Audio source classification for handsfree communications

A speech enhancement system comprising:

• a processing system;
• and
• a memory storing instructions that, when executed by the processing system, causes the speech enhancement system to:
• receive a first multi-channel audio signal via a plurality of microphones;
• determine a first relative impulse response between the plurality of microphones based on a frame of the first multi-channel audio signal;
• extract a set of first features from the first relative impulse response based at least in part on a peak of the first relative impulse response, wherein the set of first features includes a root mean square (RMS) of a pre-ring portion of the first relative impulse response normalized with respect to the peak, the pre-ring portion spanning a threshold duration ending at the peak;
• and
• train a Gaussian mixture model (GMM) to determine two non-covariate clusters including a target cluster and a distractor cluster, the target cluster associated with a target source of audio signals and the distractor cluster associated with a distractor source of audio signals, wherein the set of first features is classified as belonging to the target cluster or to the distractor cluster based at least in part on the normalized RMS of the pre-ring portion of the first relative impulse response, wherein the target cluster is associated with smaller values of the normalized RMS of the pre-ring portion as compared with the distractor cluster.