User voice activity detection

Patent metadata

Field	Value
Publication number	US-11614916-B2
Application number	US-201916730134-A
Country	US
Kind code	B2
Filing date	Dec 30, 2019
Priority date	Feb 7, 2017
Publication date	Mar 28, 2023
Grant date	Mar 28, 2023

Abstract

Many headsets include automatic noise cancellation (ANC) which dramatically reduces perceived background noise and improves user listening experience. Unfortunately, the voice microphones in these devices often capture ambient noise that the headsets output during phone calls or other communication sessions to other users. In response, many headsets and communication devices provide manual muting circuitry, but users frequently forget to turn the muting on and/or off creating further problems as they communicate. To address this, the present inventors devised, among other things, an exemplary headset that detects the absence or presence of user speech, automatically muting and unmuting the voice microphone without user intervention. Some embodiments leverage relationships between feedback and feedforward signals in ANC circuitry to detect user speech, avoiding the addition of extra hardware to the headset. Other embodiments also leverage the speech detection function to activate and deactivate keyword detectors, and/or sidetone circuits, thus extending battery.

First claim

What is claimed is:

1. An audio processing system comprising:
a headset to be worn on the head of a user, the headset being one of an in-the-ear headset, an over-the-ear headset, or an on-the-ear headset;
a plurality of inputs to receive a plurality of audio signals from a plurality of transducers disposed in the headset, the plurality of inputs including a first input to receive a first audio signal from a first transducer disposed proximate a first ear of a user, a second input to receive a second audio signal received from a second transducer disposed proximate a second ear of the user, a third input to receive a third audio signal from a third transducer disposed proximate a vocal region of the user, and a fourth input to receive a fourth audio signal from a fourth transducer, the fourth transducer being disposed proximate the first ear of the user but more distant from the first ear of the user than the first transducer; and
processing circuitry coupled to the plurality of inputs and configured to receive the first, second, third, and fourth audio signals, to compare a magnitude and a phase of speech components of the first audio signal, the second audio signal, and the fourth audio signal to determine that the speech components are provided by the user in response to determining that the magnitude and the phase of the speech components of the first audio signal and the second audio signal are substantially identical and that the magnitude of the speech components of the first audio signal and the fourth audio signal are substantially different, and to provide a voice activity detection signal indicative of whether the speech components are provided by the user.

2. The audio processing system of claim 1 wherein the processing circuitry is further configured to at least one of mute or attenuate the third audio signal responsive to determining that the speech components are not provided by the user.

3. The audio processing system of claim 1 wherein the first, second, third, and fourth transducers are microphones.

4. The audio processing system of claim 1 wherein the processing circuitry determines that the speech components are not provided by the user in response to the comparison indicating that at least the phase of the speech components of the first audio signal and the second audio signal are not substantially identical.

5. The audio processing system of claim 1 wherein the processing circuitry determines that the speech components are provided by the user in response to the comparison indicating that the magnitude and phase of the speech components of the first audio signal and the second audio signal are substantially identical and at least the magnitude of the first audio signal is substantially greater than the magnitude of the fourth audio signal.

6. A method of processing audio signals from a headset to be worn on the head of a user, the headset being one of an in-the-ear headset, an over-the-ear headset, or an on-the-ear headset, the method comprising:
receiving a first audio signal from a first transducer disposed in the headset proximate a first ear of a user;
receiving a second audio signal from a second transducer disposed in the headset proximate a second ear of the user;
receiving a third audio signal from a third transducer disposed in the headset proximate a vocal region of the user;
receiving a fourth audio signal from a fourth transducer disposed in the headset proximate the first ear of the user but more distant from the first ear of the user than the first transducer;
comparing a magnitude and a phase of speech components of the first audio signal, the second audio signal, and the fourth audio signal;
determining, based on the comparison, that the speech components are provided by the user in response to determining that the magnitude and phase of the speech components of the first audio signal and the second audio signal are substantially identical and that the magnitude of the speech components of the first audio signal and the fourth audio signal are substantially different; and
providing a voice activity detection signal indicative of whether the speech components are provided by the user.

7. The method of claim 6 further comprising at least one of muting or attenuating the third audio signal responsive to determining that the speech components are not provided by the user.

8. The audio processing system of claim 6 wherein determining that the speech components are provided by the user in response is performed in response to the comparison indicating that the magnitude and phase of the speech components of the first audio signal and the second audio signal are substantially identical and at least the magnitude of the first audio signal is substantially greater than the magnitude of the fourth audio signal.

Assignees

• Avnera Corp

Inventors

• An Jiajin
• Wurtz Michael Jon
• Wurtz David
• Khaira Manpreet
• Kumar Amit
• O'Connor Shawn
• Rathoud Shankar
• Scanlan James
• Sorensen Eric

Classifications

• G10L25/84 Primary

  for discriminating voice from noise · CPC title

• H04R1/1083

  Reduction of ambient noise (active noise reduction per se G10K11/175; protective devices for the ear, e.g. providing acoustic protection A61F11/06) · CPC title

• G10K11/1781

  characterised by the analysis of input or output signals, e.g. frequency range, modes, transfer functions · CPC title

• H04R1/1041

  Mechanical or electronic switches, or control elements (switches in general H01H) · CPC title

• H04R3/005

  for combining the signals of two or more microphones (specially adapted for hearing aids H04R25/407) · CPC title