User Voice Activity Detection Methods, Devices, Assemblies, and Components

• US 20180225082A1
• Filed: 09/21/2017
• Published: 08/09/2018
• Est. Priority Date: 02/07/2017
• Status: Active Grant

• Current Assignee: Avnera (Skyworks Solutions Incorporated)
• Original Assignee: Avnera (Skyworks Solutions Incorporated)
• Inventors: An, Jiajin, Wurtz, MIchael Jon, Wurtz, David, Khaira, Manpreet, Kumar, Amit, O'Connor, Shawn, Rathoud, Shankar, Scanlan, James, Sorensen, Eric
• Granted Patent: US 10,564,925 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 1/3206 Monitoring of events, devices or parameters that trigger a change in power modality
• CPC Class Codes: G06F 1/3287 by switching off individual functional units in the computer system
• CPC Class Codes: G06F 3/165 Management of the audio stream, e.g. setting of volume, audio stream path
• CPC Class Codes: G10K 11/1781 characterised by the analysis of input or output signals, e.g. frequency range, modes, transfer functions
• CPC Class Codes: G10K 2210/1081 Earphones, e.g. for telephones, ear protectors or headsets
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 25/84 for discriminating voice from noise
• CPC Class Codes: H04R 1/1041 Mechanical or electronic switches, or control elements switches in general H01H
• 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 2201/107 Monophonic and stereophonic headphones with microphone for two-way hands free communication
• CPC Class Codes: H04R 2460/13 Hearing devices using bone conduction transducers
• 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 5/033 Headphones for stereophonic communication details thereof, e.g. relating to batteries, cables or control elements H04R1/10
• CPC Class Codes: Y02D 10/00 Energy efficient computing, e.g. low power processors, power management or thermal management

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.

Claims

1. A communication assembly comprising:

an incoming audio signal node configured for connection to a communication device that provides an incoming audio signal Rx;

signal processing circuitry configured to output a voice activity detection signal indicative of a determined absence or presence of user speech, the signal processing circuitry configured to determine absence or presence of user speech based on a first signal Φ

, a second signal θ

, and a third signal, with the ϕ and

θ

signals derived from two or more transducers responsive to at least the ambient noise a, user speech s, and the audio input signal u, with the ϕ and

θ

signals satisfying a constraint

2. The communication assembly of claim 1, wherein the two or more transducers include first and second mics, with the first mic positioned with substantially greater acoustic coupling to a user vocal region than the second mic.

3. The communication assembly of claim 2, wherein the first mic is positioned to receive more acoustic energy from the user vocal region via a bone conduction path than the second mic.

4. The communication assembly of claim 1, further comprising

an automatic muting module configured to attenuate a voice mic output signal in response to the voice activity detection signal indicating a determined absence of user speech and to de-attenuate the voice mic output signal in response to the voice activity detection signal indicating presence of user speech.

5. The communication assembly of claim 1, wherein the automatic muting module is configured to mute or attenuate the voice mic output signal a predetermined amount of time after receipt of the voice activity detection signal.

6. The communication assembly of claim 1, further comprising:

a keyword recognition module configured to recognize one or more keywords within user speech signals derived from a voice mic output signal and responsive to the voice activity detection signal indicating a determined absence of user speech to enter a shutdown or sleep state to conserve power or memory.

7. The communication assembly of claim 1, further comprising:

a side tone module responsive to user speech to provide a side tone signal to a loud speaker within a headset earpiece and responsive to the voice activity detection signal indicating a determined absence of user speech to enter a shutdown or sleep state to conserve power or memory.

8. The communication assembly of claim 1, further comprising:

a side tone module responsive to user speech to provide a side tone signal to a loud speaker within a headset earpiece and responsive to the voice activity detection signal indicating a determined absence of user speech to enter a shutdown or sleep state to conserve power or memory.

9. The communication assembly of claim 1, further comprising:

a noise reduction module responsive to the voice activity detection signal indicating a determined presence of user speech to reduce noise in a first way and responsive to the voice activity detection signal indicating a determined absence of user speech to reduce noise in a second way.

10. The communication assembly of claim 1, further comprising:

at least one speech-dependent module configured for operation in a manner dependent on speech content of a voice mic output signal and responsive to the voice activity detection signal indicating a determined absence of user speech to enter a power and/or memory conservation mode.

11. The communication assembly of claim 1,

wherein the assembly includes a first node configured for connection to a loud speaker associated with a headset earpiece;

a second node configured for connection to a feedforward ambient mic associated with the headset earpiece, and a third node configured for connection to a feedback error mic associated with headset earpiece;

wherein signal processing circuitry is coupled to the first, second and third nodes, and configured to provide an anti-noise signal to the loud speaker in response to signals originating from the feedforward ambient mic and the feedback error mic; and

wherein the ϕ and

θ

signals are derived from signals originating from the feedforward ambient mic and the feedback error mic.

12. The communication assembly of claim 11, wherein the signal processing circuitry is further configured to indicate absence of the user speech when the first and second transducers are placed on a standard head and torso simulator (HATS) that is outputting a speech signal in the range.

13. The communication assembly of claim 11, wherein the headset earpiece in an in-the-ear earpiece having an ear-canal portion containing the feedback error mic.

14. A method of operating a communication assembly having a voice mic output signal and a set of two or more transducers, the method comprising:

determining whether a user of the communication assembly is speaking based on the output of the two or more transducers; and

in response to a determination that the use is not speaking, changing the operating state of one or more speech-dependent modules associated with the communication assembly to a resource conservation state.

15. The method of claim 14, wherein the one or more speech-dependent module includes at least one of:

a muting module configured to mute the voice mic output signal in response to the determination that the user is not speaking;

a keyword recognition module configured to recognize one or more spoken words or phrases; and

a side tone module configured to generate a side tone signal based on the voice mic output signal.

16. The method of claim 14, wherein determining whether a user of the communication assembly is speaking based on the output of the two or more transducers, comprises

deriving a first signal Φ

, a second signal θ

, and a third signal, with the ϕ and

θ

signals derived from the two or more transducers transducing an ambient noise signal a, user speech signal s, and a third signal, with the ϕ and

θ

signals satisfying a constraint

18. A communication assembly comprising:

first and second transducers configured to be worn on a user head, with the first transducer configured for substantially greater acoustic coupling to a user vocal region than the second transducer; and

signal processing circuitry configured to output a voice activity detection signal indicative of a determined absence or presence of user speech in a predetermined frequency range when the first and second transducers are mounted to a user head; and

wherein the signal processing circuitry is further configured to indicate absence of user speech when the first and second transducers are positioned on a standard head and torso simulator (HATS) that is outputting a speech signal in the predetermined frequency range.

19. The communication assembly of claim 18,

wherein the assembly includes an earpiece having a loud speaker, a feedforward ambient mic, a feedback error mic, a voice mic, and a an incoming audio signal node configured for connection to a communication device that provides an incoming audio signal Rx;

wherein the signal processing circuitry is configured to determine absence or presence of user speech based on a first signal Φ

, a second signal θ

, and a third signal, with the ϕ and

θ

signals derived at least from output signals of at least two of the feedforward ambient mic, the feedback error mic, and the voice mic in response to ambient noise a, user speech s, and a third signal, with the ϕ and

θ

signals satisfying a constraint

20. The communication assembly of claim 19:

wherein the processing circuitry is further configured to provide an anti-noise signal to the loud speaker in response to signals originating from the feedforward ambient mic and the feedback error mic; and

wherein the assembly further comprises a set of one or more speech-dependent modules, with each speech dependent module responsive to the voice activity detection signal indicating absence of user speech to enter a power or memory conservation state and responsive to the voice activity detection signal indicating presence of user speech to exit the power or memory conversation state; and

wherein the set of one or more of the speech-dependent modules includes;

a voice mic output module configured to output a voice mic signal to the communication device;

a keyword recognition module configured to recognize one or more spoken words or phrases; and

a side tone module configured to generate a side tone signal based on the voice mic output signal.