Stressed speech recognition method based on difference subspace combined with dynamic time warping

被引:0
作者
Lv, Chengguo [1 ,2 ]
Zhang, Rubo [2 ]
Li, Peihua [1 ]
机构
[1] Heilongjiang Univ, Coll Comp Sci & Technol, 74 Xuefu Rd, Harbin 150080, Peoples R China
[2] Harbin Engn Univ, Coll Comp Sci & Technol, Harbin, Peoples R China
来源
INDUSTRIAL INSTRUMENTATION AND CONTROL SYSTEMS, PTS 1-4 | 2013年 / 241-244卷
关键词
speech recognition; speech under G-force; difference subspace; dynamic time warping;
D O I
10.4028/www.scientific.net/AMM.241-244.1640
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Speech under G-force which produced when speaker was under different acceleration of gravity was analyzed and researched, considered as principal part and stressed part to. research. An isolated word recognition approach was proposed which combined difference subspace means with dynamic time warping technique. The method recognized speech under G-force by constructing a difference subspace to remove the stressed part. Dynamic time warping technique was adopted to make all feature vectors of one word in the training set have equal length, and a corresponding decision criterion was suggested. For a small vocabulary including 15 words, the method obtained the average recognition rate of 98.3%, which almost equal to the rate in normal environment. The method not only worked well in normal conditions but also had good performance for speech under G-force.
引用
收藏
页码:1640 / +
页数:2
相关论文
共 16 条
[1]   A comparative study of traditional and newly proposed features for recognition of speech under stress [J].
Bou-Ghazale, SE ;
Hansen, JHL .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2000, 8 (04) :429-442
[2]  
Chen Jingdong, 1998, Acta Acustica, V23, P537
[3]   CEPSTRAL DOMAIN TALKER STRESS COMPENSATION FOR ROBUST SPEECH RECOGNITION [J].
CHEN, YN .
IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND SIGNAL PROCESSING, 1988, 36 (04) :433-439
[4]   A novel approach to isolated word recognition [J].
Gülmezoglu, MB ;
Dzhafarov, V ;
Keskin, M ;
Barkana, A .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1999, 7 (06) :620-628
[5]   The common vector approach and its relation to principal component analysis [J].
Gülmezoglu, MB ;
Dzhafarov, V ;
Barkana, A .
IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 2001, 9 (06) :655-662
[6]  
HANSEN JHL, 1997, EUROSPEECH 97, V4, P1743
[7]  
Ma Yonglin, 2002, Acta Acustica, V27, P518
[8]   Speech under stress conditions: Overview of the effect on speech production and on system performance [J].
Steeneken, HJM ;
Hansen, JHL .
ICASSP '99: 1999 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS VOLS I-VI, 1999, :2079-2082
[9]  
Tian Bin, 2003, Acta Acustica, V28, P28
[10]  
[王玉伟 Wang Yuwei], 2002, [信号处理, Signal Processing], V18, P484