Initiating actions based on partial hotwords

• US 9,330,663 B2
• Filed: 03/20/2014
• Issued: 05/03/2016
• Est. Priority Date: 12/04/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sharifi, Matthew
• Primary Examiner(s): YEN, ERIC L
• Application Number:
  US14/220,781
• Publication Number:
  US 20150154954A1
• Time in Patent Office: 775 Days
• US Class Current: 1/1
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/1815 Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/28 Constructional details of speech recognition systems
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 25/51 for comparison or discrimination

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, receiving audio data; determining that an initial portion of the audio data corresponds to an initial portion of a hotword; in response to determining that the initial portion of the audio data corresponds to the initial portion of the hotword, selecting, from among a set of one or more actions that are performed when the entire hotword is detected, a subset of the one or more actions; and causing one or more actions of the subset to be performed.

Claims

1. A computer-implemented method comprising:

deriving audio data from a received utterance;

determining that an initial portion of the audio data corresponds to a partial utterance of a hotword;

in response to determining that the initial portion of the audio data corresponds to the partial utterance of the hotword, selecting a first set of one or more actions that are associated with the partial utterance of the hotword;

causing the one or more actions of the first set to be performed;

after determining that the initial portion of the audio data corresponds to the partial utterance of the hotword, determining that the audio data does not correspond to an utterance of the hotword;

in response to determining that the audio data does not correspond to the utterance of the hotword, selecting an additional set of one or more actions that counteract the one or more actions of the first set; and

causing the one or more actions of the additional set to be performed.

2. The computer-implemented method of claim 1, wherein determining that the audio data does not correspond to the utterance of the hotword comprises:

identifying one or more acoustic features of the audio data;

comparing the one or more acoustic features of the audio data to one or more acoustic features associated with one or more hotwords stored in a database; and

based on the comparing, determining that the audio data does not correspond to any hotword of the one or more hotwords stored in the database.

3. The computer-implemented method of claim 1, wherein determining that the audio data does not correspond to the utterance of the hotword comprises:

obtaining a transcription of the audio data;

comparing the transcription of the audio data to one or more transcriptions associated with one or more hotwords stored in a database; and

based on the comparing, determining that the audio data does not correspond to any hotword of the one or more hotwords stored in the database.

4. The computer-implemented method of claim 1, wherein determining that the audio data does not correspond to the utterance of the hotword comprises determining that the audio data does not correspond to a full utterance of the hotword.

5. The computer-implemented method of claim 1, wherein causing the one or more actions of the additional set to be performed comprises negating the actions of the first set of the one or more actions.

6. The computer-implemented method of claim 1, wherein a particular action of the first set of one or more actions includes initializing a network connection of a computing device, and a corresponding action of the additional set of one or more actions includes closing the network connection of the computing device.

7. The computer-implemented method of claim 1, wherein the one or more actions of the first set include an action whose respective result is not discernible to a user of a computing device performing the action.

8. A system comprising:

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

deriving audio data from a received utterance;

determining that an initial portion of the audio data corresponds to a partial utterance of a hotword;

in response to determining that the initial portion of the audio data corresponds to the partial utterance of the hotword, selecting a first set of one or more actions that are associated with the partial utterance of the hotword;

causing the one or more actions of the first set to be performed;

after determining that the initial portion of the audio data corresponds to the partial utterance of the hotword, determining that the audio data does not correspond to an utterance of the hotword;

in response to determining that the audio data does not correspond to the utterance of the hotword, selecting an additional set of one or more actions that counteract the one or more actions of the first set; and

causing the one or more actions of the additional set to be performed.

9. The system of claim 8, wherein determining that the audio data does not correspond to the utterance of the hotword comprises:

identifying one or more acoustic features of the audio data;

comparing the one or more acoustic features of the audio data to one or more acoustic features associated with one or more hotwords stored in a database; and

based on the comparing, determining that the audio data does not correspond to any hotword of the one or more hotwords stored in the database.

10. The system of claim 8, wherein determining that the audio data does not correspond to the utterance of the hotword comprises:

obtaining a transcription of the audio data;

comparing the transcription of the audio data to one or more transcriptions associated with one or more hotwords stored in a database; and

based on the comparing, determining that the audio data does not correspond to any hotword of the one or more hotwords stored in the database.

11. The system of claim 8, wherein determining that the audio data does not correspond to the utterance of the hotword comprises determining that the audio data does not correspond to a full utterance of the hotword.

12. The system of claim 8, wherein causing the one or more actions of the additional set to be performed comprises negating the actions of the first set of the one or more actions.

13. The system of claim 8, wherein a particular action of the first set of one or more actions includes initializing a network connection of a computing device, and a corresponding action of the additional set of one or more actions includes closing the network connection of the computing device.

14. The system of claim 8, wherein the one or more actions of the first set include an action whose respective result is not discernible to a user of a computing device performing the action.

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

deriving audio data from a received utterance;

determining that an initial portion of the audio data corresponds to a partial utterance of a hotword;

in response to determining that the initial portion of the audio data corresponds to the partial utterance of the hotword, selecting a first set of one or more actions that are associated with the partial utterance of the hotword;

causing the one or more actions of the first set to be performed;

after determining that the initial portion of the audio data corresponds to the partial utterance of the hotword, determining that the audio data does not correspond to an utterance of the hotword;

in response to determining that the audio data does not correspond to the utterance of the hotword, selecting an additional set of one or more actions that counteract the one or more actions of the first set; and

causing the one or more actions of the additional set to be performed.

16. The computer-readable medium of claim 15, wherein determining that the audio data does not correspond to the utterance of the hotword comprises:

identifying one or more acoustic features of the audio data;

comparing the one or more acoustic features of the audio data to one or more acoustic features associated with one or more hotwords stored in a database; and

based on the comparing, determining that the audio data does not correspond to any hotword of the one or more hotwords stored in the database.

17. The computer-readable medium of claim 15, wherein determining that the audio data does not correspond to the utterance of the hotword comprises:

obtaining a transcription of the audio data;

comparing the transcription of the audio data to one or more transcriptions associated with one or more hotwords stored in a database; and

based on the comparing, determining that the audio data does not correspond to any hotword of the one or more hotwords stored in the database.

18. The computer-readable medium of claim 15, wherein determining that the audio data does not correspond to the utterance of the hotword comprises determining that the audio data does not correspond to a full utterance of the hotword.

19. The computer-readable medium of claim 15, wherein causing the one or more actions of the additional set to be performed comprises negating the actions of the first set of the one or more actions.

20. The computer-readable medium of claim 15, wherein a particular action of the first set of one or more actions includes initializing a network connection of a computing device, and a corresponding action of the additional set of one or more actions includes closing the network connection of the computing device.