Computer apparatus for text-to-speech synthesizer dictionary reduction

• US 6,347,298 B2
• Filed: 02/26/2001
• Issued: 02/12/2002
• Est. Priority Date: 12/16/1998
• Status: Expired due to Fees

• Current Assignee: Hewlett-Packard Development Company, L.P. (HP Inc.)
• Original Assignee: Compaq Computer Corporation (HP Inc.)
• Inventors: Vitale, Anthony J., Kopec, Thomas, Lin, Ginger Chun-Che
• Primary Examiner(s): {haeck over (S)}mits, Ta̅livaldis Ivars
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/795,070
• Publication Number:
  US 20010012999A1
• Time in Patent Office: 351 Days
• Field of Search: 704/201, 704/235, 704/239, 704/243, 704/244, 704/245, 704/260, 704/261, 704/10
• US Class Current: 704/260
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

A computerized apparatus for reducing the size of a dictionary used in a text-to-speech synthesis system are provided. In an initial phase, the method and apparatus determine if entries in the dictionary, each containing a grapheme string and a corresponding phoneme string, can be fully matched by using at least one rule set used to synthesize words to phonemic data. If the entry can be fully matched using rule processing alone, the entry is indicated to be deleted from the dictionary. In a second phase, the method and apparatus determine if the entry, considered as a root word entry, is required in the dictionary in order to support phoneme synthesis of other entries containing the root word entry, and if so, the root word entry is indicated to be saved in the dictionary. If the other entries containing the root word entry can have correct phonemic data generated from a combination of the root word entries phonemic data and phonemes generated from rule set processing, then the other entries are indicated to be deleted from the dictionary. After all words have been processed by phase one and/or phase two, the entries indicated to be saved are aggregated to form a reduced dictionary.

Claims

1. An apparatus for reducing the size of a dictionary used in a speech synthesis system having a set of rules for determining phonemes from graphemes, the dictionary containing a plurality of entries, the apparatus comprising:

a logic unit determining if a given entry in the dictionary can be fully matched by using rules of the rule set, and if so, indicating the entry to be deleted from the dictionary;

the logic unit determining if the given entry is required in the dictionary in order to support other entries, and if so, indicating the given entry to be saved and aggregating the entries indicated as to be saved, to form a reduced dictionary therefrom; and

wherein the given entry comprises a grapheme string and a corresponding phoneme string.

2. The apparatus of claim 1 wherein:

the logic unit generates a rule-based phoneme string for the grapheme string of the entry using rules in the rule set and determines if the rule-based phoneme string matches the corresponding phoneme string of the entry, and if so, indicates the entry to be deleted from the dictionary.

3. The apparatus of claim 2 wherein:

the logic unit provides an affix rule set containing affix rules for determining phonemes from beginning and ending graphemes of character strings, each affix rule having a grapheme portion and a corresponding phoneme portion; and

the logic unit combining grapheme and phoneme strings of a root word entry from the dictionary with respective grapheme and phoneme portions of an affix rule of the affix rule set to form a grapheme combination and phoneme combination pair and determining if the grapheme combination and phoneme combination pair exists as a matching entry in the dictionary, and if so, indicating the root word entry to be saved in the dictionary, and, indicating the matching entry to be deleted from the dictionary.

4. The apparatus of claim 3, wherein:

the logic unit determines if the grapheme combination and phoneme combination pair exists as a matching entry in the dictionary, respectively for the root entry with each affix rule in the affix rule set and determines if an entry is required, for each root word entry in the dictionary starting with a first root word entry.

5. The apparatus of claim 3 wherein:

the logic unit, before generating a rule based phoneme string, determines if any affix rule from the affix rule set matches a portion of the grapheme string of the entry, and if so, skipping to a next entry in the dictionary for processing.

6. The apparatus of claim 3 wherein:

the logic unit further checks if the grapheme string of the entry is a homograph, and if so, skips to a next entry in the dictionary for processing.

7. The apparatus of claim 3 wherein:

the logic unit combines the grapheme string of the root word entry with the grapheme portion of the affix rule to form the grapheme combination and combining the phoneme string of the root word entry with the phoneme portion of the affix rule to form the phoneme combination.

8. The apparatus of claim 7, wherein:

the logic unit further determines if the grapheme combination exists as a matching grapheme string in an entry in the dictionary, and if so, obtaining the correspond ing phoneme string as a matching phoneme string for the entry and determining if the phoneme combination matches the matching phoneme string, and if so, indicating the root word entry to be saved in the dictionary and indicating the matching entry to be deleted from the dictionary.

9. The apparatus of claim 8 wherein:

the logic unit normalizes any lexical stress in the phoneme combination and the matching phoneme string before determining if the phoneme combination matches the matching phoneme string.

10. An apparatus for reducing the size of a dictionary used in a speech synthesis system, the dictionary containing a plurality of entries, the apparatus comprising:

a logic unit determining if a given entry is required in the dictionary in order to produce the phoneme string of another entry, and if so, indicating the given entry to be saved;

the logic unit creating a dictionary containing entries indicated to be saved;

the logic unit combining grapheme and phoneme strings of a root word entry in the dictionary with respective grapheme and phoneme portions of an affix rule of the affix rule set to form a grapheme combination and phoneme combination pair; and

determining if the grapheme combination and phoneme combination pair exists as a matching entry in the dictionary, and if so, indicating the root word entry to be saved in the dictionary and indicating the matching entry to be deleted; and

wherein the speech synthesis system includes an affix rule set containing affix rules for determining phonemes from beginning and ending graphemes of character strings, each affix rule having a grapheme portion and a corresponding phoneme portion.

11. The apparatus of claim 10 wherein:

the logic unit determines if the grapheme combination and phoneme combination pair exists as a matching entry in the dictionary, respectively, for the root word entry with each affix rule in the affix rule set.

12. The apparatus of claim 11 wherein the logic unit determines if an entry is required, for each root entry in the dictionary, starting with a first root word entry.

13. The apparatus of claim 12 wherein:

the logic unit further combines the grapheme string of the root word entry with the grapheme portion of the affix rule to form the grapheme combination and combines the phoneme string of the root word entry with the phoneme portion of the affix rule to form the phoneme combination.

14. The apparatus of claim 13 wherein:

the logic unit determines if the grapheme combination exists as a matching grapheme string in an entry in the dictionary, and if so, obtaining the corresponding phoneme string as a matching phoneme string for the entry and determining if the phoneme combination matches the matching phoneme string, and if so, indicating the root word entry to be saved in the dictionary and indicating the matching entry to be deleted in the dictionary.

15. The apparatus of claim 14 wherein:

the logic unit normalizes any lexical stress in the phoneme combination and the matching phoneme string before determining if the phoneme combination matches the matching phoneme string.

16. The apparatus of claim 12 wherein:

the logic unit saves, in a reduced dictionary, the entries that have been indicated to be saved.

17. The apparatus of claim 12 wherein:

the logic unit deletes entries that have been indicated to be deleted from the dictionary.

18. The apparatus of claim 12 wherein the entries in the dictionary are arranged according to length of grapheme string with the shortest grapheme string first.

19. The apparatus of claim 12 wherein:

the logic unit determines if the grapheme combination and phoneme combination pair exists as a matching entry in the dictionary, first with rules from the affix rule set for determining phonemes from beginning graphemes.

20. The apparatus of claim 12 wherein:

the logic unit determines if the grapheme combination exists as a matching grapheme string in an entry in the dictionary, and if so, obtains the corresponding phoneme string as a matching phoneme string for the entry; and

the logic unit determines if the phoneme combination matches the matching phoneme string, and if so, indicating the root word entry to be saved in the dictionary and indicating the matching entry to be deleted in the dictionary.

21. The apparatus of claim 20 wherein:

the logic unit normalizes any lexical stress in the phoneme combination and the matching phoneme string before determining if the phoneme combination matches the matching phoneme string.

22. The apparatus of claim 20 wherein:

the logic unit saves, in a reduced dictionary, entries that have been indicated to be saved.

23. An apparatus for reducing the size of a dictionary used in a speech synthesis system having a set of rules for determining phonemes from graphemes, the dictionary containing a plurality of entries, the apparatus comprising:

a logic unit determining, for each entry in the dictionary, if the entry in the dictionary can be fully matched by using rules of the rule set, and if so, indicating the entry to be deleted from the dictionary;

the logic unit creating a reduced dictionary from the entries remaining after omitting any entries indicated as to be deleted; and

wherein each entry comprises a grapheme string and a corresponding phoneme string.

24. The apparatus of claim 23 wherein:

the logic unit further generates a rule-based phoneme string for the grapheme string of the entry, using rules in the rule set, and determines if the rule-based phoneme string matches the corresponding phoneme string of the entry, and if so, indicating the entry is to be deleted from the dictionary.

25. The apparatus of claim 24 wherein:

the logic unit further determines, for each entry in the dictionary starting with a first entry, if an entry in the dictionary can be fully matched.

26. The apparatus of claim 25 wherein:

the logic unit provides an affix rule set for the speech synthesis system, the affix rule set for determining phonemes from beginning and ending graphemes of character strings, and before generating a rule based phoneme string, checking if any affix rule from the affix rule set matches a portion of the grapheme string of the entry, and if so, skipping to a next entry in the dictionary for processing.

27. The apparatus of claim 26 wherein:

the logic unit checks if the grapheme string of the entry is a homograph, and if so, skips to a next entry in the dictionary for processing.

28. The apparatus of claim 26 wherein:

the logic unit deletes entries that have been marked as to be deleted from the dictionary.

29. The apparatus of claim 26 wherein:

the logic unit saves, in a reduced dictionary, entries that have not been indicated to be saved.

30. A speech synthesis system for reducing the size of a dictionary containing a plurality of entries, the speech synthesis system having a set of rules for determining phonemes from graphemes, the speech synthesis system comprising:

a dictionary;

a text-to-speech synthesizer connected to the dictionary;

a rule set connected to the text-to-speech synthesizer;

a logic unit, contained in the text-to-speech synthesizer, determining if a given entry in the dictionary can be fully matched by using rules of the rule set, and if so, indicating the entry to be deleted from the dictionary;

the logic unit determining if the given entry is required in the dictionary in order to support other entries, and if so, indicating the given entry to be saved and aggregating the entries indicated as to be saved, to form a reduced dictionary therefrom; and

wherein the given entry comprises a grapheme string and a corresponding phoneme string.

31. A speech synthesis system for reducing the size of a dictionary containing a plurality of entries, the speech synthesis system comprising:

a dictionary;

a text-to-speech synthesizer connected to the dictionary;

a rule set connected to the text-to-speech synthesizer;

a logic unit, contained in the text-to-speech synthesizer, determining if a given entry is required in the dictionary in order to produce the phoneme string of another entry, and if so, indicating the given entry to be saved;

the logic unit creating a dictionary containing entries indicated to be saved;

the logic unit combining grapheme and phoneme strings of a root word entry in the dictionary with respective grapheme and phoneme portions of an affix rule of the affix rule set to form a grapheme combination and phoneme combination pair; and

determining if the grapheme combination and phoneme combination pair exists as a matching entry in the dictionary, and if so, indicating the root word entry to be saved in the dictionary and indicating the matching entry to be deleted; and

wherein the speech synthesis system includes an affix rule set containing affix rules for determining phonemes from beginning and ending graphemes of character strings, each affix rule having a grapheme portion and a corresponding phoneme portion.

32. A speech synthesis system for reducing the size of a dictionary containing a plurality of entries, the speech synthesis system having a set of rules for determining phonemes from graphemes, the speech synthesis system comprising:

a dictionary;

a text-to-speech synthesizer connected to the dictionary;

a rule set connected to the text-to-speech synthesizer;

a logic unit, contained in the text-to-speech synthesizer, determining for each entry in the dictionary, if the entry in the dictionary can be fully matched by using rules of the rule set, and if so, indicating the entry to be deleted from the dictionary;

the logic unit creating a reduced dictionary from the entries remaining after omitting any entries indicated as to be deleted; and

wherein each entry comprises a grapheme string and a corresponding phoneme string.

33. A computer program product comprising:

a computer usable medium for reducing the size of a dictionary containing a plurality of entries, the speech synthesis system having a set of rules for determining phonemes from graphemes;

a set of computer program instructions embodied on the computer usable medium, including instructions to;

determine if a given entry in the dictionary can be fully matched by using rules of the rule set, and if so, indicating the entry is to be deleted from the dictionary;

determine if the given entry is required in the dictionary in order to support other entries, and if so, indicating the given entry to be saved;

aggregate the entries indicated as to be saved, to form a reduced dictionary therefrom; and

wherein the given entry comprises a grapheme string and a corresponding phoneme string.

34. A computer program product comprising:

a computer usable medium for reducing the size of a dictionary used in a speech synthesis system, the dictionary containing a plurality of entries;

a set of computer program instructions embodied on the computer usable medium, including instructions to;

determine if a given entry is required in the dictionary in order to produce the phoneme string of another entry, and if so, indicating the given entry to be saved;

create a dictionary containing entries indicated to be saved;

combine grapheme and phoneme strings of a root word entry in the dictionary with respective grapheme and phoneme portions of an affix rule of the affix rule set to form a grapheme combination and phoneme combination pair;

determine if the grapheme combination and phoneme combination pair exists as a matching entry in the dictionary, and if so, indicating the root word entry to be saved in the dictionary and indicating the matching entry to be deleted; and

wherein the speech synthesis system includes an affix rule set containing affix rules for determining phonemes from beginning and ending graphemes of character strings, each affix rule having a grapheme portion and a corresponding phoneme portion.

35. A computer program product comprising:

a computer usable medium for reducing the size of a dictionary used in a speech synthesis system having a set of rules for determining phonemes from graphemes, the dictionary containing a plurality of entries;

a set of computer program instructions embodied on the computer usable medium, including instructions to;

determine, for each entry in the dictionary, if the entry in the dictionary can be fully matched by using rules of the rule set, and if so, indicating the entry to be deleted from the dictionary;

create a reduced dictionary from the entries remaining after omitting any entries indicated as to be deleted; and

wherein each entry comprises a grapheme string and a corresponding phoneme string.