Proceedings of the 2015 International Conference on Electrical, Automation and Mechanical Engineering

A Primary Research on Gabor Tensor Sparse Features Representation for Whispered Speech Recognition

Authors
X.Q. Chen, H.M. Zhao, Y.B. Yu, H.W. Wu, Z. Liu
Corresponding Author
X.Q. Chen
Available Online July 2015.
DOI
10.2991/eame-15.2015.96How to use a DOI?
Keywords
speech recognition; whispered speech; Gabor filtering; feature extraction
Abstract

Due to differences between normal and whispered speech, traditional feature performed poorly for whispered recognition. In this paper, a novel approach for whispered speech feature representation is proposed based on Gabor filtering and tensor factorization. The sparse feature is extracted by processing the data samples in tensor structure. The simulation results indicate that our proposed feature is able to improve the whispered speech recognition performance.

Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

Volume Title
Proceedings of the 2015 International Conference on Electrical, Automation and Mechanical Engineering
Series
Advances in Engineering Research
Publication Date
July 2015
ISBN
978-94-62520-71-4
ISSN
2352-5401
DOI
10.2991/eame-15.2015.96How to use a DOI?
Copyright
© 2015, the Authors. Published by Atlantis Press.
Open Access
This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Cite this article

TY  - CONF
AU  - X.Q. Chen
AU  - H.M. Zhao
AU  - Y.B. Yu
AU  - H.W. Wu
AU  - Z. Liu
PY  - 2015/07
DA  - 2015/07
TI  - A Primary Research on Gabor Tensor Sparse Features Representation for Whispered Speech Recognition
BT  - Proceedings of the 2015 International Conference on Electrical, Automation and Mechanical Engineering
PB  - Atlantis Press
SP  - 346
EP  - 348
SN  - 2352-5401
UR  - https://doi.org/10.2991/eame-15.2015.96
DO  - 10.2991/eame-15.2015.96
ID  - Chen2015/07
ER  -