Methods and systems for enabling speech-based internet searches using phonemes

• US 7,496,515 B2
• Filed: 07/26/2005
• Issued: 02/24/2009
• Est. Priority Date: 06/14/2001
• Status: Expired due to Term

• Current Assignee: Tamiras Per Pte Ltd LLC (Intellectual Ventures LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Brown, Michael K., Glinski, Stephen C.
• Primary Examiner(s): McFadden; Susan
• Application Number:
  US11/188,645
• Publication Number:
  US 20050261906A1
• Time in Patent Office: 1,309 Days
• Field of Search: 704/270.1
• US Class Current: 704/270.1
• CPC Class Codes: G06F 16/3335 Syntactic pre-processing, e.g. stopword elimination, stemming
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 2015/228 of application context

Abstract

Merged “grammars” derived from statistical indicators (e.g., N-grams and cohorts) are used to enable speech-based, Internet searches.

Claims

1. A system comprising:

a memory storing a merged grammar based on the contents of a plurality of web sites;

a recognition unit for making a comparison between a phoneme associated with a spoken word and the merged grammar; and

a generating unit operatively connected to said recognition unit for generating a list of web site addresses based on the outcome of the comparison.

2. The system as in claim 1 wherein the memory includes a grammar database storing the merged grammar, the database comprising:

one or more words or phonemes;

a probability value associated with each of the one or more of the words or phonemes; and

a pointer associated with each of the one or more words or phonemes.

3. The system as in claim 2 wherein the database further comprises distance values associated with one or more words or phonemes.

4. The system as in claim 2 wherein the database further comprises one or more web site indices associated with each pointer.

5. The system as in claim 2 wherein the database further comprises one or more synonyms of a word or phoneme.

6. The system as in claim 2 wherein the databases further comprises one or more conjugates of a word or phoneme.

7. The system as in claim 2 wherein the database further comprises one or more part of speech identifiers associated with one or more of the words or phonemes.

8. The system as in claim 1 wherein the grammar comprises one or more synonyms.

9. The system as in claim 1 wherein the grammar comprises one or more conjugates.

10. The system as in claim 1 wherein the grammar comprises part of speech identifiers.

11. The system as in claim 1 wherein the recognition unit is further generating information correlated to the spoken word.

12. A method comprising:

providing a merged grammar;

comparing a phoneme associated with a spoken word against the merged grammar;

enabling a speech-based Internet search based on the comparison; and

generating a web site address correlated to the spoken word.

13. The method as in claim 12 wherein the grammar comprises one or more synonyms.

14. The method as in claim 12 wherein the grammar comprises one or more conjugates.

15. The method as in claim 12 wherein the grammar comprises part of speech identifiers.

16. The method as in claim 12, further comprising generating information correlated to the spoken word.

17. A system for enabling a speech-based Internet search, comprising:

a memory storing a merged grammar; and

a recognition unit for comparing a phoneme associated with a spoken word against the merged grammar,

wherein the memory includes a grammar database storing the merged grammar, the database comprising;

one or more words or phonemes;

a probability value associated with each of the one or more of the words or phonemes;

a pointer associated with each of the one or more words or phonemes;

one or more web site indices associated with each pointer; and

one or more web site addresses associated with each index.

18. The system as in claim 17 wherein the database further comprises usage weights, wherein each weight is associated with a web site address.

19. A computer readable recording medium storing a program for causing a computer to carry out a method comprising:

accessing a stored merged grammar;

comparing a phoneme associated with a spoken word against the merged grammar; and

generating a web site address correlated to the spoken word.

20. The computer readable recording medium as in claim 19 wherein the grammar comprises part of speech identifiers.

22. The computer readable recording medium as in claim 19 wherein the grammar comprises one or more synonyms.

23. The computer readable recording medium as in claim 19 wherein the grammar comprises one or more conjugates.

21. The computer readable recording medium as in claim further for generating information correlated to the spoken word.