Recorded media hotword trigger suppression

• US 10,395,650 B2
• Filed: 06/05/2017
• Issued: 08/27/2019
• Est. Priority Date: 06/05/2017
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Garcia, Ricardo Antonio
• Primary Examiner(s): Shah, Paras D
• Assistant Examiner(s): Ogunbiyi, Oluwadamilola M
• Application Number:
  US15/614,213
• Publication Number:
  US 20180350356A1
• Time in Patent Office: 813 Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/20 Speech recognition techniques specially adapted for robustness in adverse environments, e.g. in noise, of stress induced speech G10L21/02 takes precedence
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 19/018 Audio watermarking, i.e. embedding inaudible data in the audio signal
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/226 using non-speech characteristics

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for suppressing hotword triggers when detecting a hotword in recorded media are disclosed. In one aspect, a method includes the actions of receiving, by a computing device, audio corresponding to playback of an item of media content. The actions further include determining, by the computing device, that the audio includes an utterance of a predefined hotword and that the audio includes an audio watermark. The actions further include analyzing, by the computing device, the audio watermark. The actions further include based on analyzing the audio watermark, determining, by the computing device, whether to perform speech recognition on a portion of the audio following the predefined hotword.

Claims

1. A computer-implemented method comprising:

receiving, by a microphone of a computing device that includes (i) the microphone, (ii) a hotword identifier, (iii) an audio watermark identifier, and (iv) an automated speech recognizer, audio corresponding to playback of an item of media content, wherein the automated speech recognizer of the computing device is configured to perform speech recognition on received audio that follows a predefined hotword;

determining, by the hotword identifier of the computing device, that the audio includes an utterance of the predefined hotword;

determining, by the audio watermark identifier of the computing device, that the audio includes an audio watermark;

analyzing, by the audio watermark identifier of the computing device, the audio watermark; and

based on analyzing the audio watermark, bypassing, by the automated speech recognizer of the computing device, performing speech recognition on a portion of the audio following the predefined hotword.

2. The method of claim 1, wherein:

analyzing the audio watermark comprises comparing the audio watermark to one or more audio watermarks, and

bypassing performing speech recognition on the portion of the audio following the predefined hotword is based further on comparing the audio watermark to the one or more audio watermarks.

3. The method of claim 1, wherein the audio watermark is an inaudible portion of the audio corresponding to playback of an item of media content.

4. The method of claim 1, comprising:

based on analyzing the audio watermark, identifying a source of the audio corresponding to playback of the item of media content,

wherein bypassing performing speech recognition on the portion of the audio following the predefined hotword is further based on the source of the audio corresponding to playback of the item of media content.

5. The method of claim 1, comprising:

based on analyzing the audio watermark, identifying a source of the audio corresponding to playback of an item of media content; and

updating a log file to indicate the source of the audio corresponding to playback of the item of media content.

6. The method of claim 1, wherein the audio watermark is included in a portion of the audio that includes the utterance of the predefined hotword.

7. The method of claim 1, comprising:

determining a type of the additional computing device,

wherein bypassing performing speech recognition on the portion of the audio following the predefined hotword is further based on the type of the additional computing device.

8. The method of claim 1, comprising:

determining a location of the additional computing device,

wherein bypassing performing speech recognition on the portion of the audio following the predefined hotword is further based on the location of the additional computing device.

9. The method of claim 1, comprising:

determining a user setting of the additional computing device,

wherein bypassing performing speech recognition on the portion of the audio following the predefined hotword is further based on the user setting of the additional computing device.

10. The method of claim 1, wherein determining that the audio includes an audio watermark comprises:

based on determining that the audio includes an utterance of a predefined hotword, determining that the audio includes the audio watermark.

11. The method of claim 1, wherein determining that the audio includes an audio watermark comprises:

after determining that the audio includes an utterance of a predefined hotword, determining that the audio includes the audio watermark.

12. The method of claim 1, wherein:

analyzing the audio watermark comprises extracting data that is encoded in the audio watermark, and

bypassing performing speech recognition on a portion of the audio following the predefined hotword is further based on the data that is encoded in the audio watermark.

13. The method of claim 1, comprising:

based on analyzing the audio watermark, identifying a type of media content of the audio corresponding to playback of an item of media content; and

updating a log file to indicate the type of media content of the audio corresponding to playback of the item of media content.

14. The method of claim 1, comprising:

based on analyzing the audio watermark, identifying a type of media content of the audio corresponding to playback of the item of media content,

wherein bypassing performing speech recognition on the portion of the audio following the predefined hotword is further based on the type of media content of the audio corresponding to playback of the item of media content.

15. 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, by a microphone of a computing device that includes (i) the microphone, (ii) a hotword identifier, (iii) an audio watermark identifier, and (iv) an automated speech recognizer, audio corresponding to playback of an item of media content, wherein the automated speech recognizer of the computing device is configured to perform speech recognition on received audio that follows a predefined hotword;

determining, by the hotword identifier of the computing device, that the audio includes an utterance of the predefined hotword;

determining, by the audio watermark identifier of the computing device, that the audio includes an audio watermark;

analyzing, by the audio watermark identifier of the computing device, the audio watermark; and

based on analyzing the audio watermark, bypassing, by the automated speech recognizer of the computing device, performing speech recognition on a portion of the audio following the predefined hotword.

16. The system of claim 15, wherein:

analyzing the audio watermark comprises comparing the audio watermark to one or more audio watermarks, and

bypassing performing speech recognition on the portion of the audio following the predefined hotword is based further on comparing the audio watermark to the one or more audio watermarks.

17. 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, by a microphone of a computing device that includes (i) the microphone, (ii) a hotword identifier, (iii) an audio watermark identifier, and (iv) an automated speech recognizer, audio corresponding to playback of an item of media content, wherein the automated speech recognizer of the computing device is configured to perform speech recognition on received audio that follows a predefined hotword;

determining, by the hotword identifier of the computing device, that the audio includes an utterance of the predefined hotword;

determining, by the audio watermark identifier of the computing device, that the audio includes an audio watermark;

analyzing, by the audio watermark identifier of the computing device, the audio watermark; and

based on analyzing the audio watermark, bypassing, by the automated speech recognizer of the computing device, performing speech recognition on a portion of the audio following the predefined hotword.