USRE40458E1 - System and method for using a correspondence table to compress a pronunciation guide - Google Patents
System and method for using a correspondence table to compress a pronunciation guide Download PDFInfo
- Publication number
- USRE40458E1 USRE40458E1 US10/342,435 US34243503A USRE40458E US RE40458 E1 USRE40458 E1 US RE40458E1 US 34243503 A US34243503 A US 34243503A US RE40458 E USRE40458 E US RE40458E
- Authority
- US
- United States
- Prior art keywords
- correspondence
- dictionary
- pronunciation
- entry
- symbol
- 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 - Lifetime
Links
Images
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
- G10L15/08—Speech classification or search
- G10L15/18—Speech classification or search using natural language modelling
- G10L15/183—Speech classification or search using natural language modelling using context dependencies, e.g. language models
- G10L15/187—Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
-
- H—ELECTRICITY
- H03—ELECTRONIC CIRCUITRY
- H03M—CODING; DECODING; CODE CONVERSION IN GENERAL
- H03M7/00—Conversion of a code where information is represented by a given sequence or number of digits to a code where the same, similar or subset of information is represented by a different sequence or number of digits
- H03M7/30—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction
- H03M7/3084—Compression; Expansion; Suppression of unnecessary data, e.g. redundancy reduction using adaptive string matching, e.g. the Lempel-Ziv method
Definitions
- This invention relates generally to data compression, and more particularity to a system and method using correspondence techniques to compress a pronunciation guide.
- RAM Computer Random Access Memory
- disk space are becoming more available and affordable in desktop computer systems.
- a typical desktop computer system currently provides on the order of sixteen megabytes of RAM and one gigabyte of hard disk memory. This increasing availability allows programmers the freedom to create application programs and data files which occupy several megabytes of computer memory. However, minimizing the size of data files remains important for optimizing system performance and use of memory resources.
- a pronunciation dictionary which includes dictionary words for a language such as American English and dictionary phonemes (phonetic sounds) representing the pronunciation of each of the dictionary words.
- a typical uncompressed pronunciation dictionary occupies up to about ten megabytes of memory.
- a pronunciation dictionary can be compressed using certain symbols to replace redundant data. For example, a typical compression technique assigns symbols to represent particular patterns of redundant data such as multiple zeros or one. Multiple compression techniques may be performed successively to eliminate more redundancies and compress data further. Accordingly, a pronunciation dictionary may be compressed to around thirty percent or less of its original size.
- the present invention overcomes limitations and deficiencies of previous systems by providing a new system and method for compressing a pronunciation guide such as a pronunciation dictionary.
- the system substitutes a single symbol for some text and its pronunciation, and includes a central processing unit (CPU) and memory.
- the memory stores a compression system including parsing routines, a correspondence table, a matching system, a decoder table and a decoder system.
- the parsing routines extract a dictionary entry, which comprises a dictionary word and corresponding dictionary phonemes representing the pronunciation of the dictionary word, from an uncompressed pronunciation dictionary also stored in the memory.
- the correspondence table is made up of correspondence sets, each of which has a text entry, a phoneme entry representing the pronunciation of the text entry, and a set-identifying symbol (i.e., a number).
- the matching system attempts to find all correspondence sets that match text and phoneme combinations of the dictionary entry.
- the matching engine selects the best matches and adds the representative correspondence symbol set to a compressed pronunciation dictionary. If a match is not found, then the matching system considers characters silent and/or phonemes unmatched, and assigns special symbols to be added to the compressed pronunciation dictionary. The matching system adds decoder code sets to a decoder table for translating the special symbols back to characters or phonemes.
- the decoder system uses the compressed pronunciation dictionary and decoder code sets to generate corresponding phonemes for selected text. These phonemes can be used in processes such as speech recognition, speech synthesis, language translation, foreign language learning, spell checking, etc.
- the present invention provides a method for compressing a pronunciation dictionary.
- the method creates a correspondence table comprised of correspondence sets, determines which correspondence sets match a dictionary word and its corresponding dictionary phonemes, and adds the correspondence symbols as compressed data entries to a compressed pronunciation dictionary.
- the invention also provides a method for using the compressed dictionary and decoder code sets to generate phonemes from input text.
- FIG. 1 is a block diagram of a computer system including a compression system in accordance with the present invention
- FIG. 2 is a block diagram showing dictionary compressing components of the FIG. 1 compression system used to construct a compressed pronunciation dictionary
- FIG. 3 is a text-phoneme correspondence table for American English
- FIG. 4 is a block diagram showing components of the FIG. 1 compression system used in application of the compressed dictionary
- FIG. 5 is a flowchart illustrating the preferred method for compressing a pronunciation dictionary and using the compressed pronunciation dictionary for decoding selected text
- FIG. 6 is a flowchart further illustrating steps of the preferred method for compressing an entry from a pronunciation dictionary
- FIG. 7 is an example phoneme set for American English.
- FIG. 1 is a block diagram of a computer system 100 including a compression system 180 in accordance with the present invention.
- Computer system 100 is preferably based on a computer such as a Power Macintosh manufactured by Apple Computer, Inc. of Cupertino, Calif.
- Computer system 100 includes a Central Processing Unit (CPU) 110 , an input device 120 such as a keyboard and mouse or scanner, and an output device 130 such as a Cathode Ray Tube (CRT) or audio speaker, a Random Access Memory (RAM) 150 , a data storage (hard disk) 160 , an operating system 170 and a compression system 180 , each coupled to sional bus 140 .
- CPU Central Processing Unit
- input device 120 such as a keyboard and mouse or scanner
- an output device 130 such as a Cathode Ray Tube (CRT) or audio speaker
- RAM Random Access Memory
- data storage hard disk
- operating system 170 operating system 170
- compression system 180 each coupled to sional bus 140 .
- Operating system 170 is a program that controls processing by CPU 110 , and is typically stored in data storage 160 and loaded into RAM 150 during computer system initialization.
- CPU 110 has access to RAM 150 for storing intermediate results and miscellaneous data.
- Compression system 180 includes a dictionary compressing program 215 for compressing a pronunciation dictionary, and a decoder system program 420 for subsequently processing text and using the compressed pronunciation dictionary to retrieve phonemes representing the pronunciation of the text. Compression system 180 is also typically stored in data storage 160 and loaded into RAM 150 prior to execution by CPU 110 .
- FIG. 2 is a block diagram illustrating dictionary compressing program 215 of compression system 180 , used with a pronunciation dictionary 210 to construct a compressed pronunciation dictionary 270 .
- Pronunciation dictionary 210 is preferably a conventional compilation of dictionary words and of corresponding dictionary phonemes in a specified format expressing proper pronunciation of the dictionary words in, for example, American English. Suitable pronunciation dictionaries include the Oxford-American® Dictionary.
- FIG. 7 illustrates an example phoneme list 700 for American English. List 700 includes thirty-eight phonemes and an example word which uses each phoneme. For example, the phoneme “AE” provides the sound made by the letter “a” as in the word “bat.” Other phonemes or sound-representative symbols can alternatively be used.
- Dictionary compressing program 215 includes parsing routines 220 , a data buffer 230 , a correspondence table 240 , a matching system 250 and a tuning function 260 .
- Parsing routines 220 extract a dictionary entry, which includes a dictionary word and at least one dictionary phoneme representing the pronunciation of the word, from pronunciation dictionary 210 .
- the extracted dictionary entry includes the dictionary word “enough” and the corresponding phonemes “IH n UX f”.
- Parsing routines 220 store the extracted dictionary entry in data buffer 230 , which may be a portion of RAM 150 (FIG. 1 ).
- Correspondence table 240 lists phoneme entries and text entries, for example, as shown for American English in FIG. 3. A text entry, a phoneme entry and a symbol together form a correspondence set, and a plurality of correspondence sets forms correspondence table 240 . Each correspondence set includes an identifier, referred to as a correspondence symbol, which may be simply the address of the set in correspondence table 240 .
- Correspondence table 240 preferably includes correspondence sets for most practical combinations of correspondence text and phonemes in a given language.
- a correspondence table 240 which included every conceivable correspondence set would be inefficient because increasing the number of code sets degrades compression by subsequent compression techniques. Therefore, a tuning function 260 facilities eliminating the less useful correspondence sets from, and adding more useful correspondence sets to, correspondence table 240 .
- the utility or productivity of a correspondence set is determined by the number of dictionary entries it helps to compress.
- a pronunciation dictionary may be compressed a first time, and the compressed dictionary examined to determine if any correspondence sets are used less than, say, five times. If so, the less used and thus unproductive correspondence sets can be eliminated or modified. Further, since phonemes typically have corresponding text, cases where a phoneme does not match any text may indicate a need to add a correspondence set.
- Matching system 250 is a program which reads the extracted dictionary entry from buffer 230 , retrieves correspondence sets from correspondence table 240 , and compares the dictionary entry with the correspondence sets. More particularly, matching system 250 attempts to match the correspondence sets with combinations of phonemes and characters from the dictionary entry. If matches are made, matching system 250 assigns the correspondence symbol associated with the “best” matching correspondence set as a compressed data entry, as described below with reference to FIG. 6 . If a match cannot be made for a particular dictionary character or phoneme, matching system 250 assigns, as compressed data entries, special symbols to represent silent characters or unmatched phonemes. The one or more compressed data entries representing an entire dictionary entry forms a “symbol set.” The symbol sets for an entire pronunciation dictionary collectively form the “compressed pronunciation dictionary” 270 .
- Matching system 250 further generates decoder code sets for de-compressing compressed pronunciation dictionary 270 , and adds the code sets to a “decoder table” 280 .
- Each decoder code set includes a decoder text entry, a corresponding decoder phoneme entry, and a decoder set-identifying symbol equivalent to a correspondence symbol of correspondence table 240 .
- Decoder table 280 is like correspondence table 240 except that decoder table 280 also includes decoder sets for the silent text characters and the unmatched phonemes. The decoder sets are described in more detail with reference to FIGS. 4 and 5 .
- FIG. 3 shows an example correspondence table 240 for American English.
- the first column specifies correspondence phoneme entries
- the second column specifies correspondence text entries
- the third column specifies correspondence symbols.
- a correspondence text entry specifies text characters such as “e” or “ou,” and is accompanied by typically only one phonetic sound.
- a correspondence phoneme entry, such as “IH,” is expressed in the format used by pronunciation dictionary 210 , for representing the phonetic sound of each correspondence text entry. Since some text entries produce multiple sounds, a phoneme entry may represent multiple sounds such as “y UH.” Further, there may be correspondence entries which have multiple text characters and multiple phonemes, like “y UW ⁇ ieu.”
- the correspondence sets may be organized into groups of rows of like phonemes. Grouping rows based on phonemes facilitates comparisons with dictionary combinations if creating table 240 by hand.
- correspondence phoneme “AE” represents one of the possible pronunciations of correspondence text entry “ai”, and this correspondence set is represented by the symbol “(1)”.
- the same correspondence phoneme “AE” represents one of the possible pronunciations of a different correspondence text entry, “a”, and this correspondence set is represented by the symbol “(2)”.
- correspondence phoneme “EY” represents another pronunciation of the same correspondence text entry “ai” in the first row, and this correspondence set is represented by symbol “(3)”.
- Correspondence table 240 may be generated manually, i.e. by typing the table into a computer file, or generated electronically, i.e. by computer analysis of productive phoneme-text combinations. It will be appreciated that each language, such as American English or French, would use a different correspondence table 240 .
- FIG. 4 is a block diagram illustrating the decoder system program 420 of compression system 180 , and its input and output data.
- Selected input text 410 may be stored in data storage 160 and loaded into RAM 150 for examination.
- Decoder system program 420 receives a word from selected input text 410 .
- Decoder system 420 uses the decoder table 280 codes to translate symbol sets of compressed pronunciation dictionary 270 in searching for the compressed dictionary word whose text matches the received word, and then in producing phonemes for the received word. If the dictionary compressing method compressed pronunciation dictionary 210 entries in the original alphabetical order of the dictionary words, then the symbol sets are entered in the same alphabetical order in compressed pronunciation dictionary 270 . Thus, decoder system 420 could approximate the location of the dictionary word which matches the input text word. Another embodiment of the dictionary compressing method provides an index to compressed pronunciation dictionary 270 . Further, any technique for searching a compressed file, such as a hashing function, may be used.
- decoder system 420 Upon matching a compressed dictionary word to the input text word, decoder system 420 uses the decoder table 280 codes to retrieve dictionary phonemes 430 from the matching symbol set. Alternatively, as it searches the compressed dictionary and converts symbol sets to find a dictionary word which matches the received text, decoder system 420 may also convert the symbol sets to produce phonemes at the same time.
- decoder system 420 receives the word “enough” from selected text 410 .
- Decoder system 420 uses decoder table 280 to decode symbol sets from compressed pronunciation dictionary 270 until decoding a symbol set to match the dictionary word “enough”.
- decoder system 420 uses decoder table 280 to translate the symbol set into the output data phonemes “IH n UX f” representing the pronunciation of the received text.
- FIG. 5 is a flowchart illustrating a method 500 for compressing pronunciation dictionary 210 and for using the compressed dictionary to generate representative phonemes from selected input text 410 .
- Method 500 begins in step 510 by creating a correspondence table 240 for a given language.
- Creatinc correspondence table 240 comprises the step of inputting a number of correspondence sets, each of which includes a phoneme entry expressing at least one phonetic sound and a text entry which indicates the phonetic sound or sounds, and inputting a correspondence set identifying symbol.
- Step 510 preferably includes inputting a correspondence set for each of the various text representations of all of the phonemes used in pronunciation dictionary 210 .
- the step 510 preferably further includes tuning function 260 ( FIG. 2 ) using the current version of correspondence table 240 to compress at least a portion of pronunciation dictionary 210 for determining which correspondence sets are unproductive and what other correspondence sets may be valuable if added.
- Tuning function 260 may be re-applied to optimize correspondence table 240 , thereby enabling matching system 250 to more effectively compress pronunciation dictionary 210 and enabling compressed pronunciation dictionary 270 to be further compressed by subsequent compression techniques.
- Program 215 in step 520 uses the optimized correspondence table 240 to compress pronunciation dictionary 210 . More particularly, parsing routines 220 extract a dictionary entry including a dictionary word and corresponding dictionary phonemes from pronunciation dictionary 210 , and store the dictionary entry in data buffer 230 .
- Matching system 250 selects a first phoneme from the dictionary entry, and retrieves all correspondence sets from correspondence table 240 which start with the selected dictionary phoneme to determine if a match can be made.
- Multiple dictionary characters which together constitute a correspondence text entry in correspondence table 240 are “related.” Divisions between related dictionary characters are typically harder to determine than divisions between dictionary phonemes. Also, there are fewer dictionary phonemes without corresponding dictionary characters (e.g., as in abbreviations such as “Mrs.” or “etc.”) than there are “silent” dictionary characters without phonemes. Therefore, matching system 250 preferably selects a dictionary phoneme, and attempts to match correspondence sets based on the dictionary phoneme.
- Matching system 250 compares the correspondence sets retrieved from correspondence table 240 with the dictionary entry to determine if any matches can be made. If only one match is made, matching system 250 selects the correspondence symbol associated with the matching correspondence set as the compressed data entry for compressed pronunciation dictionary 270 . If more than one match can be made, matching system 250 selects as the compressed data entry for compressed pronunciation dictionary 270 the symbol for the correspondence set corresponding to the best match. If no match can be made, matching system 250 generates special symbols to represent “silent” characters, or conversely generates special symbols to represent phonemes unmatched to dictionary text. Generation of special symbols is described in greater detail with reference to FIG. 6 . If a special symbols is generated, a decoder code set representing the association of the special. symbol to the silent character or alternatively to the unmatched phoneme is added to decoder table 280 for subsequently decoding the special symbol.
- Matching system 250 selects the next unprocessed phoneme, and repeats step 520 . until the compressed data entries have been generated for the entire dictionary entry. Examples of this process are described with reference to Examples 1-3. After all the pronunciation dictionary 210 entries have been compressed, the symbol set, which possibly includes special symbols, is added to compressed pronunciation dictionary 270 . It will be appreciated that step 510 and step 520 are typically performed by a product developer.
- Decoder system 420 in step 530 uses compressed pronunciation dictionary 270 and decoder table 280 to generate phonemes for selected text 410 .
- Decoder system 420 receives a selected word from text 410 , and then uses decoder table 280 to decode symbol sets from compressed pronunciation dictionary 270 until one of the decoded dictionary words matches the first input word.
- Decoder system 420 next uses decoder table 280 to retrieve the dictionary phonemes from the matching symbol set, and then method 500 ends for the first input word.
- Step 530 repeats for subsequently received words. It will be appreciated that step 530 is typically performed by a customer.
- FIG. 6 is a flowchart illustrating a preferred method 600 for compressing an entry from pronunciation dictionary 210 .
- Method 600 is repeated for every word in the dictionary to accomplish FIG. 5 step 520 .
- Method 600 begins in step 605 by matching system 250 reading a dictionary entry, which comprises a dictionary word and a dictionary phoneme entry representing the pronunciation of the dictionary word, from buffer 230 .
- Matching system 250 in step 610 determines whether any dictionary characters or dictionary phonemes remain unprocessed in the dictionary entry. If not, method 600 ends. Otherwise, matching system 250 in step 620 determines whether both a dictionary character and a dictionary phoneme remain.
- matching system 250 in step 630 searches correspondence table 240 for all correspondence sets that match dictionary phoneme-character combinations of the remaining portions of the dictionary entry. More particularly, selecting the next currently-unmatched phoneme, matching system 250 retrieves all correspondence sets which begin with the selected dictionary phoneme. Matching system 250 then compares these correspondence sets against the unmatched portions of the dictionary entry.
- matching system 250 in step 640 finds at least one match, then matching system 250 in step 650 selects the best match, assigns and stores symbols for any pending silent dictionary characters, and stores the correspondence symbol for the selected matching correspondence set. Method 600 then returns to step 610 .
- matching system 250 To select the best match, matching system 250 first selects from the matching sets as the tentative choice the correspondence set having the most phonemes. If there is more than one set having the most phonemes, then matching system 250 selects as the tentative choice the set that has the most phonemes and the most text characters. If there are more than one of these sets, matching system 250 just selects the first of them. The tentative choice is the best match unless matching system 250 determines one of the other sets satisfies selected criteria, suggesting that it is a better choice.
- the criteria include:
- matching system 250 in step 685 determines whether a threshold number of dictionary characters are currently assumed silent. If not, matching system 250 in step 690 considers the next dictionary character as silent, and returns to step 610 . If in step 685 a set threshold number of silent characters are pending, matching system 250 in step 695 assigns and stores a special symbol for the current phoneme and considers pending silent dictionary characters as no longer silent, i.e. re-labels the pending silent characters as unprocessed. Method 600 then returns to step 610 .
- matching system 250 determines whether it is characters or phonemes that remain. If characters remain, matching system 250 in step 670 assigns and stores special symbols for all pending silent and all remaining dictionary characters. If only phonemes remain, system 250 proceeds to step 695 and continues as explained above.
- Matching system 250 retrieves the dictionary word “enough” and the dictionary phonemes “IH n UX f” from data buffer 230 . Matching system 250 then selects the first dictionary phoneme “IH,” retrieves from exemplary table 240 ( FIG. 3 ) all correspondence sets which begin with the selected phoneme (IH ⁇ a, IH ⁇ e, IH ⁇ i, IH ⁇ o, IH ⁇ u, IH ⁇ y.), and determines if any of the correspondence sets match.
- Matching system 250 fins only one match (IH ⁇ e) and accordingly “remembers,” i.e. stores in memory, the symbol “(43)” representing the match.
- Matching system 250 selects the next unprocessed phoneme “n” and retrieves the correspondence sets (ny ⁇ gn, n ⁇ en, n ⁇ gn, n ⁇ kn, n ⁇ nn, n ⁇ n). IH n UX f e n ough Matching system 250 finds only match (n ⁇ n), and remembers the symbol “(161)” representing the only match.
- Matching system 250 selects the third phoneme “UX” and retrieves the correspondence sets (UXr ⁇ r, UX ⁇ a, UX ⁇ eu, UX ⁇ e, UX ⁇ i, UX ⁇ ou, UX ⁇ o, UX ⁇ u, UX ⁇ y). IH n U X f en o ough Matching system 250 finds two matches (UX ⁇ o and UX ⁇ ou), and selects the better match. Since UX ⁇ ou has more text characters matching system 250 selects it as the tentative best match. Matching system 250 applies the three-criteria test as described with reference to FIG. 6 to confirm the best match assumption. The other set UX ⁇ o has fewer text characters, and a phoneme remains after it is applied. However, a match cannot be made with the next currently unmatched phoneme “f” and remaining text characters “ugh.” Thus, matching system 250 selects UX ⁇ ou as the best match, and accordingly remembers the correspondence symbol “(89).”
- Matching system 250 selects the next unprocessed phoneme “f” and retrieves the correspondence sets (f ⁇ ff, f ⁇ f, f ⁇ gh, f ⁇ ph). IH n UX f enou g h Matching system 250 finds only one match (f ⁇ gh) and thus remembers “123” as representing the match. Accordingly, matching system 250 stores the symbol set “43 161 89 123” in compressed pronunciation dictionary 170 as the compressed data entry representing the dictionary word “enough” and its dictionary phonemes “IH n UX f”.
- Matching system 250 retrieves the dictionary word “answer” and the dictionary phonemes “AE n s UX r”. In a manner similar to that described in Example 1, matching system 250 matches the dictionary combination AE ⁇ a and represents it by correspondence symbol “2,” matches the dictionary combination n ⁇ n and represents it by symbol “161” and matches the dictionary combination s ⁇ s and represents it by symbol “173.” At this time, matching system 250 selects dictionary phoneme “UX” and retrieves the correspondence sets (UXr ⁇ r, UX ⁇ a, UX ⁇ eu, UX ⁇ e, UX ⁇ i, UX ⁇ ou, UX ⁇ o, UX ⁇ u, UX ⁇ y).
- Matching system 250 finds no match. Thus, matching system 250 assumes that “w” is silent.
- matching system 250 examines the correspondence sets with the remaining unprocessed dictionary entry. AE n s U X r answ e r Matching system 250 finds a match (UX ⁇ e), and thus assigns and stores a special symbol such as “221” to represent the silent dictionary character “w” and remembers the symbol “(87).” Further, matching system 250 adds the decoder code set, for example “221” w ⁇ ” wherein the empty set represents no phoneme, to decoder table 280 .
- matching stem 250 selects the dictionary phoneme “r” and retrieves the correspondence sets (r ⁇ rr, r ⁇ er, rr ⁇ r, r ⁇ r). AE n s UX r answe r Matching system 250 finds only one match (r ⁇ r), and selects the symbol “(155).” Matching system 250 adds “2 161 173 221 87 155” to compressed pronunciation dictionary 270 as a symbol set representing the word “answer” and the phonemes “AE n s UX r.”
- Matching system 250 retrieves the dictionary word “rhythm” and the dictionary phonemes “r IH D AX m,” selects the first dictionary phoneme “r” and retrieves the correspondence sets (r ⁇ rr, r ⁇ er, rr ⁇ r, r ⁇ r). r IH D AX m r hythm Matching system 250 finds only one match (r ⁇ r), and remembers the symbol “169.”
- Matching system 250 selects the next unprocessed phoneme “IH” and retrieves the correspondence sets (IH ⁇ a, IH ⁇ e, IH ⁇ i, IH ⁇ o, IH ⁇ u, IH ⁇ y).
- r I H D AX m r h ythm Matching system 250 finds no matches. Accordingly, matching system 250 assumes the “h” is silent. With the “h” silent, matching system 250 then examines the remaining portions of the dictionary entry.
- r I H D AX m rh y thm Matching system 250 finds a match (IH ⁇ y), assigns a special symbol such as “222” for silent “h” and remembers the symbol “47.”
- Matching system 250 selects the next unprocessed phoneme “D” and retrieves only correspondence set (D ⁇ th), since in this example matching system 250 is case sensitive.
- Matching system 250 finds a match and remembers the symbol “120.”
- Matching system 250 selects the next unprocessed phoneme “AX” and retrieves the correspondence sets (AXk ⁇ c, AXl ⁇ l, AXm ⁇ m, AX ⁇ a, AX ⁇ e, AX ⁇ ia, AX ⁇ i, AX ⁇ o, AX ⁇ u, AX ⁇ y, AXE ⁇ ′).
- r IH D A X m rhyth m Matching system 250 finds only one match (AXm ⁇ m), and remembers symbol “(16).” Since no other characters exist, matching system 250 adds “169 222 47 120 16” to compressed pronunciation dictionary 270 as a symbol set representing the dictionary word “rhythm” and the corresponding phonemes “r IH D AX m.”
- matching system 250 would find no match. Accordingly, matching system 250 would assume the text character “m” is silent. Since only characters would remain, matching system 250 would emit a special symbol such as “223” for current phoneme “AX” and would consider the text character “m” is no longer silent.
- Matching system 250 would then retrieve the correspondence sets (m ⁇ lm, m ⁇ mm, m ⁇ m) for phoneme “m”, would find the only match m ⁇ m, and would remember the symbol “155.” Since no other characters would exist, matching system 250 would add “169 222 47 120 223 155” to compressed pronunciation dictionary 270 as a symbol set representing the dictionary word “rhythm” and the corresponding phonemes “r IH D AX m.”
- the present invention advantageouly provides a system and method for compressing a pronunciation dictionary. This is especially useful, for example, as a precursor to other compression techniques.
- the system and method take advantage of the natural redundancy between dictionary text and dictionary phonemes. Since compression system 180 substitutes symbols for sets of dictionary words and phonemes, memory required to store the information is reduced by approximately one-third to one-half.
- each character in a word may be represented by five bits (since there are twenty-six letters in the English alphabet), and each phoneme may be represented by six bits (since there are about thirty-nine phonemes for American English as illustrated in FIG. 7 ).
- dictionary words and the set of phonemes for each dictionary word are divided by a terminator character.
- the word “enough” requires seven characters (including the terminator character) and thus occupies thirty-five bits.
- the corresponding phoneme set “IH n UX f” requires five characters (including the terminator character), and thus occupies thirty bits.
- the total memory for storing this dictionary entry is sixty-five bits.
- a decoder table 280 has about 220 correspondence sets and 220 correspondence symbols. Accordingly, eight bits are needed to represent a correspondence symbol. As illustrated in the first example, the four symbols “(43)”, “(161)”, “(89)” and “(123)” represent the word “enough” and phonemes “IH n UX f”. Thus, five symbols (including the terminator character) are needed and occupy forty bits. Forty bits provides a thirty-eight percent savings over the uncompressed sixty-five bits.
Abstract
Description
-
- (1) the other correspondence set is shorter than the current tentative choice, i.e., it has fewer phonemes or has the same number of phonemes and fewer text characters;
- (2) at least one unprocessed dictionary phoneme would remain in the dictionary entry after the non-tentative set is applied; and
- (3) there is a correspondence set that matches the next unprocessed dictionary phonemes and dictionary characters that would remain if the non-tentative set were to be applied.
If another set meets the above criteria, it becomes the tentative choice. The process repeats until all other sets have been tested.Method 600 then returns to step 610.
IH n UX f e nough
IH n UX f en oough
IH n UX f enou gh
AE n s UX r answ er
AE n s UX r answe r
r IH D AX m rhythm
r IH D AX m r hythm
r IH D AX m rh ythm
r IH D AX m rhyth m
Claims (28)
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US10/342,435 USRE40458E1 (en) | 1996-06-18 | 2003-01-13 | System and method for using a correspondence table to compress a pronunciation guide |
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US08/665,404 US5845238A (en) | 1996-06-18 | 1996-06-18 | System and method for using a correspondence table to compress a pronunciation guide |
US09/169,190 US6178397B1 (en) | 1996-06-18 | 1998-10-08 | System and method for using a correspondence table to compress a pronunciation guide |
US10/342,435 USRE40458E1 (en) | 1996-06-18 | 2003-01-13 | System and method for using a correspondence table to compress a pronunciation guide |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US09/169,190 Reissue US6178397B1 (en) | 1996-06-18 | 1998-10-08 | System and method for using a correspondence table to compress a pronunciation guide |
Publications (1)
Publication Number | Publication Date |
---|---|
USRE40458E1 true USRE40458E1 (en) | 2008-08-12 |
Family
ID=24669977
Family Applications (3)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/665,404 Expired - Lifetime US5845238A (en) | 1996-06-18 | 1996-06-18 | System and method for using a correspondence table to compress a pronunciation guide |
US09/169,190 Ceased US6178397B1 (en) | 1996-06-18 | 1998-10-08 | System and method for using a correspondence table to compress a pronunciation guide |
US10/342,435 Expired - Lifetime USRE40458E1 (en) | 1996-06-18 | 2003-01-13 | System and method for using a correspondence table to compress a pronunciation guide |
Family Applications Before (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US08/665,404 Expired - Lifetime US5845238A (en) | 1996-06-18 | 1996-06-18 | System and method for using a correspondence table to compress a pronunciation guide |
US09/169,190 Ceased US6178397B1 (en) | 1996-06-18 | 1998-10-08 | System and method for using a correspondence table to compress a pronunciation guide |
Country Status (1)
Country | Link |
---|---|
US (3) | US5845238A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070073541A1 (en) * | 2001-11-12 | 2007-03-29 | Nokia Corporation | Method for compressing dictionary data |
US20090070116A1 (en) * | 2007-09-10 | 2009-03-12 | Kabushiki Kaisha Toshiba | Fundamental frequency pattern generation apparatus and fundamental frequency pattern generation method |
US9135912B1 (en) * | 2012-08-15 | 2015-09-15 | Google Inc. | Updating phonetic dictionaries |
US10019995B1 (en) | 2011-03-01 | 2018-07-10 | Alice J. Stiebel | Methods and systems for language learning based on a series of pitch patterns |
US11062615B1 (en) | 2011-03-01 | 2021-07-13 | Intelligibility Training LLC | Methods and systems for remote language learning in a pandemic-aware world |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5822720A (en) | 1994-02-16 | 1998-10-13 | Sentius Corporation | System amd method for linking streams of multimedia data for reference material for display |
US6092074A (en) | 1998-02-10 | 2000-07-18 | Connect Innovations, Inc. | Dynamic insertion and updating of hypertext links for internet servers |
US6757647B1 (en) * | 1998-07-30 | 2004-06-29 | International Business Machines Corporation | Method for encoding regular expressions in a lexigon |
GB2343037B (en) * | 1998-10-22 | 2002-12-31 | Ibm | Phonetic spell checker |
US7292980B1 (en) * | 1999-04-30 | 2007-11-06 | Lucent Technologies Inc. | Graphical user interface and method for modifying pronunciations in text-to-speech and speech recognition systems |
KR100318763B1 (en) * | 1999-09-01 | 2002-01-05 | 윤덕용 | The similarity comparitive method of foreign language a tunning fork transcription |
JP2002258894A (en) * | 2001-03-02 | 2002-09-11 | Fujitsu Ltd | Device and method of compressing decompression voice data |
US7130861B2 (en) | 2001-08-16 | 2006-10-31 | Sentius International Corporation | Automated creation and delivery of database content |
JP2003263337A (en) * | 2002-03-08 | 2003-09-19 | Seiko Epson Corp | Debug function-incorporated microcomputer |
US7010488B2 (en) * | 2002-05-09 | 2006-03-07 | Oregon Health & Science University | System and method for compressing concatenative acoustic inventories for speech synthesis |
US20040030555A1 (en) * | 2002-08-12 | 2004-02-12 | Oregon Health & Science University | System and method for concatenating acoustic contours for speech synthesis |
US7479905B2 (en) * | 2003-07-28 | 2009-01-20 | International Business Machines Corporation | Apparatus, system and method for data compression using irredundant patterns |
US7524191B2 (en) * | 2003-09-02 | 2009-04-28 | Rosetta Stone Ltd. | System and method for language instruction |
US20050120300A1 (en) * | 2003-09-25 | 2005-06-02 | Dictaphone Corporation | Method, system, and apparatus for assembly, transport and display of clinical data |
US7783474B2 (en) * | 2004-02-27 | 2010-08-24 | Nuance Communications, Inc. | System and method for generating a phrase pronunciation |
US20050197837A1 (en) * | 2004-03-08 | 2005-09-08 | Janne Suontausta | Enhanced multilingual speech recognition system |
US7430503B1 (en) * | 2004-08-24 | 2008-09-30 | The United States Of America As Represented By The Director, National Security Agency | Method of combining corpora to achieve consistency in phonetic labeling |
US8719027B2 (en) * | 2007-02-28 | 2014-05-06 | Microsoft Corporation | Name synthesis |
US9158762B2 (en) | 2012-02-16 | 2015-10-13 | Flying Lizard Languages, Llc | Deconstruction and construction of words of a polysynthetic language for translation purposes |
CN105893414A (en) * | 2015-11-26 | 2016-08-24 | 乐视致新电子科技(天津)有限公司 | Method and apparatus for screening valid term of a pronunciation lexicon |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4779080A (en) | 1985-03-06 | 1988-10-18 | U.S. Philips Corporation | Electronic information display systems |
US4876541A (en) | 1987-10-15 | 1989-10-24 | Data Compression Corporation | Stem for dynamically compressing and decompressing electronic data |
US5189610A (en) | 1986-10-20 | 1993-02-23 | Xerox Corporation | Electronic dictionary with correct and incorrect words |
JPH0567075A (en) * | 1991-09-10 | 1993-03-19 | Sanyo Electric Co Ltd | Word division processing method |
US5325091A (en) | 1992-08-13 | 1994-06-28 | Xerox Corporation | Text-compression technique using frequency-ordered array of word-number mappers |
US5333313A (en) | 1990-10-22 | 1994-07-26 | Franklin Electronic Publishers, Incorporated | Method and apparatus for compressing a dictionary database by partitioning a master dictionary database into a plurality of functional parts and applying an optimum compression technique to each part |
US5500920A (en) | 1993-09-23 | 1996-03-19 | Xerox Corporation | Semantic co-occurrence filtering for speech recognition and signal transcription applications |
US5523946A (en) | 1992-02-11 | 1996-06-04 | Xerox Corporation | Compact encoding of multi-lingual translation dictionaries |
US5530645A (en) | 1993-06-30 | 1996-06-25 | Apple Computer, Inc. | Composite dictionary compression system |
US5551049A (en) | 1987-05-26 | 1996-08-27 | Xerox Corporation | Thesaurus with compactly stored word groups |
US5649221A (en) | 1995-09-14 | 1997-07-15 | Crawford; H. Vance | Reverse electronic dictionary using synonyms to expand search capabilities |
US5673362A (en) | 1991-11-12 | 1997-09-30 | Fujitsu Limited | Speech synthesis system in which a plurality of clients and at least one voice synthesizing server are connected to a local area network |
US5680601A (en) | 1994-12-14 | 1997-10-21 | Hewlett-Packard Company | Compression system for reducing the occurrence of a literal prefix |
US5799276A (en) | 1995-11-07 | 1998-08-25 | Accent Incorporated | Knowledge-based speech recognition system and methods having frame length computed based upon estimated pitch period of vocalic intervals |
US5815639A (en) * | 1993-03-24 | 1998-09-29 | Engate Incorporated | Computer-aided transcription system using pronounceable substitute text with a common cross-reference library |
US5930756A (en) | 1997-06-23 | 1999-07-27 | Motorola, Inc. | Method, device and system for a memory-efficient random-access pronunciation lexicon for text-to-speech synthesis |
US6047298A (en) * | 1996-01-30 | 2000-04-04 | Sharp Kabushiki Kaisha | Text compression dictionary generation apparatus |
-
1996
- 1996-06-18 US US08/665,404 patent/US5845238A/en not_active Expired - Lifetime
-
1998
- 1998-10-08 US US09/169,190 patent/US6178397B1/en not_active Ceased
-
2003
- 2003-01-13 US US10/342,435 patent/USRE40458E1/en not_active Expired - Lifetime
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4779080A (en) | 1985-03-06 | 1988-10-18 | U.S. Philips Corporation | Electronic information display systems |
US5189610A (en) | 1986-10-20 | 1993-02-23 | Xerox Corporation | Electronic dictionary with correct and incorrect words |
US5551049A (en) | 1987-05-26 | 1996-08-27 | Xerox Corporation | Thesaurus with compactly stored word groups |
US4876541A (en) | 1987-10-15 | 1989-10-24 | Data Compression Corporation | Stem for dynamically compressing and decompressing electronic data |
US5333313A (en) | 1990-10-22 | 1994-07-26 | Franklin Electronic Publishers, Incorporated | Method and apparatus for compressing a dictionary database by partitioning a master dictionary database into a plurality of functional parts and applying an optimum compression technique to each part |
JPH0567075A (en) * | 1991-09-10 | 1993-03-19 | Sanyo Electric Co Ltd | Word division processing method |
US5673362A (en) | 1991-11-12 | 1997-09-30 | Fujitsu Limited | Speech synthesis system in which a plurality of clients and at least one voice synthesizing server are connected to a local area network |
US5940796A (en) * | 1991-11-12 | 1999-08-17 | Fujitsu Limited | Speech synthesis client/server system employing client determined destination control |
US5523946A (en) | 1992-02-11 | 1996-06-04 | Xerox Corporation | Compact encoding of multi-lingual translation dictionaries |
US5325091A (en) | 1992-08-13 | 1994-06-28 | Xerox Corporation | Text-compression technique using frequency-ordered array of word-number mappers |
US5815639A (en) * | 1993-03-24 | 1998-09-29 | Engate Incorporated | Computer-aided transcription system using pronounceable substitute text with a common cross-reference library |
US5530645A (en) | 1993-06-30 | 1996-06-25 | Apple Computer, Inc. | Composite dictionary compression system |
US5500920A (en) | 1993-09-23 | 1996-03-19 | Xerox Corporation | Semantic co-occurrence filtering for speech recognition and signal transcription applications |
US5680601A (en) | 1994-12-14 | 1997-10-21 | Hewlett-Packard Company | Compression system for reducing the occurrence of a literal prefix |
US5649221A (en) | 1995-09-14 | 1997-07-15 | Crawford; H. Vance | Reverse electronic dictionary using synonyms to expand search capabilities |
US5799276A (en) | 1995-11-07 | 1998-08-25 | Accent Incorporated | Knowledge-based speech recognition system and methods having frame length computed based upon estimated pitch period of vocalic intervals |
US6047298A (en) * | 1996-01-30 | 2000-04-04 | Sharp Kabushiki Kaisha | Text compression dictionary generation apparatus |
US5930756A (en) | 1997-06-23 | 1999-07-27 | Motorola, Inc. | Method, device and system for a memory-efficient random-access pronunciation lexicon for text-to-speech synthesis |
Non-Patent Citations (3)
Title |
---|
Bell et al., Modeling the Text Compression, ACM Computing Surveys, Vo. 21, No. 4, Dec. 1989. * |
Furness, Spelling for the Millions, Thomas Nelson, Inc, NY, 1977, pp. 157-162. * |
van den bosh et al., Data-Oriented Methods for Grapheme-to-Phoneme Conversion, Proceedings of the Conference of the European Chapter of the ACL, 6, (1993), pp. 45-53. * |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070073541A1 (en) * | 2001-11-12 | 2007-03-29 | Nokia Corporation | Method for compressing dictionary data |
US20090070116A1 (en) * | 2007-09-10 | 2009-03-12 | Kabushiki Kaisha Toshiba | Fundamental frequency pattern generation apparatus and fundamental frequency pattern generation method |
US8478595B2 (en) * | 2007-09-10 | 2013-07-02 | Kabushiki Kaisha Toshiba | Fundamental frequency pattern generation apparatus and fundamental frequency pattern generation method |
US10019995B1 (en) | 2011-03-01 | 2018-07-10 | Alice J. Stiebel | Methods and systems for language learning based on a series of pitch patterns |
US10565997B1 (en) | 2011-03-01 | 2020-02-18 | Alice J. Stiebel | Methods and systems for teaching a hebrew bible trope lesson |
US11062615B1 (en) | 2011-03-01 | 2021-07-13 | Intelligibility Training LLC | Methods and systems for remote language learning in a pandemic-aware world |
US11380334B1 (en) | 2011-03-01 | 2022-07-05 | Intelligible English LLC | Methods and systems for interactive online language learning in a pandemic-aware world |
US9135912B1 (en) * | 2012-08-15 | 2015-09-15 | Google Inc. | Updating phonetic dictionaries |
Also Published As
Publication number | Publication date |
---|---|
US5845238A (en) | 1998-12-01 |
US6178397B1 (en) | 2001-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
USRE40458E1 (en) | System and method for using a correspondence table to compress a pronunciation guide | |
US7263488B2 (en) | Method and apparatus for identifying prosodic word boundaries | |
US6208968B1 (en) | Computer method and apparatus for text-to-speech synthesizer dictionary reduction | |
US6978239B2 (en) | Method and apparatus for speech synthesis without prosody modification | |
Glavitsch et al. | A system for retrieving speech documents | |
US6347295B1 (en) | Computer method and apparatus for grapheme-to-phoneme rule-set-generation | |
EP1668628A1 (en) | Method for synthesizing speech | |
JPH07244661A (en) | System and method for developing glyph of unknown character | |
US6188977B1 (en) | Natural language processing apparatus and method for converting word notation grammar description data | |
US20050149888A1 (en) | Method and apparatus for minimizing weighted networks with link and node labels | |
US20040225497A1 (en) | Compressed yet quickly searchable digital textual data format | |
US5815096A (en) | Method for compressing sequential data into compression symbols using double-indirect indexing into a dictionary data structure | |
CN111539199A (en) | Text error correction method, device, terminal and storage medium | |
KR20000069633A (en) | File processing method, data processing device, and storage medium | |
US6829580B1 (en) | Linguistic converter | |
Unno et al. | Trimming CFG parse trees for sentence compression using machine learning approaches | |
US6757647B1 (en) | Method for encoding regular expressions in a lexigon | |
JP2002221981A (en) | Voice synthesizer and voice synthesizing method | |
JPH1185790A (en) | Device and method for storing and retrieving document information and recording medium recording document information storage and retrieval programs | |
JP3518340B2 (en) | Reading prosody information setting method and apparatus, and storage medium storing reading prosody information setting program | |
JPH0546358A (en) | Compressing method for text data | |
JPH0546357A (en) | Compressing method and restoring method for text data | |
JPH0140372B2 (en) | ||
JPS63278174A (en) | Translation device | |
JPH1049187A (en) | Speech information retrieval apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: APPLE INC.,CALIFORNIA Free format text: CHANGE OF NAME;ASSIGNOR:APPLE COMPUTER, INC.;REEL/FRAME:020638/0127 Effective date: 20070109 Owner name: APPLE INC., CALIFORNIA Free format text: CHANGE OF NAME;ASSIGNOR:APPLE COMPUTER, INC.;REEL/FRAME:020638/0127 Effective date: 20070109 |
|
FEPP | Fee payment procedure |
Free format text: PAYOR NUMBER ASSIGNED (ORIGINAL EVENT CODE: ASPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY Free format text: PAYER NUMBER DE-ASSIGNED (ORIGINAL EVENT CODE: RMPN); ENTITY STATUS OF PATENT OWNER: LARGE ENTITY |
|
CC | Certificate of correction | ||
FPAY | Fee payment |
Year of fee payment: 12 |