Learning phase-rich features from streaming auditory images
Mohit L. Dubey, Peter F. Shultz, Garrett T. Kenyon · 2016
Sparse codes for auditory stimuli are typically based on time-dependent power spectra. These spectrographic images result in the loss of phase information at fine temporal scales that could be useful for subsequent downstream processing tasks, such as monaural source separation. Using a resonance model of the human cochlea, we were able to learn spectrotemporal features on a sliding window of auditory images that allowed for phase rich reconstructions that remained accurate to millisecond scales. Moreover, we showed that such features exhibit tonotopy when trained on musical input and are useful in denoising. To our knowledge, this is the first demonstration of how sparsely activated auditory features that preserve phase information on time scales relevant to monaural source segmentation can be learned on streaming spectrotemporal auditory images.