Method, apparatus, and computer-readable storage medium for adaptive null-voice cancellation
The present disclosure relates to a method, apparatus, and computer-readable storage medium that modulate an audio output of a microphone array in order to isolate speech of a talker in a vehicle. For instance, the present disclosure describes a method for modulating an audio output of a microphone array, comprising receiving two or more audio signals from two or more microphone capsules in the microphone array, each audio signal comprising a response to acoustic stimuli in an environment perceived by a respective microphone capsule of the microphone array, estimating an acoustic noise contribution level of the environment based on the received audio signals, estimating a voice contribution level of the environment based on the received audio signals, and determining, by processing circuitry, a direct voice contribution level of the environment based on the estimated acoustic noise contribution level of the environment and the estimated voice contribution level of the environment.
1. A method for modulating an audio output of a microphone array located within a cabin of a vehicle, comprising:
receiving two or more audio signals from two or more microphone capsules in the microphone array, each of the two or more microphone capsules being located in a different area within the cabin of the vehicle, and each audio signal comprising a response to acoustic stimuli in an environment perceived by a respective microphone capsule of the microphone array;
estimating an acoustic noise contribution level of the environment based on the received two or more audio signals from the two or more microphone capsules, each of which is located in the different area within the cabin of the vehicle;
estimating a voice contribution level of the environment based on the received two or more audio signals from the two or more microphone capsules, each of which is located in the different area within the cabin of the vehicle; and
determining, by processing circuitry, a direct voice contribution level of the environment based on the estimated acoustic noise contribution level of the environment and the estimated voice contribution level of the environment.
2. The method of claim 1 , wherein the estimating the acoustic noise contribution level of the environment estimates the acoustic noise contribution level based on an output of a beamformer applied to an audio signal, of the received two or more audio signals, received from the microphone array, a null of a polar pattern of the applied beamformer being directed at a speech origin.
3. The method of claim 1 , wherein the estimating the voice contribution level of the environment estimates the voice contribution level based on an output of a beamformer applied to an audio signal, of the received two or more audio signals, received from the microphone array, a lobe of a polar pattern of the applied beamformer being directed at a speech origin in order to receive direct speech.
4. The method of claim 1 , wherein the determined direct voice contribution level of the environment includes at least a portion of an output of one or more of a plurality of beamformers.
5. The method of claim 1 , wherein the determined direct voice contribution level of the environment maximizes a signal to noise ratio of the microphone array by minimizing contributions of the estimated acoustic noise contribution level.
6. The method of claim 1 , wherein the determining determines the direct voice contribution level of the environment by
filtering the estimated voice contribution level of the environment according to the estimated acoustic noise contribution level of the environment.
7. The method of claim 6 , wherein the filtering filters the estimated voice contribution level of the environment by
applying an adaptive filter having coefficients updated by comparing an impulse response of a speech component of the estimated acoustic noise contribution level of the environment to an impulse response of speech reflections acquired from a database, the adaptive filter coefficients being updated when there is a correlation between the impulse response of the speech component and the impulse response of the speech reflections above a predetermined threshold.
8. The method of claim 6 , wherein the filtering filters the estimated voice contribution level of the environment based on an audio signal received from a voice activity detector.
9. An apparatus for modulating an audio output of a microphone array located within a cabin of a vehicle, comprising:
processing circuitry configured to
receive two or more audio signals from two or more microphone capsules in the microphone array, each of the two or more microphone capsules being located in a different area within the cabin of the vehicle, and each audio signal comprising a response to acoustic stimuli in an environment perceived by a respective microphone capsule of the microphone array,
estimate an acoustic noise contribution level of the environment based on the received two or more audio signals from the two or more microphone capsules, each of which is located in the different area within the cabin of the vehicle,
estimate a voice contribution level of the environment based on the received two or more audio signals from the two or more microphone capsules, each of which is located in the different area within the cabin of the vehicle, and
determine a direct voice contribution level of the environment based on the estimated acoustic noise contribution level of the environment and the estimated voice contribution level of the environment.
10. The apparatus of claim 9 , wherein the processing circuitry is configured to estimate the acoustic noise contribution level based on an output of a beamformer applied to an audio signal, of the received two or more audio signals, received from the microphone array, a null of a polar pattern of the applied beamformer being directed at a speech origin.
11. The apparatus of claim 9 , wherein the processing circuitry is configured to estimate the voice contribution level based on an output of a beamformer applied to an audio signal, of the received two or more audio signals, received from the microphone array, a lobe of a polar pattern of the applied beamformer being directed at a speech origin in order to receive direct speech.
12. The apparatus of claim 9 , wherein the determined direct voice contribution level of the environment maximizes a signal to noise ratio of the microphone array by minimizing contributions of the estimated acoustic noise contribution level.
13. The apparatus of claim 9 , wherein, in order to determine the direct voice contribution level of the environment, the processing circuitry is further configured to
filter the estimated voice contribution level of the environment according to the estimated acoustic noise contribution level of the environment.
14. The apparatus of claim 13 , wherein, in order to filter the estimated voice contribution level of the environment, the processing circuitry is further configured to
apply an adaptive filter having coefficients updated by comparing an impulse response of a speech component of the estimated acoustic noise contribution level of the environment to an impulse response of speech reflections acquired from a database, the adaptive filter coefficients being updated when there is a correlation between the impulse response of the speech component and the impulse response of the speech reflections above a predetermined threshold.
15. A non-transitory computer-readable storage medium storing computer-readable instructions that, when executed by a computer, cause the computer to perform a method for modulating an audio output of a microphone array located within a cabin of a vehicle, the method comprising:
receiving two or more audio signals from two or more microphone capsules in the microphone array, each of the two or more microphone capsules being located in a different area within the cabin of the vehicle, and each audio signal comprising a response to acoustic stimuli in an environment perceived by a respective microphone capsule of the microphone array;
estimating an acoustic noise contribution level of the environment based on the received two or more audio signals from the two or more microphone capsules, each of which is located in the different area within the cabin of the vehicle;
estimating a voice contribution level of the environment based on the received two or more audio signals from the two or more microphone capsules, each of which is located in the different area within the cabin of the vehicle; and
determining a direct voice contribution level of the environment based on the estimated acoustic noise contribution level of the environment and the estimated voice contribution level of the environment.
16. The non-transitory computer-readable storage medium of claim 15 , wherein the estimating the acoustic noise contribution level of the environment estimates the acoustic noise contribution level based on an output of a beamformer applied to an audio signal, of the received two or more audio signals, received from the microphone array, a null of a polar pattern of the applied beamformer being directed at a speech origin.
17. The non-transitory computer-readable storage medium of claim 15 , wherein the estimating the voice contribution level of the environment estimates the voice contribution level based on an output of a beamformer applied to an audio signal, of the received two or more audio signals, received from the microphone array, a lobe of a polar pattern of the applied beamformer being directed at a speech origin in order to receive direct speech.
18. The non-transitory computer readable storage medium of claim 15 , wherein the determined direct voice contribution level of the environment includes at least a portion of an output of one or more of a plurality of beamformers.
19. The non-transitory computer readable storage medium of claim 15 , wherein the determined direct voice contribution level of the environment maximizes a signal to noise ratio of the microphone array by minimizing contributions of the estimated acoustic noise contribution level.
20. The non-transitory computer readable storage medium of claim 15 , wherein the determining determines the direct voice contribution level of the environment by filtering the estimated voice contribution level of the environment according to the estimated acoustic noise contribution level of the environment.