Robust Short-Time Fourier Transform Acoustic Echo Cancellation During Audio Playback

A method to be performed by a system comprising a playback device, the method comprising:

• causing, via an audio stage of the playback device, one or more speakers of the playback device to play back audio content;
• while audio content is playing back via the one or more speakers, capturing, via one or more microphones, audio within an acoustic environment, wherein the captured audio comprises audio signals representing sound produced by the one or more speakers in playing back the audio content;
• receiving an output signal from the audio stage representing the audio content being played back by the one or more speakers;
• determining a measured signal comprising a series of frames representing the captured audio within the acoustic environment by transforming into a short time Fourier transform (STFT) domain the captured audio within the acoustic environment;
• determining a reference signal comprising a series of frames representing the audio content being played back via the one or more speakers by transforming into the STFT domain the received output signal from the audio stage;
• during each nth iteration of an acoustic echo canceller (AEC):
• determining an nth frame of an output signal, wherein determining the nth frame of the output signal comprises:
• generating an nth frame of a model signal by passing an nth frame of the reference signal through an nth instance of an adaptive filter, wherein a first instance of the adaptive filter is an initial filter;
• and
• generating the nth frame of the output signal by redacting the nth frame of the model signal from an nth frame of the measured signal;
• determining a n+1th instance of the adaptive filter for a next iteration of the AEC, wherein determining the n+1th instance of the adaptive filter for the next iteration of the AEC comprises:
• determining an nth frame of an error signal, the nth frame of the error signal representing a difference between the nth frame of the model signal and the nth frame of the reference signal less audio signals representing sound from sources other than an nth frame of the audio signals representing sound produced by the one or more speakers in playing back the nth frame of the reference signal;
• determining a normalized least mean square (NMLS) of the nth frame of the error signal;
• determining a sparse NMLS of the nth frame of the error signal by applying to the NMLS of the nth frame of the error signal, a sparse partition criterion that zeroes out frequency bands of the NMLS having less than a threshold energy;
• converting the sparse NMLS of the nth frame of the error signal to an nth update filter;
• and
• generating the n+lth instance of the adaptive filter for the next iteration of the AEC by multiplying the nth instance of the adaptive filter by the nth update filter;
• and
• sending the output signal as a voice input to one or more voice services for processing of the voice input.

A tangible, non-transitory, computer-readable media having stored therein instructions executable by one or more processors to cause a system to perform operations comprising:

• causing, via an audio stage of a playback device, one or more speakers of the playback device to play back audio content;
• while audio content is playing back via the one or more speakers, capturing, via [[the]] one or more microphones, audio within an acoustic environment, wherein the captured audio comprises audio signals representing sound produced by the one or more speakers in playing back the audio content;
• receiving an output signal from the audio stage representing the audio content being played back by the one or more speakers;
• determining a measured signal comprising a series of frames representing the captured audio within the acoustic environment by transforming into a short time Fourier transform (STFT) domain the captured audio within the acoustic environment;
• determining a reference signal comprising a series of frames representing the audio content being played back via the one or more speakers by transforming into the STFT domain the received output signal from the audio stage;
• during each nth iteration of an acoustic echo canceller (AEC):
• determining an nth frame of an output signal, wherein determining the nth frame of the output signal comprises:
• generating an nth frame of a model signal by passing an nth frame of the reference signal through an nth instance of an adaptive filter, wherein a first instance of the adaptive filter is an initial filter;
• and
• generating the nth frame of the output signal by redacting the nth frame of the model signal from an nth frame of the measured signal;
• determining a n+1th instance of the adaptive filter for a next iteration of the AEC, wherein determining the n+lth instance of the adaptive filter for the next iteration of the AEC comprises:
• determining an nth frame of an error signal, the nth frame of the error signal representing a difference between the nth frame of the model signal and the nth frame of the reference signal less audio signals representing sound from sources other than an nth frame of the audio signals representing sound produced by the one or more speakers in playing back the nth frame of the reference signal;
• determining a normalized least mean square (NMLS) of the nth frame of the error signal;
• determining a sparse NMLS of the nth frame of the error signal by applying to the NMLS of the nth frame of the error signal, a sparse partition criterion that zeroes out frequency bands of the NMLS having less than a threshold energy;
• converting the sparse NMLS of the nth frame of the error signal to an nth update filter;
• and
• generating the n+1th instance of the adaptive filter for the next iteration of the AEC by multiplying the nth instance of the adaptive filter by the nth update filter;
• and
• sending the output signal as a voice input to one or more voice services for processing of the voice input.