Hotword detection on multiple devices

Patent metadata

Field	Value
Publication number	US-2016104483-A1
Application number	US-201514659861-A
Country	US
Kind code	A1
Filing date	Mar 17, 2015
Priority date	Oct 9, 2014
Publication date	Apr 14, 2016
Grant date	—

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for hotword detection on multiple devices are disclosed. In one aspect, a method includes the actions of receiving, by a computing device, audio data that corresponds to an utterance. The actions further include determining a likelihood that the utterance includes a hotword. The actions further include determining a loudness score for the audio data. The actions further include based on the loudness score, determining an amount of delay time. The actions further include, after the amount of delay time has elapsed, transmitting a signal that indicates that the computing device will initiate speech recognition processing on the audio data.

First claim

What is claimed is:

1 . A computer-implemented method comprising:
receiving, by a computing device, audio data that corresponds to an utterance; determining a likelihood that the utterance includes a hotword; determining a loudness score for the audio data; based on the loudness score, determining an amount of delay time; after the amount of delay time has elapsed, transmitting a signal that indicates that the computing device will initiate speech recognition processing on the audio data.

2 . The method of claim 1 , comprising:
receiving, by the computing device, additional audio data that corresponds to an additional utterance; determining a second likelihood that the additional utterance includes the hotword; determining a second loudness score for the additional audio data; based on the second loudness score, determining a second amount of delay time; and before the amount of delay time has elapsed, receiving a second signal that indicates that (i) a second computing device will initiate speech recognition processing on the additional audio data and (ii) the computing device should not initiate speech recognition processing on the additional audio data.

3 . The method of claim 2 , comprising:
based on receiving the second signal, determining that an activation state of the computing device is an inactive state.

4 . The method of claim 1 , comprising:
based on transmitting the signal, determining that an activation state of the computing device is an active state.

5 . The method of claim 1 , wherein the signal comprises an ultrasonic signal or short range radio signal.

6 . The method of claim 1 , wherein the signal is received by another computing device and indicates to the other computing device to not initiate speech recognition processing on the audio data.

7 . The method of claim 1 , comprising:
based on determining a likelihood that the utterance includes a hotword, preparing to receive a signal that indicates that another computing device will initiate speech recognition processing on the audio data.

8 . The method of claim 1 , wherein the loudness score is proportional to the amount of delay time.

9 . The method of claim 1 , wherein the delay time is zero when the loudness score satisfies a threshold.

10 . The method of claim 1 , wherein determining a loudness score for the audio data comprises:
determining that the likelihood that the utterance includes the hotword satisfies a likelihood threshold.

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, by a computing device, audio data that corresponds to an utterance;
determining a likelihood that the utterance includes a hotword;
determining a loudness score for the audio data;
based on the loudness score, determining an amount of delay time;
after the amount of delay time has elapsed, transmitting a signal that indicates that the computing device will initiate speech recognition processing on the audio data.

12 . The system of claim 11 , wherein the operations further comprise:
receiving, by the computing device, additional audio data that corresponds to an additional utterance; determining a second likelihood that the additional utterance includes the hotword; determining a second loudness score for the additional audio data; based on the second loudness score, determining a second amount of delay time; and before the amount of delay time has elapsed, receiving a second signal that indicates that (i) a second computing device will initiate speech recognition processing on the additional audio data and (ii) the computing device should not initiate speech recognition processing on the additional audio data.

13 . The system of claim 11 , wherein the operations further comprise:
based on transmitting the signal, determining that an activation state of the computing device is an active state.

14 . The system of claim 11 , wherein the signal comprises an ultrasonic signal or short range radio signal.

15 . The system of claim 11 , wherein the signal is received by another computing device and indicates to the other computing device to not initiate speech recognition processing on the audio data.

16 . The system of claim 11 , wherein the operations further comprise:
based on determining a likelihood that the utterance includes a hotword, preparing to receive a signal that indicates that another computing device will initiate speech recognition processing on the audio data.

17 . The system of claim 11 , wherein the loudness score is proportional to the amount of delay time.

18 . The system of claim 11 , wherein the delay time is zero when the loudness score satisfies a threshold.

19 . The system of claim 11 , wherein determining a loudness score for the audio data comprises:
determining that the likelihood that the utterance includes the hotword satisfies a likelihood threshold.

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, by a computing device, audio data that corresponds to an utterance; determining a likelihood that the utterance includes a hotword; determining a loudness score for the audio data; based on the loudness score, determining an amount of delay time; after the amount of delay time has elapsed, transmitting a signal that indicates that the computing device will initiate speech recognition processing on the audio data.

Assignees

• Google Inc

Inventors

• Foerster Jakob Nicolaus
• Gruenstein Alexander H

Classifications

• G10L25/87

  Detection of discrete points within a voice signal · CPC title

• G10L2015/088

  Word spotting · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/223

  Execution procedure of a spoken command · CPC title

• G10L15/02

  Feature extraction for speech recognition; Selection of recognition unit · CPC title