Audio device with distractor attenuator
An audio device comprising an interface, memory, and a processor is disclosed. A first microphone input signal and a second microphone input signal is processed for provision of an output audio signal; and output the output audio signal, wherein to process the microphone signals determine a first distractor indicator based on features associated with the input signals; determine a first distractor attenuation parameter based on the first distractor indicator; determine a second distractor indicator based on one or more features associated with the first microphone input signal and the second microphone input signal; determine a second distractor attenuation parameter based on the second distractor indicator; determine an attenuator gain based on the first distractor attenuation parameter and the second gain compensation parameter; and apply a noise suppression scheme to a first beamforming output signal according to the attenuator gain for provision of the output audio signal.
1. An audio device comprising an interface, memory, and a processor, wherein the processor is configured to:
obtain a first microphone input signal and a second microphone input signal;
process the first microphone input signal and the second microphone input signal for provision of an output audio signal;
wherein the processing of the first microphone input signal and the second microphone input signal comprises:
applying a first beamforming to the first microphone input signal and the second microphone input signal for provision of a first beamforming output signal;
determining a first distractor indicator based on one or more features associated with the first microphone input signal and the second microphone input signal;
determining a first distractor attenuation parameter based on the first distractor indicator;
determining a second distractor indicator based on one or more features associated with the first microphone input signal and the second microphone input signal;
determining a second distractor attenuation parameter based on the second distractor indicator;
determining an attenuator gain based on the first distractor attenuation parameter and the second distractor attenuation parameter; and
applying a noise suppression scheme to the first beamforming output signal according to the attenuator gain for provision of the output audio signal; and
output the audio signal via a wireless transceiver for wireless transmission or a connector for wired output of the interface,
wherein the audio device is a headset.
2. The audio device according to claim 1 ,
wherein the processing of the first microphone input signal and the second microphone input signal comprises determining a noise parameter indicative of ambient noise based on the first microphone input signal and the second microphone input signal, and
wherein the determining of the first distractor attenuation parameter is based on the first distractor indicator and the noise parameter.
3. The audio device according to claim 2 ,
wherein the determining of the noise parameter comprises obtaining one or more noise features associated with the first microphone input signal and/or the second microphone input signal, and
wherein the noise parameter is determined based on one or more noise features of the first microphone input signal and/or the second microphone input signal.
4. The audio device according to claim 2 ,
wherein the processing of the first microphone input signal and the second microphone input signal comprises determining a first speech parameter indicative of non-speech based on the first microphone input signal and the second microphone input signal, and
wherein a the determining of the noise parameter is based on the first speech parameter.
5. The audio device according to claim 1 , wherein the determining of the first distractor attenuation parameter comprises to determine determining whether a first limit criterion is satisfied, and in accordance with a determination that the first limit criterion is satisfied, limiting the first distractor attenuation parameter based on a first gain limit.
6. Audio The audio device according to claim 1 ,
wherein the processing of the first microphone input signal and the second microphone input signal comprises determining a second speech parameter indicative of speech based on the first microphone input signal and the second microphone input signal, and
wherein the determining of the first distractor attenuation parameter is based on the first distractor indicator and the second speech parameter.
7. The audio device according to claim 6 ,
wherein the determining of the second speech parameter comprises obtaining one or more speech features associated with the first microphone input signal and/or the second microphone input signal,
wherein the second speech parameter is determined based on one or more speech features of the first microphone input signal and/or the second microphone input signal.
8. The audio device according to claim 6 , wherein the first distractor attenuation parameter, in accordance with the second speech parameter being indicative of presence of speech, is set to a pass-through value.
9. The audio device according to claim 1 ,
wherein the processing of the first microphone input signal and the second microphone input signal comprises determining a beamformer performance parameter indicative of a performance of a beamformer that applies the first beamforming on the first microphone input signal and the second microphone input signal, and
wherein the determining of the second distractor attenuation parameter is based on the second distractor indicator and the beamformer performance parameter.
10. The audio device according to claim 9 , wherein the beamformer performance parameter is based on non-voice presence control signal from a non-voice activity detector and voice presence control signal from a voice activity detector.
11. The audio device according to claim 9 , wherein the determining of the second distractor attenuation parameter comprises determining whether a second limit criterion is satisfied, and in accordance with a determination that the second limit criterion is satisfied, limiting the second distractor attenuation parameter based on a second gain limit.
12. The audio device according to claim 1 , wherein the determining of the first distractor indicator comprises determining a first distractor indicator based on one or more features associated with the first microphone input signal and the second microphone input signal in a low-frequency range, such as in a frequency range from 125 Hz to 1125 Hz.
13. The audio device according to claim 1 , wherein the determining of the second distractor indicator comprises determining a second distractor indicator based on one or more features associated with the first microphone input signal and the second microphone input signal in a high-frequency range, such as in a frequency range from 5.5 kHz to 7 kHz.
14. The audio device according to claim 1 , wherein the attenuator gain comprises one or more gain values each being an interpolation of the first distractor attenuation parameter and the second gain compensation parameter.
15. The audio device according to claim 1 , wherein the first distractor indicator is based on a ratio between a feature being a first beamforming output signal magnitude and a feature being a second beamforming output signal magnitude.
16. The audio device according to claim 1 , wherein the second distractor indicator is based on a ratio between a feature being a first beamforming output signal magnitude and a feature being an omni magnitude.