Voice recognition system

• US 10,049,666 B2
• Filed: 01/06/2016
• Issued: 08/14/2018
• Est. Priority Date: 01/06/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Aleksic, Petar, Moreno Mengibar, Pedro J.
• Primary Examiner(s): PATEL, SHREYANS A
• Application Number:
  US14/989,642
• Publication Number:
  US 20170193999A1
• Time in Patent Office: 951 Days
• CPC Class Codes: G06F 16/632 Query formulation
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 2015/085 Methods for reducing search complexity, pruning

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for voice recognition. In one aspect, a method includes the actions of receiving a voice input; determining a transcription for the voice input, wherein determining the transcription for the voice input includes, for a plurality of segments of the voice input: obtaining a first candidate transcription for a first segment of the voice input; determining one or more contexts associated with the first candidate transcription; adjusting a respective weight for each of the one or more contexts; and determining a second candidate transcription for a second segment of the voice input based in part on the adjusted weights; and providing the transcription of the plurality of segments of the voice input for output.

Claims

1. A method comprising:

receiving a voice input;

determining a transcription for the voice input, wherein determining the transcription for the voice input includes, for a plurality of segments of the voice input;

maintaining a plurality of contexts and respective base weights associated with the plurality of contexts;

obtaining a first candidate transcription for a first segment of the voice input;

determining one or more contexts, from the plurality of contexts, associated with the first candidate transcription;

identifying one or more base weights respectively corresponding to the one or more contexts;

adjusting a respective base weight of the one or more base weights for each of the one or more contexts based on the first candidate transcription; and

determining a second candidate transcription for a second segment of the voice input based in part on the adjusted base weights; and

providing the transcription of the plurality of segments of the voice input for output.

2. The method of claim 1, wherein obtaining a first candidate transcription for a first segment of the voice input comprising:

determining that the first segment of the voice input satisfies stability criteria; and

in response to determining that the first segment of the voice input satisfies stability criteria, obtaining the first candidate transcription for the first segment of the voice input.

3. The method of claim 2, wherein the stability criteria include one or more semantic characteristics of the first segment of the voice input.

4. The method of claim 2, wherein the stability criteria include a time delay occurring after the first segment of the voice input.

5. The method of claim 1, wherein the second segment of the voice input occurs after the first segment of the voice input.

6. The method of claim 1, wherein the one or more contexts are received from a user device.

7. The method of claim 6, wherein the one or more contexts include data including a user'"'"'s geographic location, a user'"'"'s search history, user'"'"'s interests, or a user'"'"'s activity.

8. The method of claim 1, comprising:

storing a plurality of scores for a plurality of contexts; and

in response to adjusting a respective base weight for each of the one or more contexts, updating the adjusted scores for the one or more contexts.

9. The method of claim 1, further comprising:

providing the output as a search query; and

providing, in response to the search query, one or more search results to a user device.

10. The method of claim 1, wherein the first candidate transcription comprises a word, sub-word, or group of words.

11. A system comprising:

one or more computers and one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

receiving a voice input;

determining a transcription for the voice input, wherein determining the transcription for the voice input includes, for a plurality of segments of the voice input;

maintaining a plurality of contexts and respective base weights associated with the plurality of contexts;

obtaining a first candidate transcription for a first segment of the voice input;

determining one or more contexts, from the plurality of contexts, associated with the first candidate transcription;

identifying one or more base weights respectively corresponding to the one or more contexts;

adjusting a respective base weight of the one or more base weights for each of the one or more contexts based on the first candidate transcription; and

determining a second candidate transcription for a second segment of the voice input based in part on the adjusted base weights; and

providing the transcription of the plurality of segments of the voice input for output.

12. The system of claim 11, wherein obtaining a first candidate transcription for a first segment of the voice input comprising:

determining that the first segment of the voice input satisfies stability criteria; and

in response to determining that the first segment of the voice input satisfies stability criteria, obtaining the first candidate transcription for the first segment of the voice input.

13. The system of claim 12, wherein the stability criteria include one or more semantic characteristics of the first segment of the voice input.

14. The system of claim 12, wherein the stability criteria include a time delay occurring after the first segment of the voice input.

15. The system of claim 11, wherein the second segment of the voice input occurs after the first segment of the voice input.

16. The system of claim 11, wherein the one or more contexts are received from a user device.

17. The system of claim 16, wherein the one or more contexts include data including a user'"'"'s geographic location, a user'"'"'s search history, user'"'"'s interests, or a user'"'"'s activity.

18. The system of claim 11, wherein the one or more computers are configured to perform operations comprising:

storing a plurality of scores for a plurality of contexts; and

in response to adjusting a respective base weight for each of the one or more contexts, updating the adjusted scores for the one or more contexts.

19. The system of claim 11, wherein the one or more computers are configured to perform operations comprising:

providing the output as a search query; and

providing, in response to the search query, one or more search results to a user device.

20. A non-transitory computer-readable medium storing software comprising instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

receiving a voice input;

determining a transcription for the voice input, wherein determining the transcription for the voice input includes, for a plurality of segments of the voice input;

maintaining a plurality of contexts and respective base weights associated with the plurality of contexts;

obtaining a first candidate transcription for a first segment of the voice input;

determining one or more contexts, from the plurality of contexts, associated with the first candidate transcription;

identifying one or more base weights respectively corresponding to the one or more contexts;

adjusting a base respective weight of the one or more base weights for each of the one or more contexts based on the first candidate transcription; and

determining a second candidate transcription for a second segment of the voice input based in part on the adjusted base weights; and

providing the transcription of the plurality of segments of the voice input for output.