Microphone channel self-noise silencing

One or more non-transitory computer-readable media storing instructions executable to perform operations, the operations comprising:

• receiving an audio signal generated by a microphone;
• generating an input feature representing a plurality of frequency components of the audio signal;
• applying a machine learning model to the input feature, the machine learning model trained to infer frequencies attributable to self-noise generated at the microphone from the input feature;
• generating, based on the machine learning model, an attenuation mask;
• and
• applying the attenuation mask to at least a subset of the plurality of frequency components of the audio signal to remove the self-noise from the audio signal.

A computer-implemented method, comprising:

• receiving an audio signal generated by a microphone;
• generating an input feature representing a plurality of frequency components of the audio signal;
• applying a machine learning model to the input feature, the machine learning model trained to infer frequencies attributable to self-noise generated at the microphone from the input feature;
• generating, based on the machine learning model, an attenuation mask;
• and
• applying the attenuation mask to at least a subset of the plurality of frequency components of the audio signal to remove the self-noise from the audio signal.