Monitoring and activating speech process in response to a trigger phrase

Patent metadata

Field	Value
Publication number	US-10102853-B2
Application number	US-201415105755-A
Country	US
Kind code	B2
Filing date	Dec 17, 2014
Priority date	Dec 18, 2013
Publication date	Oct 16, 2018
Grant date	Oct 16, 2018

Abstract

A method of processing received data representing speech comprises monitoring the received data to detect the presence of data representing a first portion of a trigger phrase in said received data. On detection of the data representing the first portion of the trigger phrase, a control signal is sent to activate a speech processing block. The received data is monitored to detect the presence of data representing a second portion of the trigger phrase in said received data. If the control signal to activate the speech processing block has previously been sent, then, on detection of the data representing the second portion of the trigger phrase, the activation of the speech processing block is maintained.

First claim

The invention claimed is:

1. A method of processing received data representing speech comprising the steps of:
monitoring the received data to detect the presence of data representing a first portion of a trigger phrase in said received data;
sending, on detection of said data representing the first portion of the trigger phrase, a control signal to activate a speech processing block,
monitoring the received data to detect the presence of data representing a second portion of the trigger phrase in said received data, and further comprising, if said control signal to activate the speech processing block has previously been sent:
if the data representing the second portion of the trigger phrase is not detected, sending a deactivation command to deactivate the speech processing block; and
if said data representing the second portion of the trigger phrase is detected, maintaining the activation of said speech processing block;

after detecting the data representing the first portion of the trigger phrase:
supplying a part of the received data to an adaptive speech enhancement block, and
training the speech enhancement block to derive adapted parameters for the speech enhancement block; and

if the data representing the first portion of the trigger phrase is detected:
supplying at least a part of the received data to the speech enhancement block, operating with the adapted parameters, and
outputting enhanced data from the speech enhancement block.

2. A method as claimed in claim 1 wherein the step of monitoring the received data to detect the presence of data representing the first portion of the trigger phrase and the step of monitoring the received data to detect the presence of data representing the second portion of the trigger phrase occur in parallel.

3. A method as claimed in claim 1 wherein the step of monitoring the received data for the presence of data representing the second portion of the trigger phrase occurs as a result of detecting data representing the first portion of the trigger phrase.

4. A method as claimed in claim 1 wherein, if the data representing the second portion of the trigger phrase is detected, the step of maintaining the activation of the speech processing block comprises sending a confirmation signal to the speech processing block.

5. A method as claimed in claim 1 , wherein, if the data representing the second portion of the trigger phrase is detected, the step of maintaining the activation of the speech processing block comprises not sending the deactivation command.

6. A method as claimed in claim 1 further comprising:
if the data representing the second portion of the trigger phrase is detected, sending speech data to the speech processing block.

7. A method as claimed in claim 6 wherein the speech data is the received data.

8. A method as claimed in claim 1 further comprising:
if the data representing the first portion of the trigger phrase is detected, sending speech data to the speech processing block.

9. A method as claimed in claim 8 , wherein the speech data is the received data.

10. A method as claimed in claim 1 further comprising:
if the data representing the second portion of the trigger phrase is detected, supplying at least a part of the received data to the speech enhancement block, operating with the adapted parameters, and
outputting enhanced data from the speech enhancement block.

11. A method as claimed in claim 10 further comprising,
storing the received speech data, wherein the at least a part of the received data supplied to the speech enhancement block is the stored data starting from the beginning of the data representing the first portion of the trigger phrase.

12. A method as claimed in claim 10 further comprising,
storing the received speech data, wherein
the at least a part of the received data supplied to the speech enhancement block is the stored data starting from the end of the data representing the first portion of the trigger phrase.

13. A method as claimed in claim 10 further comprising,
storing the received data, wherein
the at least a part of the received data supplied to the speech enhancement block is the stored data starting from the end of the data representing the second portion of the trigger phrase.

14. A method as claimed in claim 10 wherein the at least a part of the received data supplied to the speech enhancement block, is the data received immediately after said detection.

15. A method as claimed in claim 10 wherein the speech data is the enhanced data outputted from the adaptive speech enhancement block.

16. A method as claimed in claim 1 further comprising, storing the received data.

17. A method as claimed in claim 1 wherein the first trigger phrase is the first part of the second trigger phrase.

18. A speech processor, comprising:
an input, for receiving data representing speech; and
a speech processing block,
wherein the speech processor is configured to perform a method of processing received data representing speech comprising the steps of:
monitoring the received data to detect the presence of data representing a first portion of a trigger phrase in said received data;
sending, on detection of said data representing the first portion of the trigger phrase, a control signal to activate the speech processing block, and
monitoring the received data to detect the presence of data representing a second portion of the trigger phrase in said received data, and further comprising:
if said control signal to activate the speech processing block has previously been sent:
if the data representing the second portion of the trigger phrase is not detected, sending a deactivation command to deactivate the speech processing block; and
if said data representing the second portion of the trigger phrase is detected, maintaining the activation of said speech processing block;

after detecting the data representing the first portion of the trigger phrase:
supplying a part of the received data to an adaptive speech enhancement block, and
training the speech enhancement block to derive adapted parameters for the speech enhancement block; and

if the data representing the first portion of the trigger phrase is detected:
supplying at least a part of the received data to the speech enhancement block, operating with the adapted parameters, and
outputting enhanced data from the speech enhancement block.

19. A speech processor, comprising:
an input, for receiving data representing speech; and
an output, for connection to a speech processing block,
wherein the speech processor is configured to perform a method of processing received data representing speech comprising the steps of:
monitoring the received data to detect the presence of data representing a first portion of a trigger phrase in said received data;
sending, on detection of said data representing the first portion of the trigger phrase, a control signal to activate the speech processing block, and
monitoring the received data to detect the presence of data representing a second portion of the trigger phrase in said received data, and further comprising, if said control signal to activate the speech processing block has previously been sent:
if the data representing the second portion of the trigger phrase is not detected, sending a deactivation command to deactivate the speech processing block; and
if said data representing the second portion of the trigger phrase is detected, maintaining the activation of said speech processing block;

af

Assignees

• Cirrus Logic Int Semiconductor Ltd
• Cirrus Logic Inc

Inventors

• Page Michael

Classifications

• G10L15/22 Primary

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

• G10L17/24 Primary

  the user being prompted to utter a password or a predefined phrase · CPC title

• G10L21/02

  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

• G10L15/32

  Multiple recognisers used in sequence or in parallel; Score combination systems therefor, e.g. voting systems · CPC title

• G10L15/063

  Training · CPC title