Automatic Language Model Update

• US 20160035345A1
• Filed: 10/09/2015
• Published: 02/04/2016
• Est. Priority Date: 04/03/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Cohen, Michael H., Baluja, Shumeet, Mengibar, Pedro J. Moreno
• Granted Patent: US 9,953,636 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/06 Creation of reference templates; Training of speech recognition systems, e.g. adaptation to the characteristics of the speaker's voice G10L15/14 takes precedence
• CPC Class Codes: G10L 15/063 Training
• CPC Class Codes: G10L 15/065 Adaptation
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/0635 updating or merging of old and new templates; Mean values; Weighting

Abstract

A method for generating a speech recognition model includes accessing a baseline speech recognition model, obtaining information related to recent language usage from search queries, and modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information. The portion of a sound may include a word. Also, a method for generating a speech recognition model, includes receiving at a search engine from a remote device an audio recording and a transcript that substantially represents at least a portion of the audio recording, synchronizing the transcript with the audio recording, extracting one or more letters from the transcript and extracting the associated pronunciation of the one or more letters from the audio recording, and generating a dictionary entry in a pronunciation dictionary.

Claims

1-17. -17. (canceled)

18. A method for generating a speech recognition model, comprising:

accessing a baseline speech recognition model;

obtaining information related to recent language usage from search queries; and

modifying the speech recognition model to revise probabilities of a portion of a sound occurrence based on the information.

19. The method of claim 18, wherein the portion of the sound comprises a word.

20. The method of claim 18, further comprising receiving from a remote device a verbal search term that is associated with a text search term using a recognizer implementing the speech recognition model.

21. The method of claim 20, further comprising transmitting to the remote device search results associated with the text search term.

22. The method of claim 20, further comprising transmitting to the remote device the text search term.

23. The method of claim 18, further comprising receiving a verbal command for an application that is associated with a text command using a recognizer implementing the speech recognition model.

24. The method of claim 23, wherein the speech recognition model assigns the verbal command to a sub-grammar slot.

25. The method of claim 18, wherein the speech recognition model is a rule-based model, a statistical model, or both.

26. The method of claim 18, further comprising transmitting to a remote device at least a portion of the modified speech recognition model.

27. The method of claim 26, wherein the remote device accesses the portion of the modified speech recognition model to perform speech recognition functions.

28. The method of claim 18, wherein the speech recognition model includes weightings for co-concurrence events between two or more words.

29. The method of claim 18, wherein the speech recognition model includes weightings associated with when the search queries are received.

30. The method of claim 18, wherein obtaining the information related to recent language includes generating word counts for each word.

31. A system for updating a language model, comprising:

a request processor to receive search terms;

an extractor for obtaining information related to recent language usage from the search terms; and

means for modifying a language model to revise probabilities of a word occurrence based on the information.

32. A computer implemented method for transmitting verbal terms, comprising:

transmitting search terms from a remote device to a server device, wherein the server device generates word occurrence data associated with the search terms and modifies a language model based on the word occurrence data.

33. The computer implemented method of claim 32, wherein the remote device is selected from a group consisting of a mobile telephone, a personal digital assistant, a desktop computer, and a mobile email device.