VOICE RECOGNITION SYSTEM

• US 20190214012A1
• Filed: 03/14/2019
• Published: 07/11/2019
• Est. Priority Date: 01/06/2016
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Aleksic, Petar, Mengibar, Pedro J. Moreno
• Granted Patent: US 10,643,617 B2
• Time in Patent Office: 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, at an automatic speech recognition (ASR) system, a current voice input from a user, the current voice input associated with at least two contexts, each context of the at least two contexts having a respective weight indicating a likelihood that the voice input is associated with the respective context;

generating, by the ASR system, an intermediate recognition result of the current voice input from the user;

adjusting, by the ASR system, the respective weights of the at least two contexts based on the intermediate recognition result; and

transcribing, by the ASR system, the current voice input using a language model, the language model biasing the transcription of the voice input toward one of the at least two contexts based on the adjusted weights.

2. The method of claim 1, wherein the language model comprises an N-gram model.

3. The method of claim 1, wherein adjusting the respective weights of the at least two contexts associated with the current voice input comprises boosting the respective base weight for at least one of the at least two contexts.

4. The method of claim 1, wherein adjusting the respective weights of the at least two contexts based on the intermediate recognition result comprises:

determining a most relevant one of the at least two contexts by identifying particular keywords in the intermediate recognition result; and

increasing the respective weight of the most relevant one of the at least two contexts.

5. The method of claim 1, wherein the current voice input from the user is configured to invoke a software application to perform an action using the transcription of the current voice input.

6. The method of claim 1, further comprising providing the transcription of the current voice input to a dialogue system interacting with the user.

7. The method of claim 1, wherein at least one of the at least two contexts comprises data indicating a current time when the current voice input is received at the ASR system.

8. The method of claim 1, wherein at least one of the at least two contexts associated with the current voice input is based on one or more prior voice inputs from the user within a past time period of the current voice input.

9. The method of claim 1, wherein at least one of the at least two contexts comprises named-entities associated with a particular category.

10. The method of claim 1, wherein the ASR system resides on a server in communication with a computing device associated with the user, the computing device configured to capture the current voice input spoken by the user and transmit the captured voice input to the ASR system.

11. An automatic speech recognition (ASR) system comprising:

data processing hardware; and

memory hardware in communication with the data processing hardware and storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising;

receiving a current voice input from a user, the current voice input associated with at least two contexts, each context of the at least two contexts having a respective weight indicating a likelihood that the voice input is associated with the respective context;

generating an intermediate recognition result of the current voice input from the user;

adjusting the respective weights of the at least two contexts based on the intermediate recognition result; and

transcribing the current voice input using a language model, the language model biasing the transcription of the voice input toward one of the at least two contexts based on the adjusted weights.

12. The ASR system of claim 11, wherein the language model comprises an N-gram model.

13. The ASR system of claim 12, wherein adjusting the respective weights of the at least two contexts associated with the current voice input comprises boosting the respective base weight for at least one of the at least two contexts.

14. The ASR system of claim 11, wherein adjusting the respective weights of the at least two contexts based on the intermediate recognition result comprises:

determining a most relevant one of the at least two contexts by identifying particular keywords in the intermediate recognition result; and

increasing the respective weight of the most relevant one of the at least two contexts.

15. The ASR system of claim 11, wherein the current voice input from the user is configured to invoke a software application to perform an action using the transcription of the current voice input.

16. The ASR system of claim 11, wherein the operations further comprise providing the transcription of the current voice input to a dialogue system interacting with the user.

17. The ASR system of claim 11, wherein at least one of the at least two contexts comprises data indicating a current time when the current voice input is received at the ASR system.

18. The ASR system of claim 11, wherein at least one of the at least two contexts associated with the current voice input is based on one or more prior voice inputs from the user within a past time period of the current voice input.

19. The ASR system of claim 11, wherein at least one of the at least two contexts comprises named-entities associated with a particular category.

20. The ASR system of claim 11, wherein the data processing hardware and the memory hardware reside on a server in communication with a computing device associated with the user, the computing device configured to capture the current voice input spoken by the user and transmit the current voice input to the ASR system.