Voice Activity Detection (VAD) for a Coded Speech Bitstream without Decoding

• US 20150154981A1
• Filed: 12/02/2013
• Published: 06/04/2015
• Est. Priority Date: 12/02/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Sharma, Dushyant, Barreda, Daniel A., Lainez, Jose E.G., Naylor, Patrick
• Granted Patent: US 9,997,172 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G10L 25/78 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

Abstract

A system, method and computer program product are described for voice activity detection (VAD) within a digitally encoded bitstream. A parameter extraction module is configured to extract parameters from a sequence of coded frames from a digitally encoded bitstream containing speech. A VAD classifier is configured to operate with input of the digitally encoded bitstream to evaluate each coded frame based on bitstream coding parameter classification features to output a VAD decision indicative of whether or not speech is present in one or more of the coded frames.

Claims

1. A system for voice activity detection (VAD) within a digitally encoded bitstream, the system comprising:

a parameter extraction module configured to extract parameters from a sequence of coded frames from a digitally encoded bitstream containing speech; and

a VAD classifier configured to operate with input of the digitally encoded bitstream to evaluate each coded frame based on bitstream coding parameter classification features to output a VAD decision indicative of whether or not speech is present in one or more of the coded frames.

2. The system according to claim 1, further comprising:

a speech enhancement module configured to perform speech enhancement based on the VAD decision for each coded frame.

3. The system according to claim 1, further comprising:

a VAD smoothing module configured to smooth the VAD decisions for the coded frames based on the VAD decisions of some number N neighboring coded frames.

4. The system according to claim 1, further comprising:

a hysteresis module configured to introduce a hysteresis element to the VAD decisions based on a defined hold on and/or hold off time.

5. The system according to claim 1, wherein the VAD classifier is a Classification and Regression Tree (CART) classifier or a Deep Belief Network (DBN) classifier.

6. The system according to claim 1, wherein the VAD classifier one or more of a plurality of VAD classifiers selected based on bit rate of the digital bitstream.

7. The system according to claim 1, wherein the digital bitstream is an adaptive multi-rate (AMR) coded bitstream and the bitstream coding parameter classification features are AMR encoding features.

8. A method for voice activity detection implemented as a plurality of computer processes executing on at least one hardware processor, the method comprising:

extracting parameters from a sequence of coded frames from a digitally encoded bitstream containing speech; and

evaluating each coded frame with a voice activity detection (VAD) classifier operating based on bitstream coding parameter classification features with input of the digitally encoded bitstream to output a VAD decision whether or not speech is present in one or more of the coded frames.

9. The method according to claim 8, further comprising:

based on the VAD decision for each coded frame, making an enhancement decision whether or not to perform speech enhancement processing.

10. The method according to claim 8, further comprising:

smoothing the VAD decisions for the coded frames based on the VAD decisions of some number N neighboring coded frames.

11. The method according to claim 8, further comprising:

introducing a hysteresis element to the VAD decisions based on a defined hold on and/or hold off time.

12. The method according to claim 8, wherein the VAD classifier is a Classification and Regression Tree (CART) classifier or a Deep Belief Network (DBN) classifier.

13. The method according to claim 8, wherein the VAD classifier is one or more VAD classifiers selected from a plurality of VAD classifiers based on bit rate of the digital bitstream.

14. The method according to claim 8, wherein the digital bitstream is an adaptive multi-rate (AMR) coded bitstream and the bitstream coding parameter classification features are AMR encoding features.

15. A computer program product implemented in a tangible computer readable storage medium for voice activity detection, the product comprising:

program code for extracting parameters from a sequence of coded frames from a digitally encoded bitstream containing speech; and

program code for evaluating each coded frame with a voice activity detection (VAD) classifier operating based on bitstream coding parameter classification features with input of the digitally encoded bitstream to output a VAD decision whether or not speech is present in one or more of the coded frames.

16. The product according to claim 15, further comprising:

program code for making an enhancement decision whether or not to perform speech enhancement processing for each coded frame based on the VAD decision.

17. The product according to claim 15, further comprising:

program code for smoothing the VAD decisions for the coded frames based on the VAD decisions of some number N neighboring coded frames.

18. The product according to claim 15, further comprising:

program code for introducing a hysteresis element to the VAD decisions based on a defined hold on and/or hold off time.

19. The product according to claim 15, wherein the VAD classifier is a Classification and Regression Tree (CART) classifier or a Deep Belief Network (DBN) classifier.

20. The product according to claim 15, wherein the VAD classifier is one or more VAD classifiers selected from a plurality of VAD classifiers based on bit rate of the digital bitstream.