HMM Compensation Based on Non-uniform Spectral Compression for Noisy Speech Recognition

被引：0
|
作者：
Ning, Geng-xin [1 ]
Zhang, Jun [1 ]
Yu, Hua [1 ]
机构：
[1] S China Univ Technol, Sch Elect & Informat Engn, Guangzhou 510640, Peoples R China
来源：
2008 11TH IEEE SINGAPORE INTERNATIONAL CONFERENCE ON COMMUNICATION SYSTEMS (ICCS), VOLS 1-3 | 2008年
关键词：
Model-based compensation; non-uniform spectral compression; noisy speech recognition;
D O I：
10.1109/ICCS.2008.4737168
中图分类号：
TP3 [计算技术、计算机技术];
学科分类号：
0812 ;
摘要：
A robust speech feature extraction method based on the power law of hearing and non-uniform spectral compression technique is proposed, and the correspondent model compensation algorithm is given. The mismatch functions, reflecting the infections of additive noise and spectral compression, and the model compensation formulae are deduced. The experiment results show that the significant improvement is obtained over the popular VTS (Vector Taylor Series) by adopting those approaches. It's concluded that the proposed method can deal with the speech recognition tasks in different additive noisy environments.
引用
收藏
页码：184 / 187
页数：4
相关论文
共 50 条
  • [31] Incorporating the voicing information into HMM-based automatic speech recognition in noisy environments
    Jancovic, Peter
    Koekueer, Muenevver
    SPEECH COMMUNICATION, 2009, 51 (05) : 438 - 451
  • [32] Automatic generation of non-uniform HMM structures based on variational Bayesian approach
    Jitsuhiro, T
    Nakamura, S
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 805 - 808
  • [33] Dispersion compensation using transmission based non-uniform grating
    Survaiya, SP
    Saxena, S
    OPTICAL ENGINEERING FOR SENSING AND NANOTECHNOLOGY (ICOSN 2001), 2001, 4416 : 170 - 173
  • [34] Compensation of speaker directivity in speech recognition using HMM composition
    Giron, F
    Minami, Y
    Tanaka, M
    Furuya, K
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 253 - 256
  • [35] A dynamic parameter compensation method for noisy speech recognition
    Ning, Geng-xin
    Leung, Shu-hung
    Chu, Kam-keung
    Wei, Gang
    SPEECH COMMUNICATION, 2006, 48 (10) : 1283 - 1293
  • [36] An Investigation of Non-Uniform Error Cost Function Design in Automatic Speech Recognition
    Fu, Qiang
    Juang, Biing-Hwang
    SEVENTH INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND APPLICATIONS, PROCEEDINGS, 2008, : 168 - +
  • [37] Perceptual Speech Enhancement System Based on Non-Uniform Analysis
    Zoghlami, Novlene
    Lachiri, Zied
    INTERNATIONAL CONFERENCE ON SIGNALS AND ELECTRONIC SYSTEMS (ICSES '10): CONFERENCE PROCEEDINGS, 2010, : 73 - 76
  • [38] Speech enhancement method based on feature compensation gain for effective speech recognition in noisy environments
    Bae, Ara
    Kim, Wooil
    JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2019, 38 (01): : 51 - 55
  • [39] Speech recognition based on HMM decomposition and composition method with a microphone array in noisy reverberant environments
    Miki, K
    Nishiura, T
    Nakamura, S
    Shikano, K
    ELECTRONICS AND COMMUNICATIONS IN JAPAN PART II-ELECTRONICS, 2002, 85 (09): : 13 - 22
  • [40] An RNN-based noise estimation and likelihood compensation for noisy speech recognition
    Hong, WT
    Chen, SH
    NEURAL NETWORKS FOR SIGNAL PROCESSING VI, 1996, : 293 - 301
12345