Publication Details
Deriving Spectro-temporal Properties of Hearing from Speech Data
perception, spectro-temporal, auditory, deeplearning
Human hearing and human speech are intrinsically tied together, asthe properties of speech almost certainly developed in order to beheard by human ears. As a result of this connection, it has beenshown that certain properties of human hearing are mimicked withindata-driven systems that are trained to understand human speech.In this paper, we further explore this phenomenon by measuring thespectro-temporal responses of data-derived filters in a front-end convolutionallayer of a deep network trained to classify the phonemesof clean speech. The analyses show that the filters do indeed exhibitspectro-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 ArticulationIndex.
@inproceedings{BUT160004,
author="ONDEL YANG, L. and LI, R. and SELL, G. and HEŘMANSKÝ, H.",
title="Deriving Spectro-temporal Properties of Hearing from Speech Data",
booktitle="Proceedings of ICASSP",
year="2019",
pages="411--415",
publisher="IEEE Signal Processing Society",
address="Brighton",
doi="10.1109/ICASSP.2019.8682787",
isbn="978-1-5386-4658-8",
url="https://ieeexplore.ieee.org/document/8682787"
}