Voice command triggered speech enhancement

Patent metadata

Field	Value
Publication number	US-10755697-B2
Application number	US-201916393542-A
Country	US
Kind code	B2
Filing date	Apr 24, 2019
Priority date	Dec 18, 2013
Publication date	Aug 25, 2020
Grant date	Aug 25, 2020

Abstract

Received data representing speech is stored, and a trigger detection block detects a presence of data representing a trigger phrase in the received data. In response, a first part of the stored data representing at least a part of the trigger phrase is supplied to an adaptive speech enhancement block, which is trained on the first part of the stored data to derive adapted parameters for the speech enhancement block. A second part of the stored data, overlapping with the first part of the stored data, is supplied to the adaptive speech enhancement block operating with said adapted parameters, to form enhanced stored data. A second trigger phrase detection block detects the presence of data representing the trigger phrase in the enhanced stored data. In response, enhanced speech data are output from the speech enhancement block for further processing, such as speech recognition.

First claim

The invention claimed is:

1. A method of processing received data representing speech, comprising:
storing the received data;
detecting a presence of data representing a first predefined trigger phrase in the received data;
in response to said detecting, supplying a first part of the stored data representing at least a part of the first predefined trigger phrase to an adaptive speech enhancement block;
training the speech enhancement block on the first part of the stored data to derive adapted parameters for the speech enhancement block;
supplying a second part of the stored data to the adaptive speech enhancement block operating with said adapted parameters, wherein the second part of the stored data overlaps with the first part of the stored data; and
outputting enhanced speech data from the speech enhancement block.

2. A method as claimed in claim 1 , wherein the first predefined trigger phrase is a part of a whole predefined trigger phrase, the method comprising attempting to detect the whole predefined trigger phrase, and
further comprising supplying the second part of the stored data to the adaptive speech enhancement block only if the whole predefined trigger phrase is detected.

3. A method as claimed in claim 1 wherein the first part of the stored data is the data stored from a first defined starting point.

4. A method as claimed in claim 3 wherein the second part of the stored data is the data stored from a second defined starting point, and the second defined starting point is later than the first defined starting point.

5. A method as claimed in claim 1 , wherein the second part of the stored data comprises data representing at least part of the whole predefined trigger phrase.

6. A method as claimed in claim 1 , further comprising sending the output enhanced speech data from the speech enhancement block to a speech recognition engine.

7. A method as claimed in claim 6 , comprising sending the output enhanced speech data from the speech enhancement block to the speech recognition engine within a single device.

8. A method as claimed in claim 1 , comprising supplying the second part of the stored data to the speech enhancement block and outputting the enhanced speech data from the speech enhancement block at a higher rate than real time.

9. A method as claimed in claim 8 , comprising supplying the second part of the stored data to the speech enhancement block and outputting the enhanced speech data from the speech enhancement block at a higher rate than real time until the data being supplied is substantially time aligned with the data being stored.

10. A method as claimed in claim 1 , further comprising performing a second adaptive speech enhancement on the received speech data.

11. A method as claimed in claim 10 , further comprising inhibiting adaptation of the second adaptive speech enhancement while training the speech enhancement block.

12. A method as claimed in claim 11 , further comprising resuming adaptation of the second adaptive speech enhancement after training the speech enhancement block.

13. A method as claimed in claim 11 , wherein the second adaptive speech enhancement is an acoustic echo cancellation.

14. A speech processor, comprising:
an input, for receiving data representing speech; and
a speech processing block,
wherein the speech processing block is configured to perform a method comprising:
storing the received data;
detecting a presence of data representing a first predefined trigger phrase in the received data;
in response to said detecting, supplying a first part of the stored data representing at least a part of the first predefined trigger phrase to an adaptive speech enhancement block;
training the speech enhancement block on the first part of the stored data to derive adapted parameters for the speech enhancement block;
supplying a second part of the stored data to the adaptive speech enhancement block operating with said adapted parameters, wherein the second part of the stored data overlaps with the first part of the stored data; and
outputting enhanced speech data from the speech enhancement block to the speech processing block.

15. A speech processor as claimed in claim 14 , wherein the speech processing block comprises a speech recognition engine.

16. A mobile device, comprising a speech processor as claimed in claim 14 .

17. A speech processor, comprising:
an input, for receiving data representing speech; and
an output, for connection to a speech processing block,
wherein the speech processing block is configured to perform a method comprising:
storing the received data;
detecting a presence of data representing a first predefined trigger phrase in the received data;
in response to said detecting, supplying a first part of the stored data representing at least a part of the first predefined trigger phrase to an adaptive speech enhancement block;
training the speech enhancement block on the first part of the stored data to derive adapted parameters for the speech enhancement block;
supplying a second part of the stored data to the adaptive speech enhancement block operating with said adapted parameters, wherein the second part of the stored data overlaps with the first part of the stored data; and
outputting enhanced speech data from the speech enhancement block to the output, for connection to the speech processing block.

18. A speech processor as claimed in claim 17 , wherein the speech processing block comprises a speech recognition engine.

19. A mobile device, comprising a speech processor as claimed in claim 17 .

Assignees

• Cirrus Logic Int Semiconductor Ltd
• Cirrus Logic Inc

Inventors

• Hatfield Robert James
• Page Michael

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/00

  Speech recognition (G10L17/00 takes precedence) · CPC title

• G10L25/78

  Detection of presence or absence of voice signals (switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10) · CPC title

• G10L21/02 Primary

  Speech enhancement, e.g. noise reduction or echo cancellation (reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08) · CPC title

• G10L21/0208 Primary

  Noise filtering · CPC title