A Speech Enhance Method of Spectral Subtraction Based on Objective Evaluation

DOI

10.2991/ammee-17.2017.109How to use a DOI?

Keywords

Objective Evaluation, Spectrum Subtraction, Speech Coding, Acoustic Communication.

Abstract

Speech coding is a technique that transforms speech signal of big data to digital signal of small data. This characteristic is suitable for the underwater acoustic transmission of narrowband communication. It's one of the support to underwater acoustic high speed voice communication on the source code level. This paper expounds MELP, and applies PESQ, an objective speech quality assessment, to evaluate and mark the quality of speech coding. According to the evaluation score to judge the quality of speech communication. It is suppressed that the stabile noise components in decode speech by using spectrum subtraction method. Experimental results show that it can improve the PESQ evaluation score and obtain better auditory perception.

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  - Zitong Yu
AU  - Longxiang Guo
AU  - Huifeng Li
PY  - 2017/06
DA  - 2017/06
TI  - A Speech Enhance Method of Spectral Subtraction Based on Objective Evaluation
BT  - Proceedings of the Advances in Materials, Machinery, Electrical Engineering (AMMEE 2017)
PB  - Atlantis Press
SP  - 555
EP  - 558
SN  - 2352-5401
UR  - https://doi.org/10.2991/ammee-17.2017.109
DO  - 10.2991/ammee-17.2017.109
ID  - Yu2017/06
ER  -