Improving Noise Robustness of Speech Emotion Recognition System

被引：12

作者：

Juszkiewicz, Lukasz ^{[1
]}

机构：

[1] Wroclaw Univ Technol, Inst Comp Engn Control & Robot, PL-50370 Wroclaw, Poland

来源：

INTELLIGENT DISTRIBUTED COMPUTING VII | 2014年 / 511卷

关键词：

D O I：

10.1007/978-3-319-01571-2_27

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In this paper method of improving noise robustness of speech emotion recognition system is proposed. Such a system has been developed for use in a social robot, but its performance is highly degraded by environmental noise. To alleviate this problem, the histogram equalisation is proposed to reduce the difference between feature vectors in clean and noisy conditions. In training phase of the system the averaged histograms of pitch and MFCC are computed and then serve as reference for equalisation. System performance was evaluated using Database of Polish Emotional Speech, which was split into training and test sets. Test sets were noised with 3 different noise samples. Presented preliminary results show a significant improvement of recognition accuracy in noisy environment conditions.

引用

页码：223 / 232

页数：10

共 22 条

[1] Alam MJ, 2011, LECT NOTES ARTIF INT, V7015, P246, DOI 10.1007/978-3-642-25020-0_32
[2] Casale S., 2008, 2008 Second IEEE International Conference on Semantic Computing (ICSC), P158, DOI 10.1109/ICSC.2008.43
[3] Dautenhahn K., 2002, SOCIALLY INTELLIGENT
[4] Garcia L., 2008, HISTOGRAM EQUALIZATI
[5] Georgogiannis A, 2012, EUR SIGNAL PR CONF, P2045
[6] Hall M., 2009, SIGKDD Explorations, V11, P10, DOI DOI 10.1145/1656274.1656278
[7] Quantile based histogram equalization for noise robust large vocabulary speech recognition
Hilger, F
Ney, H
[J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (03): : 845 - 854
[8] Juszkiewicz Lukasz, 2012, POSTEPY ROBOTYKI, P695
[9] Lodz University of Technology Medical Electronics Division, DATABASE OF POLISH E
[10] Mao X, 2007, ELE COM ENG, P369

← 1 2 3 →