Publication detail

Deriving Spectro-temporal Properties of Hearing from Speech Data

ONDEL YANG, L. LI, R. SELL, G. HEŘMANSKÝ, H.

Original Title

Deriving Spectro-temporal Properties of Hearing from Speech Data

Type

conference paper

Language

English

Original 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.

Keywords

perception, spectro-temporal, auditory, deep learning

Authors

ONDEL YANG, L.; LI, R.; SELL, G.; HEŘMANSKÝ, H.

Released

12. 5. 2019

Publisher

IEEE Signal Processing Society

Location

Brighton

ISBN

978-1-5386-4658-8

Book

Proceedings of ICASSP

Pages from

411

Pages to

415

Pages count

5

URL

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"
}