WO1999026233A2 - Hardware sharing in a speech-based intercommunication system - Google Patents
Hardware sharing in a speech-based intercommunication system Download PDFInfo
- Publication number
- WO1999026233A2 WO1999026233A2 PCT/IB1998/001651 IB9801651W WO9926233A2 WO 1999026233 A2 WO1999026233 A2 WO 1999026233A2 IB 9801651 W IB9801651 W IB 9801651W WO 9926233 A2 WO9926233 A2 WO 9926233A2
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- speech
- items
- recognized
- assigning
- understanding
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/26—Speech to text systems
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L15/00—Speech recognition
- G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
Definitions
- the invention relates to a method for operating a multistation intercommunication system provided with human speech recognition.
- US Patent 5,471,521 describes a system in which a first computer handles an incoming telephone call, whereas a second computer performs the desired technical processing.
- Various server classes may be present.
- the present inventor has recognized a need in mass communication systems that accommodate many distributed subscribers, to allocate available facilities in an efficient manner, whilst recognizing the various levels in speech processing complexity and the frequent change of processing dynamics between various such levels on short notice. Further, the system should provide high reliability, and therefore be able to reconfigure its topology automatically.
- the invention also relates to a system arranged for executing a method as claimed in Claim 1.
- the invention also relates to a subsystem facility arranged for operating in a method context as claimed in Claim 1, and/ or as part of a system as claimed in Claim 2. Further advantageous aspects of the invention are recited in dependent Claims.
- Figure 1 a system diagram of the present invention
- Figure 2 a block diagram of a requester station
- Figure 3 a block diagram of a requester station
- Figure 4 a block diagram of stations and server stations
- Figure 5 a distributed network broker device.
- Figure 1 is a system diagram of the present invention.
- a physical network 22 has been shown in the form of a ring.
- the organization of the network is generally irrelevant for the invention.
- network protocols have been ignored.
- the user stations are suitable for receiving user person speech, and if required, also for outputting machine-generated speech or other types of simulated human speech, such as from a tape recording.
- a user station may be an unattended gateway into a telephone network.
- the system output may be in the form of a character display.
- the overall number of stations may go up to the million's range, of which at any instant several thousands may be operative in an actual dialog.
- the dialog may pertain to an information system, wherein the user undertakes to access a large data base 20.
- Another field of use may relate to an ordering service for items such as train tickets, or to a mass interview system, wherein the system poses questions and check answers as to their cognitive content.
- the dialog may from both sides relate to information that has an uncertain content or structure towards the other side, and wherein based on the outcome of the dialog the system will make a relevant selection.
- the analog speech is received in the applicable front end device or receiver station, and converted into a stream of digital codes that allow easy transfer on network 22.
- the terminals may directly receive digital coded speech, e.g. from an ISDN telephone network.
- speech recognition stations 36-40 are arranged for receiving strings of digital codes and for using word models, language models and possibly further models to map the stream of speech on a destination sequence of words, phonemes or other items.
- speech understanding subsystems 42-46 are arranged for receiving the string of words etcetera so recognized, and for using one or more dialog models to map the stream of recognized words on stringed information, that has such content as to be relevant in the actual progress of the dialog.
- the system may present some kind of "failed" indication and exhort the user person to change tactics, such as to repeat or to reformulate an earlier utterance.
- the user person will eventually have presented some sensible speech information, to which system 20 may present some output that would be suitable in the context of the dialog.
- the output may be a repartee to a user person statement, a solution to a problem, a verisimilar item such as one that indicates to a user what has indeed been understood by the system, or a further inquisitive statement.
- still further types of answer are feasible.
- the assigning of the various tasks to the elements of distributed facility will be done by the system as a whole and in a distributed manner, the user applications being passive in this respect, apart from their signalling that some assistance is necessary on a particular level of complexity or functionality. After a particular processing facility has been assigned to the application in question, the user station may forward the information to be processed.
- Figure 2 is a block diagram of a requester station 60 that may be closely associated to a particular user station or front end station.
- the user person is linked by bidirectional speech channel 50 to the system.
- the speech is bidirectionally converted by a voice input subsystem 52 and by a voice output subsystem 54.
- the converted speech information is forwarded to speech recognition server 62.
- the recognized speech is sent back to local station 60, and subsequently locally processed in speech understanding module 56.
- the speech so understood is sent to block 58, which represents the actual application, and which then may control the output line of connection 50.
- a server machine may host several speech recognizer instances, and therefore, be capable of providing service to multiple clients simultaneously, all operating under the constraint of real-time. Furtheremore, because users talk only a fraction of total dialog time, a recognition server instance can be shared among multiple clients. Realtime reacting on a user utterance may have a delay corresponding to human subjective expectations, that may well be in the order of a tenth of a second. Furthermore, the client system shown may be dedicated to handle the I/O traffic, such as voice data to multiple telephone lines, database access, and the application program.
- Figure 3 is an interactivity diagr.am of the system, based on a two-sided dialog.
- the bottom line indicates that upon detecting an incipient dialog, such as by a user taking off a telephone mouthpiece, the system will output a greeting statement, and possibly a first question or exhortation statement.
- the top line indicates that the user person may then come up with a first question or with a first answer, in speech.
- the bottom line indicates that in reaction thereon the system presents a further statement, question, or other speech item to the user. This may be followed by a further utterance from the user on the top line.
- the system will present a final amount of information or affirm the user request. Then it takes leave from the user person.
- Figure 4 shows an association of user stations such as 92 and server stations such as 94 that by means of selectors 96, 98 are connected to network 100. If a speech recognizer facility is hosted in a network environment, it may be shared among different dialogs, such as in order to utilize computer power during pauses in another dialog. With such scenario, the number of speech recognizers realized in hardware or software may be much less than the actual number of simultaneously active dialogs without violating the constraint for recognition in real-time.
- the speech recognizer is assigned to an application dialog on a per-utterance basis, but generally not assigned permanently to a particular dialog.
- the voice data stream is routed to an available voice recognizer.
- the recognizer then activates an appropriate recognition context, such as language model and lexicon, each time a new utterance is being assigned to that particular server.
- an appropriate recognition context such as language model and lexicon
- each utter.ance may be evaluated on a different server, and each speech recognition server may receive consecutive utterances from various different client systems and/or dialogs.
- they may each offer several parallel speech recognizer processes, operating under the real-time constraint.
- clients may serve multiple parallel dialogs. In this scenario, the utterance-based routing offers the greatest flexibility in utilizing the available computing facilities.
- Figure 5 shows a distributed broker organization with respect to network 110.
- the speech recognizers may be collected on server systems 116, 118, that are connected to the application client systems 112, 114, over the network.
- the network organization has a respective local network broker in each of the four systems shown which are the entities responsible for coordinating the requesters and the resources. If a particular dialog on a particular client system needs a speech recognizer, because a speaker has started an utterance, the broker in question undertakes to find an available speech recognizer that may be located on an arbitrary server system in the network. The broker will then route the voice data stream to that particular speech recognizer entity and will return the resulting wordgraph back to the dialog application on the client system.
- the network broker is a completely decentralized structure. It uses an automatic dynamic configuration mechanism that can adapt to any currently existing configuration of client and server systems. Additional server and client stations may be added to the environment without the need to disrupt or to make any changes to the previously existing systems. Upcoming clients may immediately use the available servers, and upcoming servers will be immediately considered by the clients for use. If a client or server system fails or is switched off, then only the dialogs handled by this particular machine will be affected. The remainder of the configuration will automatically reconfigure to operate without the component that has been removed.
- the network broker consists of two sorts of entities, one residing on the client side .and one residing on the speech recognition server side. Since each such entity deals with multiple entities of its counterpart, there is a many -to-many relationship between broker entities. Each network broker may manage multiple dialogs or speech recognizers.
- the speech recognizers are assembled on server systems, that are connected to the application client systems over the network.
- the network broker is the entity responsible for coordinating the requesters and resources. If a dialog on a client system has the need for a speech recognizer, the broker will undertake to find an available speech recognizer on any server system present in the network.
- a simple statistical method is used to assign an appropriate resource.
- the method for load distribution ensures that the real-time constraint for speech recognition is observed, that is, no more simultaneous utterances should be assigned to a recognition server system than could be evaluated in real-time.
- the risk for conflicting allocations from multiple clients is minimized by a random selection method. Different processor resource requirements of various utterances are also handled by the load distribution without the need for estimate calculations.
- the method has the following advantages:
- Reserved recognizers are configured on the servers that may be assigned in congestion situations, even if those assignments would violate the real-time capability of that particular server.
- the load distribution algorithm ensures that reserved resources will then be assigned only in exceptional situations, either when no other real-time capable recognizer is available in the network, or if a concurrent request occurs for the last real-time capable resource of a server.
- a particular advantage of the remote and distributed processing according to the invention is that such system is nearly full-proof, because no effort is necessary for setting up the configuration.
Abstract
Description
Claims
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP52798499A JP2001508200A (en) | 1997-11-14 | 1998-10-19 | Method and system for selective hardware sharing voice processing at multiple levels in a voice-based intercommunication system |
EP98946662A EP0954855B1 (en) | 1997-11-14 | 1998-10-19 | Method and system arranged for selective hardware sharing in a speech-based intercommunication system with speech processing on plural levels of relative complexity |
DE69814819T DE69814819T2 (en) | 1997-11-14 | 1998-10-19 | METHOD AND SYSTEM FOR SHARED USE OF HARDWARE IN A VOICE-BASED COMMUNICATION SYSTEM WITH LANGUAGE PROCESSING AT DIFFERENT RELATIVE COMPLEXITY LEVELS |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP97203554 | 1997-11-14 | ||
EP97203554.7 | 1997-11-14 |
Publications (2)
Publication Number | Publication Date |
---|---|
WO1999026233A2 true WO1999026233A2 (en) | 1999-05-27 |
WO1999026233A3 WO1999026233A3 (en) | 1999-07-22 |
Family
ID=8228925
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/IB1998/001651 WO1999026233A2 (en) | 1997-11-14 | 1998-10-19 | Hardware sharing in a speech-based intercommunication system |
Country Status (5)
Country | Link |
---|---|
US (1) | US6327568B1 (en) |
EP (1) | EP0954855B1 (en) |
JP (1) | JP2001508200A (en) |
DE (1) | DE69814819T2 (en) |
WO (1) | WO1999026233A2 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001004876A1 (en) * | 1999-07-13 | 2001-01-18 | British Telecommunications Public Limited Company | Distributed object oriented architecture for speech understanding |
EP1209662A2 (en) * | 2000-11-27 | 2002-05-29 | Canon Kabushiki Kaisha | Client-server based speech recognition |
Families Citing this family (69)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7174299B2 (en) * | 1995-08-18 | 2007-02-06 | Canon Kabushiki Kaisha | Speech recognition system, speech recognition apparatus, and speech recognition method |
US7003463B1 (en) | 1998-10-02 | 2006-02-21 | International Business Machines Corporation | System and method for providing network coordinated conversational services |
WO2000058946A1 (en) * | 1999-03-26 | 2000-10-05 | Koninklijke Philips Electronics N.V. | Client-server speech recognition |
US20050261907A1 (en) | 1999-04-12 | 2005-11-24 | Ben Franklin Patent Holding Llc | Voice integration platform |
US6408272B1 (en) * | 1999-04-12 | 2002-06-18 | General Magic, Inc. | Distributed voice user interface |
US20050091057A1 (en) * | 1999-04-12 | 2005-04-28 | General Magic, Inc. | Voice application development methodology |
US7330815B1 (en) | 1999-10-04 | 2008-02-12 | Globalenglish Corporation | Method and system for network-based speech recognition |
US6442519B1 (en) * | 1999-11-10 | 2002-08-27 | International Business Machines Corp. | Speaker model adaptation via network of similar users |
US7050977B1 (en) | 1999-11-12 | 2006-05-23 | Phoenix Solutions, Inc. | Speech-enabled server for internet website and method |
US6615172B1 (en) | 1999-11-12 | 2003-09-02 | Phoenix Solutions, Inc. | Intelligent query engine for processing voice based queries |
US7392185B2 (en) | 1999-11-12 | 2008-06-24 | Phoenix Solutions, Inc. | Speech based learning/training system using semantic decoding |
US6633846B1 (en) * | 1999-11-12 | 2003-10-14 | Phoenix Solutions, Inc. | Distributed realtime speech recognition system |
US6665640B1 (en) | 1999-11-12 | 2003-12-16 | Phoenix Solutions, Inc. | Interactive speech based learning/training system formulating search queries based on natural language parsing of recognized user queries |
US9076448B2 (en) | 1999-11-12 | 2015-07-07 | Nuance Communications, Inc. | Distributed real time speech recognition system |
US7725307B2 (en) | 1999-11-12 | 2010-05-25 | Phoenix Solutions, Inc. | Query engine for processing voice based queries including semantic decoding |
US6757362B1 (en) * | 2000-03-06 | 2004-06-29 | Avaya Technology Corp. | Personal virtual assistant |
US7366673B2 (en) * | 2001-06-15 | 2008-04-29 | International Business Machines Corporation | Selective enablement of speech recognition grammars |
US8214196B2 (en) | 2001-07-03 | 2012-07-03 | University Of Southern California | Syntax-based statistical translation model |
US6950795B1 (en) | 2001-10-11 | 2005-09-27 | Palm, Inc. | Method and system for a recognition system having a verification recognition system |
US7146321B2 (en) * | 2001-10-31 | 2006-12-05 | Dictaphone Corporation | Distributed speech recognition system |
US7133829B2 (en) * | 2001-10-31 | 2006-11-07 | Dictaphone Corporation | Dynamic insertion of a speech recognition engine within a distributed speech recognition system |
US20030144837A1 (en) * | 2002-01-29 | 2003-07-31 | Basson Sara H. | Collaboration of multiple automatic speech recognition (ASR) systems |
WO2004001623A2 (en) | 2002-03-26 | 2003-12-31 | University Of Southern California | Constructing a translation lexicon from comparable, non-parallel corpora |
US7292975B2 (en) * | 2002-05-01 | 2007-11-06 | Nuance Communications, Inc. | Systems and methods for evaluating speaker suitability for automatic speech recognition aided transcription |
US7236931B2 (en) | 2002-05-01 | 2007-06-26 | Usb Ag, Stamford Branch | Systems and methods for automatic acoustic speaker adaptation in computer-assisted transcription systems |
US7797159B2 (en) * | 2002-09-16 | 2010-09-14 | Movius Interactive Corporation | Integrated voice navigation system and method |
US7571100B2 (en) * | 2002-12-03 | 2009-08-04 | Speechworks International, Inc. | Speech recognition and speaker verification using distributed speech processing |
US8548794B2 (en) | 2003-07-02 | 2013-10-01 | University Of Southern California | Statistical noun phrase translation |
US8296127B2 (en) | 2004-03-23 | 2012-10-23 | University Of Southern California | Discovery of parallel text portions in comparable collections of corpora and training using comparable texts |
US8666725B2 (en) | 2004-04-16 | 2014-03-04 | University Of Southern California | Selection and use of nonstatistical translation components in a statistical machine translation framework |
KR100636317B1 (en) | 2004-09-06 | 2006-10-18 | 삼성전자주식회사 | Distributed Speech Recognition System and method |
KR100695127B1 (en) | 2004-10-08 | 2007-03-14 | 삼성전자주식회사 | Multi-Layered speech recognition apparatus and method |
WO2006042321A2 (en) | 2004-10-12 | 2006-04-20 | University Of Southern California | Training for a text-to-text application which uses string to tree conversion for training and decoding |
US8024194B2 (en) * | 2004-12-08 | 2011-09-20 | Nuance Communications, Inc. | Dynamic switching between local and remote speech rendering |
US8886517B2 (en) | 2005-06-17 | 2014-11-11 | Language Weaver, Inc. | Trust scoring for language translation systems |
US8676563B2 (en) | 2009-10-01 | 2014-03-18 | Language Weaver, Inc. | Providing human-generated and machine-generated trusted translations |
US7389222B1 (en) * | 2005-08-02 | 2008-06-17 | Language Weaver, Inc. | Task parallelization in a text-to-text system |
US8032372B1 (en) | 2005-09-13 | 2011-10-04 | Escription, Inc. | Dictation selection |
US10319252B2 (en) | 2005-11-09 | 2019-06-11 | Sdl Inc. | Language capability assessment and training apparatus and techniques |
US8943080B2 (en) | 2006-04-07 | 2015-01-27 | University Of Southern California | Systems and methods for identifying parallel documents and sentence fragments in multilingual document collections |
US8886518B1 (en) | 2006-08-07 | 2014-11-11 | Language Weaver, Inc. | System and method for capitalizing machine translated text |
US8433556B2 (en) | 2006-11-02 | 2013-04-30 | University Of Southern California | Semi-supervised training for statistical word alignment |
US9122674B1 (en) | 2006-12-15 | 2015-09-01 | Language Weaver, Inc. | Use of annotations in statistical machine translation |
US8468149B1 (en) | 2007-01-26 | 2013-06-18 | Language Weaver, Inc. | Multi-lingual online community |
US8615389B1 (en) | 2007-03-16 | 2013-12-24 | Language Weaver, Inc. | Generation and exploitation of an approximate language model |
US8831928B2 (en) | 2007-04-04 | 2014-09-09 | Language Weaver, Inc. | Customizable machine translation service |
US8825466B1 (en) | 2007-06-08 | 2014-09-02 | Language Weaver, Inc. | Modification of annotated bilingual segment pairs in syntax-based machine translation |
US8019608B2 (en) * | 2008-08-29 | 2011-09-13 | Multimodal Technologies, Inc. | Distributed speech recognition using one way communication |
US8494857B2 (en) | 2009-01-06 | 2013-07-23 | Regents Of The University Of Minnesota | Automatic measurement of speech fluency |
US8990064B2 (en) | 2009-07-28 | 2015-03-24 | Language Weaver, Inc. | Translating documents based on content |
US8380486B2 (en) | 2009-10-01 | 2013-02-19 | Language Weaver, Inc. | Providing machine-generated translations and corresponding trust levels |
US8346549B2 (en) * | 2009-12-04 | 2013-01-01 | At&T Intellectual Property I, L.P. | System and method for supplemental speech recognition by identified idle resources |
US10417646B2 (en) | 2010-03-09 | 2019-09-17 | Sdl Inc. | Predicting the cost associated with translating textual content |
US9246914B2 (en) | 2010-07-16 | 2016-01-26 | Nokia Technologies Oy | Method and apparatus for processing biometric information using distributed computation |
US20120078635A1 (en) * | 2010-09-24 | 2012-03-29 | Apple Inc. | Voice control system |
US10049669B2 (en) | 2011-01-07 | 2018-08-14 | Nuance Communications, Inc. | Configurable speech recognition system using multiple recognizers |
US8810368B2 (en) | 2011-03-29 | 2014-08-19 | Nokia Corporation | Method and apparatus for providing biometric authentication using distributed computations |
US11003838B2 (en) | 2011-04-18 | 2021-05-11 | Sdl Inc. | Systems and methods for monitoring post translation editing |
US8694303B2 (en) | 2011-06-15 | 2014-04-08 | Language Weaver, Inc. | Systems and methods for tuning parameters in statistical machine translation |
US8886515B2 (en) | 2011-10-19 | 2014-11-11 | Language Weaver, Inc. | Systems and methods for enhancing machine translation post edit review processes |
US8972263B2 (en) * | 2011-11-18 | 2015-03-03 | Soundhound, Inc. | System and method for performing dual mode speech recognition |
US8942973B2 (en) | 2012-03-09 | 2015-01-27 | Language Weaver, Inc. | Content page URL translation |
US9576593B2 (en) | 2012-03-15 | 2017-02-21 | Regents Of The University Of Minnesota | Automated verbal fluency assessment |
US10261994B2 (en) | 2012-05-25 | 2019-04-16 | Sdl Inc. | Method and system for automatic management of reputation of translators |
WO2014055076A1 (en) | 2012-10-04 | 2014-04-10 | Nuance Communications, Inc. | Improved hybrid controller for asr |
US9152622B2 (en) | 2012-11-26 | 2015-10-06 | Language Weaver, Inc. | Personalized machine translation via online adaptation |
US9213694B2 (en) | 2013-10-10 | 2015-12-15 | Language Weaver, Inc. | Efficient online domain adaptation |
US10971157B2 (en) | 2017-01-11 | 2021-04-06 | Nuance Communications, Inc. | Methods and apparatus for hybrid speech recognition processing |
US10410635B2 (en) | 2017-06-09 | 2019-09-10 | Soundhound, Inc. | Dual mode speech recognition |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4955054A (en) * | 1988-10-05 | 1990-09-04 | Precision Software Incorporated | Integrated telecommunication system with improved digital voice response |
US5349526A (en) * | 1991-08-07 | 1994-09-20 | Occam Research Corporation | System and method for converting sentence elements unrecognizable by a computer system into base language elements recognizable by the computer system |
US5471521A (en) * | 1993-07-29 | 1995-11-28 | International Business Machines Corporation | Distributed system for call processing |
US5553119A (en) * | 1994-07-07 | 1996-09-03 | Bell Atlantic Network Services, Inc. | Intelligent recognition of speech signals using caller demographics |
-
1998
- 1998-10-19 WO PCT/IB1998/001651 patent/WO1999026233A2/en active IP Right Grant
- 1998-10-19 EP EP98946662A patent/EP0954855B1/en not_active Expired - Lifetime
- 1998-10-19 JP JP52798499A patent/JP2001508200A/en active Pending
- 1998-10-19 DE DE69814819T patent/DE69814819T2/en not_active Expired - Lifetime
- 1998-11-10 US US09/189,528 patent/US6327568B1/en not_active Expired - Lifetime
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4955054A (en) * | 1988-10-05 | 1990-09-04 | Precision Software Incorporated | Integrated telecommunication system with improved digital voice response |
US5349526A (en) * | 1991-08-07 | 1994-09-20 | Occam Research Corporation | System and method for converting sentence elements unrecognizable by a computer system into base language elements recognizable by the computer system |
US5471521A (en) * | 1993-07-29 | 1995-11-28 | International Business Machines Corporation | Distributed system for call processing |
US5553119A (en) * | 1994-07-07 | 1996-09-03 | Bell Atlantic Network Services, Inc. | Intelligent recognition of speech signals using caller demographics |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2001004876A1 (en) * | 1999-07-13 | 2001-01-18 | British Telecommunications Public Limited Company | Distributed object oriented architecture for speech understanding |
EP1209662A2 (en) * | 2000-11-27 | 2002-05-29 | Canon Kabushiki Kaisha | Client-server based speech recognition |
EP1209662A3 (en) * | 2000-11-27 | 2004-01-28 | Canon Kabushiki Kaisha | Client-server based speech recognition |
US7099824B2 (en) | 2000-11-27 | 2006-08-29 | Canon Kabushiki Kaisha | Speech recognition system, speech recognition server, speech recognition client, their control method, and computer readable memory |
Also Published As
Publication number | Publication date |
---|---|
EP0954855A2 (en) | 1999-11-10 |
JP2001508200A (en) | 2001-06-19 |
DE69814819T2 (en) | 2004-04-01 |
WO1999026233A3 (en) | 1999-07-22 |
EP0954855B1 (en) | 2003-05-21 |
US6327568B1 (en) | 2001-12-04 |
DE69814819D1 (en) | 2003-06-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
EP0954855B1 (en) | Method and system arranged for selective hardware sharing in a speech-based intercommunication system with speech processing on plural levels of relative complexity | |
US7751551B2 (en) | System and method for speech-enabled call routing | |
US7917364B2 (en) | System and method using multiple automated speech recognition engines | |
US6119087A (en) | System architecture for and method of voice processing | |
EP1617410B1 (en) | Distributed speech recognition for mobile devices | |
US5574784A (en) | Dynamic admission control for telecommunications relay service with text-to-speech synthesis | |
US7006512B2 (en) | Apparatus and methods for managing queues on a mobile device system | |
US9350860B2 (en) | Voice interactive service system and method for providing different speech-based services | |
CN110392168B (en) | Call processing method, device, server, storage medium and system | |
ATE257992T1 (en) | MULTIMEDIA CONFERENCE ON PARALLEL NETWORKS | |
US8494127B2 (en) | Systems and methods for processing audio using multiple speech technologies | |
EP1451808B1 (en) | Method of operating a barge-in dialogue system | |
US9060060B2 (en) | Efficient utilization of IVR resources supplied to switching systems | |
US20040042591A1 (en) | Method and system for the processing of voice information | |
US7552225B2 (en) | Enhanced media resource protocol messages | |
US6055437A (en) | Dynamic allocation of communication resources | |
JP6689953B2 (en) | Interpreter service system, interpreter service method, and interpreter service program | |
CN112583984A (en) | Agent allocation method, device, system, equipment and medium based on voice interaction | |
EP2293290A1 (en) | Voice interactive service system and method for providing different speech-based services | |
KR102346110B1 (en) | Method and device for providing consultation service using artificial intelligence | |
CN112466283B (en) | Cooperative software voice recognition system | |
EP1619662A1 (en) | Speech recognition system | |
CN114330379A (en) | Multitask translation system based on artificial intelligence | |
CN115604398A (en) | IVR service node skipping method and system | |
Huang et al. | Performance Analysis of Cost Optimization Algorithms In Multimedia Gateway Call Routing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AK | Designated states |
Kind code of ref document: A2 Designated state(s): JP |
|
AL | Designated countries for regional patents |
Kind code of ref document: A2 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
WWE | Wipo information: entry into national phase |
Ref document number: 1998946662 Country of ref document: EP |
|
ENP | Entry into the national phase |
Ref country code: JP Ref document number: 1999 527984 Kind code of ref document: A Format of ref document f/p: F |
|
AK | Designated states |
Kind code of ref document: A3 Designated state(s): JP |
|
AL | Designated countries for regional patents |
Kind code of ref document: A3 Designated state(s): AT BE CH CY DE DK ES FI FR GB GR IE IT LU MC NL PT SE |
|
121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
WWP | Wipo information: published in national office |
Ref document number: 1998946662 Country of ref document: EP |
|
WWG | Wipo information: grant in national office |
Ref document number: 1998946662 Country of ref document: EP |