Skip to content

Publications

Detail of publication

Citation

Jan Zelinka and Petr Salajka and Luděk Müller : On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum . Speech and Computer, 17th International Conference, SPECOM 2015, p. 301-308, Springer, 2015.

Abstract

This paper demonstrates how usual feature extraction methods such as the PLP can be successfully replaced by a neural network and how signal processing methods such as mean normalization, variance normalization and delta coefficients can be successfully utilized when a NN-based feature extraction and a NN-based acoustic model are used simultaneously. The importance of the deep NNs is also investigated. The system performance was evaluated on the British English speech corpus WSJCAM0.

Detail of publication

Title: On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum
Author: Jan Zelinka ; Petr Salajka ; Luděk Müller
Language: English
Year: 2015
Type of publication: Papers in proceedings of reviewed conferences
Title of journal or book: Speech and Computer, 17th International Conference, SPECOM 2015
Page: 301 - 308
ISBN: 978-3-319-23131-0
ISSN: 0302-9743
Publisher: Springer
/ 2019-11-18 12:54:45 /

BibTeX

@MISC{JanZelinka_2015_OnDeepandShallow,
 author = {Jan Zelinka and Petr Salajka and Lud\v{e}k M\"{u}ller},
 title = {On Deep and Shallow Neural Networks in Speech Recognition from Speech Spectrum},
 year = {2015},
 publisher = {Springer},
 journal = {Speech and Computer, 17th International Conference, SPECOM 2015},
 pages = {301-308},
 ISBN = {978-3-319-23131-0},
 ISSN = {0302-9743},
 url = {http://www.kky.zcu.cz/en/publications/JanZelinka_2015_OnDeepandShallow},
}