer 34. Since several speech templates are required for each verification or command phrase, the above procedure is repeated several times.
Thus, it is through the storage of reference speech template sets that the card 1 is "trained" for speaker verification and voice command. When training is completed, the card 1 is removed from the terminal 2. The card may subsequently be used to access particular services at appropriate terminals until financial or ; period of validity limits are reached.
In order to use the card to obtain access to ;~ particular services, the user inserts a previously trained card 1 into the read-write interface 21. As in the case of the training procedure, an automatic interchange takes place between the card and terminal, during which, the - 20 card is accepted by the terminal, the signalling protocol is established, the card and terminal mutually authenticate themselves and the non-secret user identity is extracted from the card memory and displayed as part of a greeting to the user on the terminal's display.
A computer program stored in terminal memory 24 causes the terminal to send to the card CPU 4 a command requesting the character string or phonetic descriptor corresponding to the word or phrase to be used for speaker verification and pointers to the locations in protected field 5 of the card memory 7 at which are stored the multiple reference templates corresponding to that descriptor. A computer program stored in the card memory 7 responds by transferring the requested data to the terminal memory 24 via the card CPU 4, read-write interface 21 and terminal CPU 22. The character string or phonetic descriptor is in turn transmitted to the display 33 and/or speech synthesizer 34 to prompt the user to - 9 1~26299 speak the verification phrase.
Under control of a computer program stored in the terminal, the voice response of the user is received by way of microphone 31 and is digitized by mea~s of analog/digital converter 40. The diqitized speech signal is then processed in speaker verifier 36 or alternatively used as data input to a speaker verification program resident in terminal memory 24. In either case, a test template is computed from the processed speech signal using the same algorithm that was used to compute the ~ verification reference speech templates during the ; training session described above (e.g. computation of cepstral coefficients). The multiple reference templates stored in the card are retrieved one by one using the pointers previously transferred to the terminal memory.
These reference templates are inputted to the speaker verifier or equivalent software program. When each reference template is transferred from the card memory 7 to the speaker verifier or stored program, it is compared to the test template through computation of a closeness metric. When the full set of closeness metrics is computed, the closeness metrics are utilized by a stored program in the terminal to issue a decision. The decision is either "accept", "reject", or "try another identification mechanism".
If an "accept" decision is made, the appropriate message is sent to display 33 and/or speech synthesizer 34. A new template may be transmitted from speaker verifier 36 to the protected field of the card memory 7, along with a pointer to a template storage location, to replace one of the previously stored reference templates.
This new template may be the test template, i.e. derived solely from the phrase spoken by the user for verification or alternatively may be an appropriate combination of the test template with the reference templates previously stored in the card memory, such-as a simple average.
` A further automatic personalization of the - lo - 132~2~9 terminal follows speaker verification. For example, if the terminal is an integrated voice/data communications terminal, data are extracted from the card memory specifying personal telephone numbers, a personal calling directory, billing codes, calling privileges and limitations, interexchange and data network carrier access codes, an electronic mailbox address, service access codes, and/or service selections. The terminal is able to communicate with a telecommunications network to supply such services by way of communications interface 37.
As indicated above, control of the now accessed services may be accomplished, in particular embodiments of the invention by way of voice command. The voice command procedure differs somewhat from the user verification procedure. One difference is that no prompting of the -; speaker is needed other than a notification that commands will be accepted. Furthermore, the "accept" decision of the verification procedure is replaced by a number of possible recognition decisions corresponding to the available command set. The command speech templates, the closeness metric and any other relevant design cr~terion are optimized for distinguishing among commands rather than for distinguishing among speakers.
The user is prompted, via display 33 and/or text-to-speech synthesizer to indicate completion of a utilization session by voice or keyboard means. When this is done, services opened by use of the card are closed, user specific data stored in terminal memory 24 are erased, all communications connections out of and into the terminal through communications interface 37 are terminated, and the user is prompted to remove the card.
; The sequence of operations necessary for using smart card 1 and terminal 2 to verify the identification of a user is reviewed in connection with the flow chart of FIG. 2. As indicated above, the card is inserted into the terminal and startup protocols are executed. The card and terminal then authenticate themselves to one another.
t i - 11 - 132~299 After this, the following sequence is followed:
(1) Text or phonetic descriptors of one or more candidate words or phrases for speaker verification are transmitted from the card to the terminal. The terminal prompts the user to speak one of these candidates, which may be randomly selected if there are more than one.
(Boxes 102 and 104 of FIG. 2).
(2) The word or phrase spoken by the user is digitized by the terminal and processed to extract the test speech template. (box 106 of FlG 2) (If the data - derived from the spoken word or phrase are unsuitable because of ambient noise, equipment malfunction, or other detectable cause, and assuming a keyboard is available, the user is prompted to submit alternative verification, such as a keyed-in password or a keyed-in response to a personal question such as "what is your mother-in-law's - name"? This keyed-in sequence is transmitted to the card for internal comparison with a stored reference.) (3) If the data derived from the spoken word or phrase are technically satisfactory, the terminal instructs the card to successively transmit to it each of the stored reference templates for that word or phrase.
Each template typically occupies 256 to 512 bytes of memory. (box 108) (4) A closeness metric is computed (boxes 110, 112, 114) in the terminal, between the test template derived from the spoken word or phrase and each reference template received from the card. A known algorithm is ; executed to arrive at an "accept", "reject", or "test ` 30 further" decision. ~he algorithm achieves a specified compromise between false rejection (of a legitimate cardholder) and false acceptance (of an imposter).
(5) If the decision is to "accept", i.e. the claimed identity is verified by the spoken sample, `~ 35 instructions are sent from terminal to card to open applications and memory locations of the card relevant to services and privileges accessed by the card. (box 116) -132~299 -~ - 12 -(6) Given a decision to "accept", the reference template set stored in the card memory is optionally - updated. Several updating algorithms are possible including:
a) Substituting for a previously stored reference template an average template which averages in the newly accepted test template of the spoken word or phrases, or -~ b) Discarding the oldest reference template and ; 10 substituting the new test template. (box 118) (7) If the decision is not to accept, the user may, at the option of the system designer, be offered another opportunity to speak the same word, be requested to speak a different word, or be prompted to use a backup password (box 120). An alternative identity verification means such as providing an answer to a personal question may also be used (box 122). An additional decision ~ category, "referral" to a local human or to an online -~ human or mechanical verification authority, may also be provided. The number of verification attempts allowed at each transaction is limited according to instructions in the card, and an identity verification history is optionally stored in the card. Future accept/reject/referral decisions may be made functionally - 25 dependent on this history.
(8) A visual or aural indicator (box 124) ;~ signals the user to remove the card or initiate a new services procedure when a service procedure is completed.
(9) A reject decision is also communicated ; 30 using a visual or aural indicator (box 126).
In short, a speaker verification and voice ~ command system utilizing speech templates stored in a ; integrated circuit card is disclosed. To verify the -~ user's identity, a comparison is made between a set of reference speech templates stored in the user's integrated circuit card and a test template derived from a word or ~ words spoken by the user. Templates stored in the card ,~
- - `
. .
-- 13 - ~326299 may also be used to distinguish among various spoken commands.
Finally, the above described embodiments of the invention are intended to be illustrative only. Numerous alternative embodiments may be derived by those skilled in the art, without departing from the spirit or scope of the following claims.
, .,.
,, . .
,. ~
.~
.
., -- ,, ,.
. .
" .
After the identity of the user is established, voice commands may be used to control particular service.
For this purpose, the card stores a set of reference templates, for each command in a list of valid commands.
; Illustratively, in a particular embodiment of the invention, a user may verbally request that a particular telephone number be dialed. In this case the verbal command is digitized in the terminal and processed in accordance with a known algorithm to form a test template.
This test template is then compared to the sets of command reference templates stored in the card to determine which command was spoken by the user. The speech processing algorithms used to form the reference and test templates in the verification and command processes are different since the purposes are different. In the case of - verification, a speech processing algorithm is used which can enable identification of the user. In the case of voice command, a speech processing algorithm is used which can enable identification of a particular command.
. . .
.
Brief Description of the Drawinq FIG. 1 schematically illustrates an integrated circuit card which stores speech templates and a terminal in which the card may be used, in accordance with an ~ 5 illustrative embodiment of the invention.
- FIG. 2 is a flow chart which illustrates the sequence of operations of the card and terminal of FIG. 1 when used for voice verification, in accordance with an illustrative embodiment of the present invention.
Detailed Description FIG. 1 illustrates a system comprising an integrated circuit or "smart" card 1 capable of storing speech templates and a terminal 2. The card may be used at the terminal for verifying the claimed identity of an individual and for implementing voice commands.
The card 1 comprises memory 7 and a microprocessing unit 4. The memory 7 comprises three fields: an open field 6, a protected field 5, and a secret field 3.
The card is received by the user from the issuer. The issuer initializes the card by writing the issuer identity, security codes, and user identity (e.g.
name and account number) into the card. The issuer ;` security code and a user password are stored in the secret field 3 of the card memory 7 and can be accessed only by computer programs executed within the card. Additional security information, such as the answer to a personal question (e.g. what is your mother-in-law's name?) can optionally be included. The issuer may also enter a payment authorization such as a credit restriction or prepaid balance and period of validity.
The card 1, once in the user's possession, is trained for speaker verification and voice command while inserted into the terminal 2. The user inserts the card 1 into the card read-write interface 21 of the terminal 2.
In the illustrative embodiment of the invention shown in FIG. 1, the connections between the card 1 and terminal 2 132~299 are electric. Thus, the processing unit 4 and other electronic circuitry in the card 1 receive power from the power supply 41 of the terminal 2 as does the electronic circuitry in the terminal 2. Serial data is transmitted between the card 1 and the interface 21 of the terminal 2 via bus 42. Lines 43 and 44 are provided for clock and enable signals. In an alternative embodiment of the invention the card and terminal may be optically connected.
lo After the user inserts card 1 into the read-write interface 21 of the terminal 2, under the control of programs stored in the card memory 3 and terminal memory 24, an automatic exchange is carried out in which the signaling protocol between the card and terminal is established and the card is recognized by the terminal.
The user's non-secret identity (e.g. name or identification number) is extracted from the open field 6 of the card memory 3 and displayed in a welcoming message on the terminal display device 33.
After this initial interchange between card and - terminal is completed, the terminal then prompts the user, ;~ visually and/or aurally, to speak a particular ; verification or command phase. Such prompting is carried out under control of a conventional program stored in terminal memory 24, which program is run on terminal CPU
22. A character string describing the verification phrase - is extracted from the terminal memory 24 and transmitted to a character generator and display 32, 33 and/or to a text-to-speech synthesizer 34 which can be used for the visual and/or aural prompting of the user, respectively.
The user's response is input via microphone 31 and analog- to-digital converter 40. The resulting digitized speech signal is routed to and analyzed in either speaker verifier 36 or speech recognizer 35 depending on whether the prompted phrase is for speaker verification or voice command. Alternatively, the speaker verifier and speech recognizer may be realized entirely in ~ _ 7 _ 132~299 software stored in terminal memory 24 and executed by terminal CPU 22.
When the card 1 is being "trained", the speaker verifier 36 or speech recognizer 35 is used to extract certain characteristic features from the digitized version of the spoken phrase, which extracted features are used to form a reference speech template. Examples of such features include cepstral coefficients. Cepstral coefficients are coefficients of a polynomial which models the spectrum of the speech signal during a particular time window. Thus, the cepstral coefficients vary from time window to time window. A template comprises a plurality of cepstral coefficient sets. Illustratively, a user verification reference template is formed as a result of processing in speaker verifier 36. A voice command reference template may be formed as a result of processing in the speech recognizer 35. The reason for this is that the voice command templates and the user verification templates are formed using different speech processing algorithms. For example, algorithms for verification and voice command may weight cepstral coefficients differently. In an alternative embodiment of the invention, filter bank outputs may be used to form the speech templates. Examples of such filter banks are disclosed in L.R. Rabiner and R.W. Schafer "Digital Processing of Speech Signals" Chapter 6, copyright 1978, Bell Telephone Laboratories.
Each reference speech template including a time stamp is stored in the protected field 5 of the card memory 7 via the terminal CPU 22, card read-write interface 21 and card CPU 4 under the control of interacting programs in the terminal memory 24 and card memory 3. Techniques for data transfers between the card and terminal are well known in the prior art. The character string or standard phonetic descriptor describing the words or phrase from which each reference template was derived is also stored in the card memory ~326299 along with a pointer (i.e. memory address) to the corresponding template. The acceptance of a spoken phrase is signaled to the user by passing an appropriate notification message from memory 24 to display 33 and/or text-to- speech synthesizer 34. Since several speech templates are required for each verification or command phrase, the above procedure is repeated several times.
Thus, it is through the storage of reference speech template sets that the card 1 is "trained" for speaker verification and voice command. When training is completed, the card 1 is removed from the terminal 2. The card may subsequently be used to access particular services at appropriate terminals until financial or ; period of validity limits are reached.
In order to use the card to obtain access to ;~ particular services, the user inserts a previously trained card 1 into the read-write interface 21. As in the case of the training procedure, an automatic interchange takes place between the card and terminal, during which, the - 20 card is accepted by the terminal, the signalling protocol is established, the card and terminal mutually authenticate themselves and the non-secret user identity is extracted from the card memory and displayed as part of a greeting to the user on the terminal's display.
A computer program stored in terminal memory 24 causes the terminal to send to the card CPU 4 a command requesting the character string or phonetic descriptor corresponding to the word or phrase to be used for speaker verification and pointers to the locations in protected field 5 of the card memory 7 at which are stored the multiple reference templates corresponding to that descriptor. A computer program stored in the card memory 7 responds by transferring the requested data to the terminal memory 24 via the card CPU 4, read-write interface 21 and terminal CPU 22. The character string or phonetic descriptor is in turn transmitted to the display 33 and/or speech synthesizer 34 to prompt the user to - 9 1~26299 speak the verification phrase.
Under control of a computer program stored in the terminal, the voice response of the user is received by way of microphone 31 and is digitized by mea~s of analog/digital converter 40. The diqitized speech signal is then processed in speaker verifier 36 or alternatively used as data input to a speaker verification program resident in terminal memory 24. In either case, a test template is computed from the processed speech signal using the same algorithm that was used to compute the ~ verification reference speech templates during the ; training session described above (e.g. computation of cepstral coefficients). The multiple reference templates stored in the card are retrieved one by one using the pointers previously transferred to the terminal memory.
These reference templates are inputted to the speaker verifier or equivalent software program. When each reference template is transferred from the card memory 7 to the speaker verifier or stored program, it is compared to the test template through computation of a closeness metric. When the full set of closeness metrics is computed, the closeness metrics are utilized by a stored program in the terminal to issue a decision. The decision is either "accept", "reject", or "try another identification mechanism".
If an "accept" decision is made, the appropriate message is sent to display 33 and/or speech synthesizer 34. A new template may be transmitted from speaker verifier 36 to the protected field of the card memory 7, along with a pointer to a template storage location, to replace one of the previously stored reference templates.
This new template may be the test template, i.e. derived solely from the phrase spoken by the user for verification or alternatively may be an appropriate combination of the test template with the reference templates previously stored in the card memory, such-as a simple average.
` A further automatic personalization of the - lo - 132~2~9 terminal follows speaker verification. For example, if the terminal is an integrated voice/data communications terminal, data are extracted from the card memory specifying personal telephone numbers, a personal calling directory, billing codes, calling privileges and limitations, interexchange and data network carrier access codes, an electronic mailbox address, service access codes, and/or service selections. The terminal is able to communicate with a telecommunications network to supply such services by way of communications interface 37.
As indicated above, control of the now accessed services may be accomplished, in particular embodiments of the invention by way of voice command. The voice command procedure differs somewhat from the user verification procedure. One difference is that no prompting of the -; speaker is needed other than a notification that commands will be accepted. Furthermore, the "accept" decision of the verification procedure is replaced by a number of possible recognition decisions corresponding to the available command set. The command speech templates, the closeness metric and any other relevant design cr~terion are optimized for distinguishing among commands rather than for distinguishing among speakers.
The user is prompted, via display 33 and/or text-to-speech synthesizer to indicate completion of a utilization session by voice or keyboard means. When this is done, services opened by use of the card are closed, user specific data stored in terminal memory 24 are erased, all communications connections out of and into the terminal through communications interface 37 are terminated, and the user is prompted to remove the card.
; The sequence of operations necessary for using smart card 1 and terminal 2 to verify the identification of a user is reviewed in connection with the flow chart of FIG. 2. As indicated above, the card is inserted into the terminal and startup protocols are executed. The card and terminal then authenticate themselves to one another.
t i - 11 - 132~299 After this, the following sequence is followed:
(1) Text or phonetic descriptors of one or more candidate words or phrases for speaker verification are transmitted from the card to the terminal. The terminal prompts the user to speak one of these candidates, which may be randomly selected if there are more than one.
(Boxes 102 and 104 of FIG. 2).
(2) The word or phrase spoken by the user is digitized by the terminal and processed to extract the test speech template. (box 106 of FlG 2) (If the data - derived from the spoken word or phrase are unsuitable because of ambient noise, equipment malfunction, or other detectable cause, and assuming a keyboard is available, the user is prompted to submit alternative verification, such as a keyed-in password or a keyed-in response to a personal question such as "what is your mother-in-law's - name"? This keyed-in sequence is transmitted to the card for internal comparison with a stored reference.) (3) If the data derived from the spoken word or phrase are technically satisfactory, the terminal instructs the card to successively transmit to it each of the stored reference templates for that word or phrase.
Each template typically occupies 256 to 512 bytes of memory. (box 108) (4) A closeness metric is computed (boxes 110, 112, 114) in the terminal, between the test template derived from the spoken word or phrase and each reference template received from the card. A known algorithm is ; executed to arrive at an "accept", "reject", or "test ` 30 further" decision. ~he algorithm achieves a specified compromise between false rejection (of a legitimate cardholder) and false acceptance (of an imposter).
(5) If the decision is to "accept", i.e. the claimed identity is verified by the spoken sample, `~ 35 instructions are sent from terminal to card to open applications and memory locations of the card relevant to services and privileges accessed by the card. (box 116) -132~299 -~ - 12 -(6) Given a decision to "accept", the reference template set stored in the card memory is optionally - updated. Several updating algorithms are possible including:
a) Substituting for a previously stored reference template an average template which averages in the newly accepted test template of the spoken word or phrases, or -~ b) Discarding the oldest reference template and ; 10 substituting the new test template. (box 118) (7) If the decision is not to accept, the user may, at the option of the system designer, be offered another opportunity to speak the same word, be requested to speak a different word, or be prompted to use a backup password (box 120). An alternative identity verification means such as providing an answer to a personal question may also be used (box 122). An additional decision ~ category, "referral" to a local human or to an online -~ human or mechanical verification authority, may also be provided. The number of verification attempts allowed at each transaction is limited according to instructions in the card, and an identity verification history is optionally stored in the card. Future accept/reject/referral decisions may be made functionally - 25 dependent on this history.
(8) A visual or aural indicator (box 124) ;~ signals the user to remove the card or initiate a new services procedure when a service procedure is completed.
(9) A reject decision is also communicated ; 30 using a visual or aural indicator (box 126).
In short, a speaker verification and voice ~ command system utilizing speech templates stored in a ; integrated circuit card is disclosed. To verify the -~ user's identity, a comparison is made between a set of reference speech templates stored in the user's integrated circuit card and a test template derived from a word or ~ words spoken by the user. Templates stored in the card ,~
- - `
. .
-- 13 - ~326299 may also be used to distinguish among various spoken commands.
Finally, the above described embodiments of the invention are intended to be illustrative only. Numerous alternative embodiments may be derived by those skilled in the art, without departing from the spirit or scope of the following claims.
, .,.
,, . .
,. ~
.~
.
., -- ,, ,.
. .
" .
Claims (3)
1. In combination, an integrated circuit card including an electronic memory for storing one or more first reference speech templates formed in accordance with a first speech processing algorithm and corresponding to a verification word or phrase and for storing one or more second reference speech templates formed in accordance with a second speech processing algorithm and corresponding to one or more spoken commands, which commands enable access to an individualized set of telecommunications services, a terminal for forming a first test speech template from a speech signal of a prospective user and corresponding to said verification word or phrase for verifying if the prospective user is a legitimate user, and for forming a second test speech template from a command spoken by said legitimate user to enable said legitimate user to selectively access said individualized set of telecommunications services, and comparison means for comparing said first test template with at least one of said first reference templates and said second test template with at least one of said second reference templates.
2 . A method for obtaining access to telecommunications services comprising the steps of providing an integrated circuit card including an electronic memory for storing one ox more first reference speech templates formed in accordance with a first speech processing algorithm and corresponding to a verification word or phrase and for storing one or more second reference speech templates formed in accordance with a second speech processing algorithm and corresponding to one or more spoken commands, which commands enable access to an individualized set of telecommunications services, speaking said verification word or phrase by a prospective user into a microphone associated with a terminal, forming a first test template in said terminal from said spoken verification word or phrase in accordance with said first speech processing algorithm, comparing said first test template with one or more of said first reference templates to determine if said prospective user is a legitimate user of said terminal, if said prospective user of said terminal is a legitimate user, speaking a command into said microphone, forming a second test template from said spoken command in said terminal in accordance with said second speech processing algorithm, and comparing said second test template with one or more of said second reference templates to selectively provide said legitimate user with access to said set of telecommunications services.
3. A terminal for use in obtaining access to telecommunications services comprising means for receiving an integrated circuit card including an electronic memory for storing one or more first reference speech templates formed in accordance with a first speech processing algorithm and corresponding to a verification word and for storing one or more second reference speech templates formed in accordance with a second speech processing algorithm and corresponding to one or more spoken commands, which commands enable access to an individualized set of telecommunications services, microphone means for receiving spoken verification words and spoken command words, first speech processing means for converting a spoken verification word into a first test speech template in accordance with said first speech processing algorithm, second speech processing means for converting a spoken command word into a second test speech template in accordance with said second speech processing algorithm, and comparator means for comparing said first test template with one or more of said first reference templates to determine if a prospective user is a legitimate user and for comparing said second test speech template with one or more of said second reference speech templates to enable a user to selectively access said telecommunications services.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US07/082,198 | 1987-08-06 | ||
US07/082,198 US4827518A (en) | 1987-08-06 | 1987-08-06 | Speaker verification system using integrated circuit cards |
Publications (1)
Publication Number | Publication Date |
---|---|
CA1326299C true CA1326299C (en) | 1994-01-18 |
Family
ID=22169671
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CA000571878A Expired - Fee Related CA1326299C (en) | 1987-08-06 | 1988-07-13 | Speaker verification system using integrated circuit cards |
Country Status (2)
Country | Link |
---|---|
US (1) | US4827518A (en) |
CA (1) | CA1326299C (en) |
Families Citing this family (196)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS6269297A (en) * | 1985-09-24 | 1987-03-30 | 日本電気株式会社 | Speaker checking terminal |
US5054083A (en) * | 1989-05-09 | 1991-10-01 | Texas Instruments Incorporated | Voice verification circuit for validating the identity of an unknown person |
EP0407882A1 (en) * | 1989-07-11 | 1991-01-16 | Siemens Aktiengesellschaft | Device for verifying a person's system access authorization |
GB2237135A (en) * | 1989-10-16 | 1991-04-24 | Logica Uk Ltd | Speaker recognition |
US5127043A (en) * | 1990-05-15 | 1992-06-30 | Vcs Industries, Inc. | Simultaneous speaker-independent voice recognition and verification over a telephone network |
US5517558A (en) * | 1990-05-15 | 1996-05-14 | Voice Control Systems, Inc. | Voice-controlled account access over a telephone network |
US5303299A (en) * | 1990-05-15 | 1994-04-12 | Vcs Industries, Inc. | Method for continuous recognition of alphanumeric strings spoken over a telephone network |
US5125022A (en) * | 1990-05-15 | 1992-06-23 | Vcs Industries, Inc. | Method for recognizing alphanumeric strings spoken over a telephone network |
US5365574A (en) * | 1990-05-15 | 1994-11-15 | Vcs Industries, Inc. | Telephone network voice recognition and verification using selectively-adjustable signal thresholds |
US5263181A (en) * | 1990-10-18 | 1993-11-16 | Motorola, Inc. | Remote transmitter for triggering a voice-operated radio |
AU1436792A (en) * | 1991-02-22 | 1992-09-15 | Seaway Technologies, Inc. | Acoustic method and apparatus for identifying human sonic sources |
US5167004A (en) * | 1991-02-28 | 1992-11-24 | Texas Instruments Incorporated | Temporal decorrelation method for robust speaker verification |
US10361802B1 (en) | 1999-02-01 | 2019-07-23 | Blanding Hovenweep, Llc | Adaptive pattern recognition based control system and method |
US5425128A (en) * | 1992-05-29 | 1995-06-13 | Sunquest Information Systems, Inc. | Automatic management system for speech recognition processes |
US5566229A (en) * | 1992-08-24 | 1996-10-15 | At&T | Voice directed communications system employing shared subscriber identifiers |
CA2108935A1 (en) * | 1992-10-22 | 1994-04-23 | Walter E. Parkerson | Apparatus and method for fast initiation of connection in cordless telephones |
EP0598469A3 (en) * | 1992-10-27 | 1996-07-10 | Daniel P Dunlevy | Interactive credit card fraud control process. |
NZ250812A (en) * | 1993-02-27 | 1996-09-25 | Alcatel Australia | Voice controlled data memory and input/output card |
DE4306199A1 (en) * | 1993-02-27 | 1994-09-01 | Sel Alcatel Ag | Portable speech module |
US5594784A (en) * | 1993-04-27 | 1997-01-14 | Southwestern Bell Technology Resources, Inc. | Apparatus and method for transparent telephony utilizing speech-based signaling for initiating and handling calls |
US5608784A (en) * | 1994-01-24 | 1997-03-04 | Miller; Joel F. | Method of personnel verification using voice recognition |
US5623539A (en) * | 1994-01-27 | 1997-04-22 | Lucent Technologies Inc. | Using voice signal analysis to identify authorized users of a telephone system |
US5774525A (en) * | 1995-01-23 | 1998-06-30 | International Business Machines Corporation | Method and apparatus utilizing dynamic questioning to provide secure access control |
DE19511622A1 (en) * | 1995-03-30 | 1996-10-02 | Michael Wolf | Door answering machine |
WO1997011435A2 (en) * | 1995-09-04 | 1997-03-27 | British Telecommunications Public Limited Company | Transaction support apparatus |
US5774858A (en) * | 1995-10-23 | 1998-06-30 | Taubkin; Vladimir L. | Speech analysis method of protecting a vehicle from unauthorized accessing and controlling |
JPH09149133A (en) * | 1995-11-22 | 1997-06-06 | Fujitsu Ltd | Voice input terminal and voice synthesis terminal for video conference system |
FR2744277B1 (en) * | 1996-01-26 | 1998-03-06 | Sextant Avionique | VOICE RECOGNITION METHOD IN NOISE AMBIENCE, AND IMPLEMENTATION DEVICE |
US5940476A (en) | 1996-06-28 | 1999-08-17 | Distributed Software Development, Inc. | System and method for identifying an unidentified caller |
ES2114493A1 (en) * | 1996-05-22 | 1998-05-16 | Univ Madrid Politecnica | System for verifying the identity of persons by means of a portable data medium based on voice recognition. |
US5901203A (en) | 1996-06-28 | 1999-05-04 | Distributed Software Development, Inc. | Computer-based system and method for identifying an unidentified caller |
US6529881B2 (en) | 1996-06-28 | 2003-03-04 | Distributed Software Development, Inc. | System and method for identifying an unidentified customer at the point of sale |
US7006605B1 (en) | 1996-06-28 | 2006-02-28 | Ochopee Big Cypress Llc | Authenticating a caller before providing the caller with access to one or more secured resources |
US6205204B1 (en) | 1996-06-28 | 2001-03-20 | Distributed Software Development, Inc. | System and method for identifying an unidentified person using an ambiguity-resolution criterion |
NL1003666C2 (en) * | 1996-07-24 | 1998-01-28 | Chiptec International Ltd | Identity card with easy to use, card shaped information carrier with memory |
US6556127B1 (en) | 1996-10-15 | 2003-04-29 | Swisscom Ag | Speaker verification method |
IL119948A (en) | 1996-12-31 | 2004-09-27 | News Datacom Ltd | Voice activated communication system and program guide |
US7321783B2 (en) * | 1997-04-25 | 2008-01-22 | Minerva Industries, Inc. | Mobile entertainment and communication device |
US20040157612A1 (en) * | 1997-04-25 | 2004-08-12 | Minerva Industries, Inc. | Mobile communication and stethoscope system |
US6182037B1 (en) | 1997-05-06 | 2001-01-30 | International Business Machines Corporation | Speaker recognition over large population with fast and detailed matches |
US5940791A (en) * | 1997-05-09 | 1999-08-17 | Washington University | Method and apparatus for speech analysis and synthesis using lattice ladder notch filters |
US6847717B1 (en) | 1997-05-27 | 2005-01-25 | Jbc Knowledge Ventures, L.P. | Method of accessing a dial-up service |
US9978373B2 (en) | 1997-05-27 | 2018-05-22 | Nuance Communications, Inc. | Method of accessing a dial-up service |
US5924070A (en) * | 1997-06-06 | 1999-07-13 | International Business Machines Corporation | Corporate voice dialing with shared directories |
US5953700A (en) * | 1997-06-11 | 1999-09-14 | International Business Machines Corporation | Portable acoustic interface for remote access to automatic speech/speaker recognition server |
DE19726265C2 (en) | 1997-06-20 | 2001-08-02 | Deutsche Telekom Ag | Method for operating a system for using a chip card |
US6078807A (en) * | 1997-08-26 | 2000-06-20 | International Business Machines Corporation | Telephony fraud detection using voice recognition techniques |
US6213391B1 (en) | 1997-09-10 | 2001-04-10 | William H. Lewis | Portable system for personal identification based upon distinctive characteristics of the user |
IL122023A (en) * | 1997-10-26 | 2007-06-17 | Enco Tone Ltd | Non-transferable bio-metric token-based identification method and devices |
JP2002507772A (en) * | 1998-03-18 | 2002-03-12 | シーメンス アクチエンゲゼルシヤフト | Device for information reproduction or function execution |
US6618806B1 (en) | 1998-04-01 | 2003-09-09 | Saflink Corporation | System and method for authenticating users in a computer network |
AU4964899A (en) * | 1998-06-30 | 2000-01-17 | &Commatpos.Com, Inc. | User biometric-secured smartcard holding data for multiple credit cards |
US6928547B2 (en) * | 1998-07-06 | 2005-08-09 | Saflink Corporation | System and method for authenticating users in a computer network |
US6400310B1 (en) * | 1998-10-22 | 2002-06-04 | Washington University | Method and apparatus for a tunable high-resolution spectral estimator |
US7260187B1 (en) | 1999-05-11 | 2007-08-21 | Verizon Services Corp. | Voice response apparatus and method of providing automated voice responses with silent prompting |
DE19924628A1 (en) * | 1999-05-28 | 2000-11-30 | Giesecke & Devrient Gmbh | Setup and method for biometric authentication |
US6393305B1 (en) * | 1999-06-07 | 2002-05-21 | Nokia Mobile Phones Limited | Secure wireless communication user identification by voice recognition |
US6510414B1 (en) | 1999-10-05 | 2003-01-21 | Cisco Technology, Inc. | Speech recognition assisted data entry system and method |
US6618703B1 (en) * | 1999-10-26 | 2003-09-09 | Persay Inc. | Interface to a speech processing system |
IL134988A0 (en) * | 2000-03-09 | 2001-05-20 | Shusteri Yigal | Secure system for smartcard transactions |
US8645137B2 (en) | 2000-03-16 | 2014-02-04 | Apple Inc. | Fast, language-independent method for user authentication by voice |
US7587368B2 (en) | 2000-07-06 | 2009-09-08 | David Paul Felsher | Information record infrastructure, system and method |
US7181017B1 (en) | 2001-03-23 | 2007-02-20 | David Felsher | System and method for secure three-party communications |
US8266451B2 (en) * | 2001-08-31 | 2012-09-11 | Gemalto Sa | Voice activated smart card |
US20040015243A1 (en) * | 2001-09-28 | 2004-01-22 | Dwyane Mercredi | Biometric authentication |
US20040015702A1 (en) * | 2002-03-01 | 2004-01-22 | Dwayne Mercredi | User login delegation |
US20030204403A1 (en) * | 2002-04-25 | 2003-10-30 | Browning James Vernard | Memory module with voice recognition system |
GB2388947A (en) * | 2002-05-22 | 2003-11-26 | Domain Dynamics Ltd | Method of voice authentication |
AU2002326879A1 (en) | 2002-06-05 | 2003-12-22 | Vas International, Inc. | Biometric identification system |
US20040059590A1 (en) * | 2002-09-13 | 2004-03-25 | Dwayne Mercredi | Credential promotion |
US9818136B1 (en) | 2003-02-05 | 2017-11-14 | Steven M. Hoffberg | System and method for determining contingent relevance |
US8447668B2 (en) | 2004-01-16 | 2013-05-21 | Keith Jentoft | Audio-equipped transaction card systems and approaches |
EP1610273A1 (en) * | 2004-06-25 | 2005-12-28 | STMicroelectronics Belgium N.V. | Improved security device and terminal and method for communication between them |
US20060136741A1 (en) * | 2004-12-16 | 2006-06-22 | Saflink Corporation | Two factor token identification |
US8677377B2 (en) | 2005-09-08 | 2014-03-18 | Apple Inc. | Method and apparatus for building an intelligent automated assistant |
US8874477B2 (en) | 2005-10-04 | 2014-10-28 | Steven Mark Hoffberg | Multifactorial optimization system and method |
US9318108B2 (en) | 2010-01-18 | 2016-04-19 | Apple Inc. | Intelligent automated assistant |
US8977255B2 (en) | 2007-04-03 | 2015-03-10 | Apple Inc. | Method and system for operating a multi-function portable electronic device using voice-activation |
US9330720B2 (en) | 2008-01-03 | 2016-05-03 | Apple Inc. | Methods and apparatus for altering audio output signals |
US8996376B2 (en) | 2008-04-05 | 2015-03-31 | Apple Inc. | Intelligent text-to-speech conversion |
US10496753B2 (en) | 2010-01-18 | 2019-12-03 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
US20100030549A1 (en) | 2008-07-31 | 2010-02-04 | Lee Michael M | Mobile device having human language translation capability with positional feedback |
US9959870B2 (en) | 2008-12-11 | 2018-05-01 | Apple Inc. | Speech recognition involving a mobile device |
US10706373B2 (en) | 2011-06-03 | 2020-07-07 | Apple Inc. | Performing actions associated with task items that represent tasks to perform |
US10241752B2 (en) | 2011-09-30 | 2019-03-26 | Apple Inc. | Interface for a virtual digital assistant |
US9858925B2 (en) | 2009-06-05 | 2018-01-02 | Apple Inc. | Using context information to facilitate processing of commands in a virtual assistant |
US10241644B2 (en) | 2011-06-03 | 2019-03-26 | Apple Inc. | Actionable reminder entries |
US9431006B2 (en) | 2009-07-02 | 2016-08-30 | Apple Inc. | Methods and apparatuses for automatic speech recognition |
US10276170B2 (en) | 2010-01-18 | 2019-04-30 | Apple Inc. | Intelligent automated assistant |
US10553209B2 (en) | 2010-01-18 | 2020-02-04 | Apple Inc. | Systems and methods for hands-free notification summaries |
US10679605B2 (en) | 2010-01-18 | 2020-06-09 | Apple Inc. | Hands-free list-reading by intelligent automated assistant |
US10705794B2 (en) | 2010-01-18 | 2020-07-07 | Apple Inc. | Automatically adapting user interfaces for hands-free interaction |
WO2011089450A2 (en) | 2010-01-25 | 2011-07-28 | Andrew Peter Nelson Jerram | Apparatuses, methods and systems for a digital conversation management platform |
US8682667B2 (en) | 2010-02-25 | 2014-03-25 | Apple Inc. | User profiling for selecting user specific voice input processing information |
US10762293B2 (en) | 2010-12-22 | 2020-09-01 | Apple Inc. | Using parts-of-speech tagging and named entity recognition for spelling correction |
US9262612B2 (en) | 2011-03-21 | 2016-02-16 | Apple Inc. | Device access using voice authentication |
US10672399B2 (en) | 2011-06-03 | 2020-06-02 | Apple Inc. | Switching between text data and audio data based on a mapping |
US10057736B2 (en) | 2011-06-03 | 2018-08-21 | Apple Inc. | Active transport based notifications |
TW201301261A (en) * | 2011-06-27 | 2013-01-01 | Hon Hai Prec Ind Co Ltd | Identity authentication system and method thereof |
US8994660B2 (en) | 2011-08-29 | 2015-03-31 | Apple Inc. | Text correction processing |
US10134385B2 (en) | 2012-03-02 | 2018-11-20 | Apple Inc. | Systems and methods for name pronunciation |
US9483461B2 (en) | 2012-03-06 | 2016-11-01 | Apple Inc. | Handling speech synthesis of content for multiple languages |
US9280610B2 (en) | 2012-05-14 | 2016-03-08 | Apple Inc. | Crowd sourcing information to fulfill user requests |
US9721563B2 (en) | 2012-06-08 | 2017-08-01 | Apple Inc. | Name recognition system |
US9495129B2 (en) | 2012-06-29 | 2016-11-15 | Apple Inc. | Device, method, and user interface for voice-activated navigation and browsing of a document |
US9576574B2 (en) | 2012-09-10 | 2017-02-21 | Apple Inc. | Context-sensitive handling of interruptions by intelligent digital assistant |
US9547647B2 (en) | 2012-09-19 | 2017-01-17 | Apple Inc. | Voice-based media searching |
US9691377B2 (en) | 2013-07-23 | 2017-06-27 | Google Technology Holdings LLC | Method and device for voice recognition training |
EP2954514B1 (en) | 2013-02-07 | 2021-03-31 | Apple Inc. | Voice trigger for a digital assistant |
US9275638B2 (en) | 2013-03-12 | 2016-03-01 | Google Technology Holdings LLC | Method and apparatus for training a voice recognition model database |
US10642574B2 (en) | 2013-03-14 | 2020-05-05 | Apple Inc. | Device, method, and graphical user interface for outputting captions |
US9977779B2 (en) | 2013-03-14 | 2018-05-22 | Apple Inc. | Automatic supplementation of word correction dictionaries |
US10572476B2 (en) | 2013-03-14 | 2020-02-25 | Apple Inc. | Refining a search based on schedule items |
US9368114B2 (en) | 2013-03-14 | 2016-06-14 | Apple Inc. | Context-sensitive handling of interruptions |
US10652394B2 (en) | 2013-03-14 | 2020-05-12 | Apple Inc. | System and method for processing voicemail |
US9733821B2 (en) | 2013-03-14 | 2017-08-15 | Apple Inc. | Voice control to diagnose inadvertent activation of accessibility features |
CN105144133B (en) | 2013-03-15 | 2020-11-20 | 苹果公司 | Context-sensitive handling of interrupts |
AU2014233517B2 (en) | 2013-03-15 | 2017-05-25 | Apple Inc. | Training an at least partial voice command system |
WO2014144579A1 (en) | 2013-03-15 | 2014-09-18 | Apple Inc. | System and method for updating an adaptive speech recognition model |
US10748529B1 (en) | 2013-03-15 | 2020-08-18 | Apple Inc. | Voice activated device for use with a voice-based digital assistant |
WO2014144395A2 (en) | 2013-03-15 | 2014-09-18 | Apple Inc. | User training by intelligent digital assistant |
WO2014197334A2 (en) | 2013-06-07 | 2014-12-11 | Apple Inc. | System and method for user-specified pronunciation of words for speech synthesis and recognition |
US9582608B2 (en) | 2013-06-07 | 2017-02-28 | Apple Inc. | Unified ranking with entropy-weighted information for phrase-based semantic auto-completion |
WO2014197336A1 (en) | 2013-06-07 | 2014-12-11 | Apple Inc. | System and method for detecting errors in interactions with a voice-based digital assistant |
WO2014197335A1 (en) | 2013-06-08 | 2014-12-11 | Apple Inc. | Interpreting and acting upon commands that involve sharing information with remote devices |
US10176167B2 (en) | 2013-06-09 | 2019-01-08 | Apple Inc. | System and method for inferring user intent from speech inputs |
DE112014002747T5 (en) | 2013-06-09 | 2016-03-03 | Apple Inc. | Apparatus, method and graphical user interface for enabling conversation persistence over two or more instances of a digital assistant |
KR101809808B1 (en) | 2013-06-13 | 2017-12-15 | 애플 인크. | System and method for emergency calls initiated by voice command |
US9548047B2 (en) | 2013-07-31 | 2017-01-17 | Google Technology Holdings LLC | Method and apparatus for evaluating trigger phrase enrollment |
AU2014306221B2 (en) | 2013-08-06 | 2017-04-06 | Apple Inc. | Auto-activating smart responses based on activities from remote devices |
US10296160B2 (en) | 2013-12-06 | 2019-05-21 | Apple Inc. | Method for extracting salient dialog usage from live data |
US9620105B2 (en) | 2014-05-15 | 2017-04-11 | Apple Inc. | Analyzing audio input for efficient speech and music recognition |
US10592095B2 (en) | 2014-05-23 | 2020-03-17 | Apple Inc. | Instantaneous speaking of content on touch devices |
US9502031B2 (en) | 2014-05-27 | 2016-11-22 | Apple Inc. | Method for supporting dynamic grammars in WFST-based ASR |
US9842101B2 (en) | 2014-05-30 | 2017-12-12 | Apple Inc. | Predictive conversion of language input |
US10170123B2 (en) | 2014-05-30 | 2019-01-01 | Apple Inc. | Intelligent assistant for home automation |
US10289433B2 (en) | 2014-05-30 | 2019-05-14 | Apple Inc. | Domain specific language for encoding assistant dialog |
US9715875B2 (en) | 2014-05-30 | 2017-07-25 | Apple Inc. | Reducing the need for manual start/end-pointing and trigger phrases |
AU2015266863B2 (en) | 2014-05-30 | 2018-03-15 | Apple Inc. | Multi-command single utterance input method |
US9760559B2 (en) | 2014-05-30 | 2017-09-12 | Apple Inc. | Predictive text input |
US10078631B2 (en) | 2014-05-30 | 2018-09-18 | Apple Inc. | Entropy-guided text prediction using combined word and character n-gram language models |
US9430463B2 (en) | 2014-05-30 | 2016-08-30 | Apple Inc. | Exemplar-based natural language processing |
US9734193B2 (en) | 2014-05-30 | 2017-08-15 | Apple Inc. | Determining domain salience ranking from ambiguous words in natural speech |
US9785630B2 (en) | 2014-05-30 | 2017-10-10 | Apple Inc. | Text prediction using combined word N-gram and unigram language models |
US9633004B2 (en) | 2014-05-30 | 2017-04-25 | Apple Inc. | Better resolution when referencing to concepts |
US10659851B2 (en) | 2014-06-30 | 2020-05-19 | Apple Inc. | Real-time digital assistant knowledge updates |
US9338493B2 (en) | 2014-06-30 | 2016-05-10 | Apple Inc. | Intelligent automated assistant for TV user interactions |
US10446141B2 (en) | 2014-08-28 | 2019-10-15 | Apple Inc. | Automatic speech recognition based on user feedback |
US9818400B2 (en) | 2014-09-11 | 2017-11-14 | Apple Inc. | Method and apparatus for discovering trending terms in speech requests |
US10789041B2 (en) | 2014-09-12 | 2020-09-29 | Apple Inc. | Dynamic thresholds for always listening speech trigger |
US9886432B2 (en) | 2014-09-30 | 2018-02-06 | Apple Inc. | Parsimonious handling of word inflection via categorical stem + suffix N-gram language models |
US10127911B2 (en) | 2014-09-30 | 2018-11-13 | Apple Inc. | Speaker identification and unsupervised speaker adaptation techniques |
US9646609B2 (en) | 2014-09-30 | 2017-05-09 | Apple Inc. | Caching apparatus for serving phonetic pronunciations |
US9668121B2 (en) | 2014-09-30 | 2017-05-30 | Apple Inc. | Social reminders |
US10074360B2 (en) | 2014-09-30 | 2018-09-11 | Apple Inc. | Providing an indication of the suitability of speech recognition |
US10552013B2 (en) | 2014-12-02 | 2020-02-04 | Apple Inc. | Data detection |
US9711141B2 (en) | 2014-12-09 | 2017-07-18 | Apple Inc. | Disambiguating heteronyms in speech synthesis |
US9865280B2 (en) | 2015-03-06 | 2018-01-09 | Apple Inc. | Structured dictation using intelligent automated assistants |
US9721566B2 (en) | 2015-03-08 | 2017-08-01 | Apple Inc. | Competing devices responding to voice triggers |
US9886953B2 (en) | 2015-03-08 | 2018-02-06 | Apple Inc. | Virtual assistant activation |
US10567477B2 (en) | 2015-03-08 | 2020-02-18 | Apple Inc. | Virtual assistant continuity |
US9899019B2 (en) | 2015-03-18 | 2018-02-20 | Apple Inc. | Systems and methods for structured stem and suffix language models |
TWI525532B (en) * | 2015-03-30 | 2016-03-11 | Yu-Wei Chen | Set the name of the person to wake up the name for voice manipulation |
US9842105B2 (en) | 2015-04-16 | 2017-12-12 | Apple Inc. | Parsimonious continuous-space phrase representations for natural language processing |
US10083688B2 (en) | 2015-05-27 | 2018-09-25 | Apple Inc. | Device voice control for selecting a displayed affordance |
US10127220B2 (en) | 2015-06-04 | 2018-11-13 | Apple Inc. | Language identification from short strings |
US10255907B2 (en) | 2015-06-07 | 2019-04-09 | Apple Inc. | Automatic accent detection using acoustic models |
US10186254B2 (en) | 2015-06-07 | 2019-01-22 | Apple Inc. | Context-based endpoint detection |
US11025565B2 (en) | 2015-06-07 | 2021-06-01 | Apple Inc. | Personalized prediction of responses for instant messaging |
US10747498B2 (en) | 2015-09-08 | 2020-08-18 | Apple Inc. | Zero latency digital assistant |
US10671428B2 (en) | 2015-09-08 | 2020-06-02 | Apple Inc. | Distributed personal assistant |
US9697820B2 (en) | 2015-09-24 | 2017-07-04 | Apple Inc. | Unit-selection text-to-speech synthesis using concatenation-sensitive neural networks |
US11010550B2 (en) | 2015-09-29 | 2021-05-18 | Apple Inc. | Unified language modeling framework for word prediction, auto-completion and auto-correction |
US10366158B2 (en) | 2015-09-29 | 2019-07-30 | Apple Inc. | Efficient word encoding for recurrent neural network language models |
US11587559B2 (en) | 2015-09-30 | 2023-02-21 | Apple Inc. | Intelligent device identification |
US10691473B2 (en) | 2015-11-06 | 2020-06-23 | Apple Inc. | Intelligent automated assistant in a messaging environment |
US10049668B2 (en) | 2015-12-02 | 2018-08-14 | Apple Inc. | Applying neural network language models to weighted finite state transducers for automatic speech recognition |
US10223066B2 (en) | 2015-12-23 | 2019-03-05 | Apple Inc. | Proactive assistance based on dialog communication between devices |
US10446143B2 (en) | 2016-03-14 | 2019-10-15 | Apple Inc. | Identification of voice inputs providing credentials |
US9934775B2 (en) | 2016-05-26 | 2018-04-03 | Apple Inc. | Unit-selection text-to-speech synthesis based on predicted concatenation parameters |
US9972304B2 (en) | 2016-06-03 | 2018-05-15 | Apple Inc. | Privacy preserving distributed evaluation framework for embedded personalized systems |
US10249300B2 (en) | 2016-06-06 | 2019-04-02 | Apple Inc. | Intelligent list reading |
US10049663B2 (en) | 2016-06-08 | 2018-08-14 | Apple, Inc. | Intelligent automated assistant for media exploration |
DK179309B1 (en) | 2016-06-09 | 2018-04-23 | Apple Inc | Intelligent automated assistant in a home environment |
US10192552B2 (en) | 2016-06-10 | 2019-01-29 | Apple Inc. | Digital assistant providing whispered speech |
US10067938B2 (en) | 2016-06-10 | 2018-09-04 | Apple Inc. | Multilingual word prediction |
US10586535B2 (en) | 2016-06-10 | 2020-03-10 | Apple Inc. | Intelligent digital assistant in a multi-tasking environment |
US10490187B2 (en) | 2016-06-10 | 2019-11-26 | Apple Inc. | Digital assistant providing automated status report |
US10509862B2 (en) | 2016-06-10 | 2019-12-17 | Apple Inc. | Dynamic phrase expansion of language input |
DK179415B1 (en) | 2016-06-11 | 2018-06-14 | Apple Inc | Intelligent device arbitration and control |
DK179343B1 (en) | 2016-06-11 | 2018-05-14 | Apple Inc | Intelligent task discovery |
DK201670540A1 (en) | 2016-06-11 | 2018-01-08 | Apple Inc | Application integration with a digital assistant |
DK179049B1 (en) | 2016-06-11 | 2017-09-18 | Apple Inc | Data driven natural language event detection and classification |
US10593346B2 (en) | 2016-12-22 | 2020-03-17 | Apple Inc. | Rank-reduced token representation for automatic speech recognition |
DK179745B1 (en) | 2017-05-12 | 2019-05-01 | Apple Inc. | SYNCHRONIZATION AND TASK DELEGATION OF A DIGITAL ASSISTANT |
DK201770431A1 (en) | 2017-05-15 | 2018-12-20 | Apple Inc. | Optimizing dialogue policy decisions for digital assistants using implicit feedback |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
BE787377A (en) * | 1971-08-09 | 1973-02-09 | Waterbury Nelson J | SECURITY CARDS AND SYSTEM FOR USING SUCH CARDS |
JPS5944639B2 (en) * | 1975-12-02 | 1984-10-31 | フジゼロツクス カブシキガイシヤ | Standard pattern update method in voice recognition method |
FR2469760A1 (en) * | 1979-11-09 | 1981-05-22 | Cii Honeywell Bull | METHOD AND SYSTEM FOR IDENTIFYING PEOPLE REQUESTING ACCESS TO CERTAIN MEDIA |
JPS58129682A (en) * | 1982-01-29 | 1983-08-02 | Toshiba Corp | Individual verifying device |
JPH0658670B2 (en) * | 1983-08-01 | 1994-08-03 | 沖電気工業株式会社 | Automatic trading system |
JPS6191790A (en) * | 1984-10-12 | 1986-05-09 | カシオ計算機株式会社 | Card collator |
EP0218723A1 (en) * | 1985-04-09 | 1987-04-22 | Drexler Technology Corporation | Data card system for initializing spoken-word recognition units |
-
1987
- 1987-08-06 US US07/082,198 patent/US4827518A/en not_active Expired - Lifetime
-
1988
- 1988-07-13 CA CA000571878A patent/CA1326299C/en not_active Expired - Fee Related
Also Published As
Publication number | Publication date |
---|---|
US4827518A (en) | 1989-05-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CA1326299C (en) | Speaker verification system using integrated circuit cards | |
EP0686297B1 (en) | Voice command control and verification system and method | |
US7310042B2 (en) | System and method for biometric-based fraud protection | |
EP0746846B1 (en) | Voice-controlled account access over a telephone network | |
EP0932885B1 (en) | Speaker verification method | |
US5297194A (en) | Simultaneous speaker-independent voice recognition and verification over a telephone network | |
US6691089B1 (en) | User configurable levels of security for a speaker verification system | |
US7142091B2 (en) | Self-authenticating identification substrate with encoded packet output | |
US6389397B1 (en) | User identification system using improved voice print identification processing | |
US20030074201A1 (en) | Continuous authentication of the identity of a speaker | |
EP0953972A2 (en) | Simultaneous speaker-independent voice recognition and verification over a telephone network | |
US20080208580A1 (en) | Method and Dialog System for User Authentication | |
CN1099893A (en) | Speaker verification system and process | |
US20030200447A1 (en) | Identification system | |
EP2368213A2 (en) | Biometric identity verification | |
US20020191765A1 (en) | Acoustic encoding of dynamic identification codes | |
CN107147499A (en) | The method and system verified using phonetic entry | |
WO1998054695A1 (en) | Method of accessing a dial-up service | |
US6349279B1 (en) | Method for the voice recognition of a speaker using a predictive model, particularly for access control applications | |
JP2000293491A (en) | Information terminal machine | |
Lapere et al. | User authentication in mobile telecommunication environments using voice biometrics and smartcards | |
US20110044433A1 (en) | Method of generating a temporarily limited and/or usage limited means and/or status, method of obtaining a temporarily limited and/or usage limited means and/or status, corresponding system and computer readable medium | |
KR20070020477A (en) | Method and dialog system for user authentication | |
JP2004514308A (en) | How to identify a caller under a telephone service operator | |
Shaw | Voice verification—Authenticating remote users over the telephone |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
MKLA | Lapsed |