Adaptive noise estimation

A method of adaptive noise estimation, comprising:

• dividing, using at least one processor, an audio input into speech and non-speech segments;
• for each frame in each non-speech segment, estimating, using the at least one processor, a time-varying noise spectrum of the non-speech segment and reducing noise in the audio input based on the time-varying noise spectrum;
• for each frame in each speech segment:
• estimating, using the at least one processor, a speech spectrum of the speech segment;
• identifying one or more non-speech frequency components in the speech spectrum;
• comparing the one or more non-speech frequency components with one or more corresponding frequency components in a plurality of estimated noise spectra, wherein the plurality of estimated noise spectra comprises a first estimated noise spectrum for a past non-speech segment and a second estimated noise spectrum for a future non-speech segment;
• selecting one of the first or second estimated noise spectrums based on a result of the comparing;
• and
• reducing noise in the audio input based on the selected first or second estimated noise spectrum.