System and method for using a correspondence table to compress a pronunciation guide

• US RE40,458 E1
• Filed: 01/13/2003
• Issued: 08/12/2008
• Est. Priority Date: 06/18/1996
• Status: Expired due to Term

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: Fredenburg, Timothy
• Primary Examiner(s): Harper; V. Paul
• Application Number:
  US10/342,435
• Time in Patent Office: 2,038 Days
• Field of Search: None
• US Class Current: 704/1
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: H03M 7/3084 using adaptive string matching, e.g. the Lempel-Ziv method

Abstract

Parsing routines extract from a conventional pronunciation dictionary an entry, which includes a dictionary word and dictionary phonemes representing the pronunciation of the dictionary word. A correspondence table is used to compress the pronunciation dictionary. The correspondence table includes correspondence sets for a particular language, each set having a correspondence text entry, a correspondence phoneme entry representing the pronunciation of the correspondence text entry and a unique correspondence set identifying symbol. A matching system compares a dictionary entry with the correspondence sets, and replaces the dictionary entry with the symbols representing the best matches. In the absence of a match, symbols representing silent text or unmatched phonemes can be used. The correspondence symbols representing the best matches provide compressed pronunciation dictionary entries. The matching system also generates decoder code sets for subsequently translating the symbol sets. A decoder system uses the decoder code sets for translating symbol sets in the compressed pronunciation dictionary to generate phonemes corresponding to selected text.

Claims

1. A computer data storage medium storing a correspondence table which enables compression of program product for compressing a pronunciation dictionary, the computer program product comprising a computer-readable medium containing computer program code for:

generating a correspondence table comprising;

a plurality of correspondence sets each including

a correspondence text entry that is part of a dictionary word;

a correspondence phoneme entry representing the pronunciation of the correspondence text entry; and

a correspondence symbol for identifying the correspondence set,

wherein at least one said correspondence symbol forms a symbol set for use as a compressed data entry in generating said compressed pronunciation dictionary.

2. The computer data storage medium program product of claim 1 further comprising computer program code for:

storing a tuning function for optimizing said correspondence table.

3. The computer data storage medium program product of claim 2 wherein said tuning function eliminates redundant correspondence sets and low usage correspondence sets from said correspondence table.

4. The computer data storage medium program product of claim 1 wherein said correspondence table includes said correspondence sets for all practical combinations of said correspondence text entries and said correspondence phoneme entries for a given language.

5. The computer data storage medium program product of claim 1 further comprising computer program code for:

storing;

a grouping of a plurality of said correspondence sets.

6. The computer data storage medium of claim 5 wherein correspondence phoneme entries of said grouping are similar to one another in pronunciation.

7. The computer data storage medium program product of claim 1 wherein a matching system uses said correspondence phoneme entry to match said correspondence sets in generating said compressed pronunciation dictionary.

8. A system for storing a pronunciation guide comprising:

a memory element storing;

a correspondence table for storing pronunciation data; and

a tuning function for optimizing said correspondence table;

wherein said correspondence table includes at least one correspondence set having

a correspondence text entry that is part of a dictionary word,

a correspondence phonetic entry representing the pronunciation of said correspondence text entry, and

a correspondence symbol for identifying the correspondence set; and

wherein a matching system uses said correspondence phonetic entry to match said at least one correspondence set in generating a compressed pronunciation dictionary.

9. The system of claim 8 wherein said tuning function eliminates redundant correspondence sets from said correspondence table.

10. The system of claim 9 wherein at least one said correspondence symbol forms a symbol set for us as a compressed entry in generating said compressed pronunciation dictionary.

11. The system of claim 9 wherein said correspondence table includes a respective correspondence set for each practical combination of any correspondence text entry and any correspondence phonetic entry for a given language.

12. The system of claim 9 further comprising:

a grouping of a plurality of said at least one correspondence set.

13. The system of claim 12 wherein said phonetic entries of said grouping are similar to one another in pronunciation.

14. The system of claim 8 wherein said tuning function eliminates low usage correspondence sets from said correspondence table.

15. The system of claim 8 wherein said phonetic entry is a phoneme, an allophone, or a syllable.

16. A method of storing generating a pronunciation guide, comprising the steps of:

inputting a correspondence set into a correspondence table, the correspondence set comprising a text entry and a phoneme entry representing the pronunciation of the text entry; and

inputting into said correspondence table a correspondence symbol corresponding to identifying said correspondence set;

wherein at least one said correspondence symbol forms a symbol set for use as a compressed entry in generating a compressed pronunciation dictionaryand

generating a pronunciation guide, wherein said correspondence symbol comprises an entry in the pronunciation guide.

17. The method of claim 16 further comprising the steps of:

optimizing said correspondence table; and

grouping said correspondence set into a plurality of said correspondence sets.

18. The method of claim 17 wherein said step of optimizing comprises the steps of:

eliminating redundant correspondence sets from said correspondence table;

eliminating low-usage correspondence sets from said correspondence table; and

adding productive correspondence sets to said correspondence table.

19. The method of claim 16 wherein said step of inputting a correspondence set further comprises the steps of:

inputting a correspondence text entry that is part of a dictionary word into said correspondence table; and

inputting a phonetic entry corresponding to said correspondence text entry into said correspondence table.

20. The method of claim 19 16 further comprising the step of using said phonetic phoneme entry to generate said compressed pronunciation dictionary guide.

21. A computer program product for generating a compressed pronunciation dictionary, the computer program product comprising a computer-readable medium containing computer program code for:

generating a plurality of correspondence sets each including

a correspondence text that is part of a dictionary word;

a correspondence phoneme representing the pronunciation of the correspondence text; and

a correspondence symbol for identifying the correspondence set;

storing wherein the correspondence symbol in the compressed pronunciation dictionary.

22. A system for storing a pronunciation guide comprising:

a memory element storing;

a correspondence table for storing pronunciation data; and

a tuning function for optimizing the correspondence data structure;

wherein the correspondence table includes at least one correspondence set having

a correspondence text that is part of a dictionary word,

a correspondence phoneme representing the pronunciation of the correspondence text, and

a correspondence symbol for identifying the correspondence set; and

wherein a matching system uses the correspondence phoneme to match the correspondence set in generating a compressed pronunciation dictionary.

23. A method of generating a pronunciation guide, comprising the steps of:

inputting a correspondence set into a correspondence table, the correspondence set comprising a text entry and a phoneme entry representing the pronunciation of the text entry; and

inputting into the correspondence table a correspondence symbol identifying the correspondence set; and

generating a pronunciation guide, wherein the correspondence symbol comprises an entry in the pronunciation guide.

24. A computer-readable medium having instructions contained thereon, which, when executed by a processor, cause the processor to perform the operations of:

inputting a correspondence set into a correspondence table

inputting into the correspondence table a correspondence symbol identifying the correspondence set; and

generating a compressed pronunciation dictionary, wherein the correspondence symbol is used as an entry in the compressed pronunciation dictionary.

25. A system for compressing a pronunciation dictionary guide which includes a plurality of dictionary entries, each entry having a guide word and at least one associated phoneme representing the pronunciation of the word, the system comprising:

a computer-readable medium storing

(1) correspondence data which includes a plurality of correspondence sets, each set having

(i) a text entry,

(ii) a phoneme entry representing a pronunciation of the text entry, and

(iii) a symbol identifying the correspondence set; and

(2) a matching process for comparing a selected dictionary entry and the associated phonemes with the correspondence sets, and storing correspondence symbols which represent matching correspondence sets as a compressed pronunciation guide entry in the computer-readable medium; and

a processor coupled to the computer-readable medium for controlling the operations of the matching system.

26. A system for using a compressed pronunciation dictionary and decoder data to decode selected text, comprising:

memory storing

decoder data having a plurality of decoder code sets for translating symbol sets, each decoder code set including a decoder text entry, a decoder phoneme entry and a decoder symbol representing the decoder code set;

a decoder process for using the decoder data to translate symbol sets to find a dictionary entry which matches the selected text, and upon finding a match using the decoder data

to retrieve the decoder phonemes from the matching symbol set; and

a processor coupled to the memory for controlling the operations of the decoder system.

27. A computer-based method for compressing a pronunciation guide which includes a plurality of dictionary entries, each entry having a dictionary text entry and at least one associated dictionary phoneme representing the pronunciation of the guide word dictionary text entry, comprising the steps of:

storing in a first portion of a computer memory correspondence data which includes a plurality of correspondence sets, each correspondence set including a correspondence text entry, a correspondence phoneme entry representing a pronunciation of the correspondence text entry and a unique correspondence symbol identifying the correspondence set;

receiving a dictionary text entry and at least one dictionary phoneme representing the pronunciation of the guide word;

comparing the dictionary text entry and dictionary phonemes with correspondence sets; and

storing the correspondence symbols representing matching correspondence sets as compressed pronunciation guide entries in a second portion of the computer memory.

28. A computer storage medium storing a computer program for causing a computer to perform the steps of:

storing decoder data which includes a plurality of decoder sets, each decoder set having a decoder text entry, a decoder phoneme entry representing the pronunciation of the decoder text entry, and a unique decoder set identifying symbol;

receiving selected text;

using the decoder data to decode a symbol set to produce a dictionary entry;

comparing the selected text with the dictionary entry to determine if they match; and

if a match is made, using the decoder data to retrieve the phoneme entries corresponding to a matching symbol set.