Robust Speaker Recognition Algorithm

DOI

10.2991/ceie-16.2017.19How to use a DOI?

Keywords

Speaker Recognition; Mel-Frequency Cepstral Coefficients; Gaussian Mixture Model

Abstract

The accuracy of speaker recognition algorithm would be decreased greatly due to the noise issues. According to noisy environment, a new robust speaker recognition algorithm is proposed in this paper. After Mel-frequency Cepstral Coefficient (MFCC) feature extraction, the features are calibrated with half rised-sine function. Then the features are processed by feature normalization, feature folding and feature mapping. A method of combining BP neural network(NN) with Gaussian mixture model(GMM) is proposed to improve the recognition accuracy and robustness of the model. The neural network works in the probability space of GMM gathers the interactive information between different speakers. The experiment result proves that the proposed algorithm shows more accuracy and robustness.

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  - Wenchao Hao
AU  - Yi Chen
AU  - Lei Wang
AU  - Chunguang Li
AU  - Yueqin Feng
AU  - Qingyun Wang
PY  - 2016/10
DA  - 2016/10
TI  - Robust Speaker Recognition Algorithm
BT  - Proceedings of the International Conference on Communication and Electronic Information Engineering (CEIE 2016)
PB  - Atlantis Press
SP  - 137
EP  - 143
SN  - 2352-5401
UR  - https://doi.org/10.2991/ceie-16.2017.19
DO  - 10.2991/ceie-16.2017.19
ID  - Hao2016/10
ER  -