DERIVING SPECTRO-TEMPORAL PROPERTIES OF HEARING FROM SPEECH DATA

Human hearing and human speech are intrinsically tied together, as the properties of speech almost certainly developed in order to be heard by human ears. As a result of this connection, it has been shown that certain properties of human hearing are mimicked within data-driven systems that are trained to understand human speech. In this paper, we further explore this phenomenon by measuring the spectro-temporal responses of data-derived filters in a front-end convolutional layer of a deep network trained to classify the phonemes of clean speech. The analyses show that the filters do indeed exhibit spectro-temporal responses similar to those measured in mammals, and also that the filters exhibit an additional level of frequency selectivity, similar to the processing pipeline assumed within the Articulation Index.