Publication Details

Deriving Spectro-temporal Properties of Hearing from Speech Data

ONDEL YANG, L.; LI, R.; SELL, G.; HEŘMANSKÝ, H. Deriving Spectro-temporal Properties of Hearing from Speech Data. In Proceedings of ICASSP. Brighton: IEEE Signal Processing Society, 2019. p. 411-415. ISBN: 978-1-5386-4658-8.
Czech title
Odvozování spektrálně-časových vlastností slyšení z řečových dat
Type
conference paper
Language
English
Authors
ONDEL YANG, L.
Li Ruizhi
SELL, G.
Heřmanský Hynek, prof. Ing. (DCGM)
URL
Keywords

perception, spectro-temporal, auditory, deep learning

Abstract

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.

Published
2019
Pages
411–415
Proceedings
Proceedings of ICASSP
ISBN
978-1-5386-4658-8
Publisher
IEEE Signal Processing Society
Place
Brighton
DOI
UT WoS
000482554000083
EID Scopus
BibTeX
@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"
}
Back to top