Voice activity detection for communication headset

• US 10,249,323 B2
• Filed: 05/31/2017
• Issued: 04/02/2019
• Est. Priority Date: 05/31/2017
• Status: Active Grant

• Current Assignee: Bose Corporation
• Original Assignee: Bose Corporation
• Inventors: Saffran, Richard E.
• Primary Examiner(s): Hang, Vu B
• Application Number:
  US15/609,297
• Publication Number:
  US 20180350394A1
• Time in Patent Office: 671 Days
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2025/783 based on threshold decision
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• 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
• CPC Class Codes: G10L 25/84 for discriminating voice from noise
• CPC Class Codes: H04R 1/1083 Reduction of ambient noise active noise reduction per se G10K11/175; protective devices for the ear, e.g. providing acoustic protection A61F11/06
• CPC Class Codes: H04R 1/406 microphones
• CPC Class Codes: H04R 2430/25 Array processing for suppression of unwanted side-lobes in directivity characteristics, e.g. a blocking matrix
• CPC Class Codes: H04R 25/405 by combining a plurality of transducers
• CPC Class Codes: H04R 25/407 Circuits for combining signals of a plurality of transducers
• CPC Class Codes: H04R 25/552 Binaural
• CPC Class Codes: H04R 3/005 for combining the signals of two or more microphones specially adapted for hearing aids H04R25/407
• CPC Class Codes: H04R 3/04 for correcting frequency response

Abstract

A headset and a method for determining that a headset user is speaking, includes receiving a first signal from a first microphone and receiving a second signal from a second microphone. A principal signal is provided from a sum of the first and second signals. A reference signal is provided from a difference between the first and second signals. A rate of change of at least one of the principal signal or the reference signal is limited by a time constant. The principal signal and the reference signal are compared, and an indication that the user is speaking is selectively made based at least in part upon the comparison.

Claims

1. A method of determining that a headset user is speaking, the method comprising:

receiving a first signal from a first microphone;

receiving a second signal from a second microphone;

adding the first signal and the second signal, by a processor, to generate a principal signal;

subtracting, by the processor, one of the first signal and the second signal from the other of the first signal and the second signal to generate a reference signal;

limiting a rate of change, by the processor, of at least one of the principal signal or the reference signal by a time constant;

comparing the principal signal to the reference signal, by the processor, to determine whether the principal signal exceeds the reference signal by a threshold amount;

selectively indicating that the user is speaking, responsive to determining that the principal signal exceeds the reference signal by the threshold amount; and

activating a voice operated control in response to selectively indicating that the user is speaking.

2. The method of claim 1 further comprising comparing a level at which the user is speaking to an appropriate level to be audible over a background noise.

3. The method of claim 2 further comprising providing an indication to the user of whether the user is speaking at the appropriate level.

4. The method of claim 1 further comprising band filtering at least one of the first signal, the second signal, the principal signal, and the reference signal.

5. The method of claim 1 wherein the time constant is a first time constant applied to the principal signal and further comprising limiting a rate of change of the reference signal by a second time constant.

6. The method of claim 5 wherein the second time constant is longer than the first time constant.

18. The method of claim 1 wherein the voice operated control includes at least one of cueing an audio recording, cueing a voice recognition system, activating a virtual personal assistant, triggering an automatic gain control, adjusting an echo processing or cancellation, adjusting a noise processing, cancellation, or suppression, and adjusting a sidetone gain.

7. A communication headset, comprising:

a left microphone associated with a left earpiece to provide a left signal;

a right microphone associated with a right earpiece to provide a right signal; and

a detection circuit coupled to the left and right microphones and configured to;

add the left and right signals to determine a principal signal,

take a difference between the left and right signals to determine a reference signal,

limit a rate of change of at least one of the principal signal and the reference signal by a time constant,

compare the principal signal to the reference signal to determine whether the principal signal exceeds the reference signal by a threshold amount, and

selectively indicate to a voice operated component that the user is speaking based at least in part upon the determination that the principal signal exceeds the reference signal by the threshold amount.

8. The communication headset of claim 7 wherein each of the principal signal and the reference signal is band filtered.

9. The communication headset of claim 7 wherein the detection circuit is further configured to compare a level at which the user is speaking to an appropriate level of speech to be audible over a background noise.

10. The communication headset of claim 9 wherein the detection circuit is further configured to provide an indication to the user of whether the user is speaking at the appropriate level.

11. The communication headset of claim 7 wherein the time constant is a first time constant applied to the principal signal and the detection circuit is further configured to limit a rate of change of the reference signal by a second time constant.

12. The communication headset of claim 11 wherein the second time constant is longer than the first time constant.

19. The communication headset of claim 7 wherein the voice operated component is configured to perform at least one of cueing an audio recording, cueing a voice recognition system, activating a virtual personal assistant, triggering an automatic gain control, adjusting an echo processing or cancellation, adjusting a noise processing, cancellation, or suppression, and adjusting a sidetone gain.

13. A non-transitory computer readable medium having instructions encoded therein that, when processed by a suitable processor, cause the processor to perform a method comprising:

receiving a first signal from a first microphone;

receiving a second signal from a second microphone;

adding the first signal and the second signal to generate a principal signal;

taking a difference between the first signal and the second signal to generate a reference signal;

limiting a rate of change of at least one of the principal signal or the reference signal by a time constant;

comparing the principal signal to the reference signal to determine whether the principal signal exceeds the reference signal by a threshold amount;

selectively indicating that a user is speaking, responsive to determining that the principal signal exceeds the reference signal by the threshold amount; and

activating a voice operated control in response to selectively indicating that the user is speaking.

14. The non-transitory computer readable medium of claim 13 further comprising instructions for comparing a level at which the user is speaking to an appropriate speech level and for indicating whether the user is speaking at the appropriate speech level.

15. The non-transitory computer readable medium of claim 13 further comprising instructions for band filtering at least one of the first signal, the second signal, the principal signal, and the reference signal.

16. The non-transitory computer readable medium of claim 13 wherein the time constant is a first time constant applied to the principal signal and further comprising limiting a rate of change of the reference signal by a second time constant.

17. The non-transitory computer readable medium of claim 16 wherein the second time constant is longer than the first time constant.

20. The non-transitory computer readable medium of claim 13 wherein the voice operated control includes at least one of cueing an audio recording, cueing a voice recognition system, activating a virtual personal assistant, triggering an automatic gain control, adjusting an echo processing or cancellation, adjusting a noise processing, cancellation, or suppression, and adjusting a sidetone gain.