Robust speech recognition by selecting mel-filter banks

DOI

10.2991/eeeis-16.2017.52How to use a DOI?

Keywords

Speech recognition; Mel-filterbank (MFB); Melfilterbank energies; Mel-Frequency Cepstral Coefficients (MFCCs).

Abstract

Mel-filterbank energies is a key feature that is widely employed in automatic speech recognition(ASR) system. It arises from a sub-band spectrum typically. But when the noise exists in the background, Mel-filterbank energies can not be easy to estimated accurately. In this paper, the fact that the trajectories of not only "traditional" log Mel-filterbank energies, but also its delta parameters can be influenced by noise will be theoretically analyzed. As a result, log Mel-filterbank energies and their delta parameters can not be calculated correctly. In this paper, we propose to remove those severely contaminated Mel-filterbank features and only keep those variations which perform better in the speech remained. We demonstrate the effectiveness of this novel operation through speech recognition experiments conducted on the Aurora-2 database.

Copyright

© 2017, 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)

TY  - CONF
AU  - Yun-Peng Wu
AU  - Jia-Min Mao
AU  - Wei-Feng Li
PY  - 2016/12
DA  - 2016/12
TI  - Robust speech recognition by selecting mel-filter banks
BT  - Proceedings of the 2nd Annual International Conference on Electronics, Electrical Engineering and Information Science (EEEIS 2016)
PB  - Atlantis Press
SP  - 407
EP  - 416
SN  - 2352-5401
UR  - https://doi.org/10.2991/eeeis-16.2017.52
DO  - 10.2991/eeeis-16.2017.52
ID  - Wu2016/12
ER  -