Mixed environment compensation based on maximum a posteriori estimation for robust speech recognition

被引：0
|
作者：
Haifeng Shen
Gang Liu
Jun Guo
机构：
[1] Beijing University of Posts and Telecommunications,
来源：
Artificial Intelligence Review | 2009年 / 32卷
关键词：
Robust speech recognition; Mixed environment compensation; MAP; EM;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Noise robustness is a fundamental problem for speech recognition system in the real environments. The paper presents mixed environment compensation technique in which feature compensation algorithm and acoustic model compensation algorithm is combined together. The target is to obtain the fine compensated static acoustic model and the dynamic compensated speech. Therefore, the modified speech sequence can well match the modified acoustic model. The experimental results show that significant performance improvement has been observed.
引用
收藏
页码：1 / 11
页数：10
相关论文
共 50 条
  • [21] A Noise Robust Speech Recognition Method Using Model Compensation Based on Speech Enhancement
    Shen, Guanghu
    Jung, Ho-Youl
    Chung, Hyun-Yeol
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, 2008, 27 (04): : 191 - 199
  • [22] Target Speech GMM-based Spectral Compensation for Noise Robust Speech Recognition
    Shinozaki, Takahiro
    Furui, Sadaoki
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1223 - 1226
  • [23] Channel compensation for robust telephone speech recognition
    Han, JQ
    Han, MS
    Gao, W
    [J]. IEEE TENCON'97 - IEEE REGIONAL 10 ANNUAL CONFERENCE, PROCEEDINGS, VOLS 1 AND 2: SPEECH AND IMAGE TECHNOLOGIES FOR COMPUTING AND TELECOMMUNICATIONS, 1997, : 169 - 172
  • [24] Predictive model-based compensation schemes for robust speech recognition
    Gales, MJF
    [J]. SPEECH COMMUNICATION, 1998, 25 (1-3) : 49 - 74
  • [25] Harmonicity based dereverberation with maximum a posteriori estimation
    Nakatani, T
    Juang, BH
    Kinoshita, K
    Miyoshi, M
    [J]. 2005 WORKSHOP ON APPLICATIONS OF SIGNAL PROCESSING TO AUDIO AND ACOUSTICS (WASPAA), 2005, : 94 - 97
  • [26] Maximum a Posteriori Speech Enhancement Based on Double Spectrum
    Mowlaee, Pejman
    Scheran, Daniel
    Stahl, Johannes
    Wood, Sean U. N.
    Kleijn, W. Bastiaan
    [J]. INTERSPEECH 2019, 2019, : 2738 - 2742
  • [27] SPEECH ENHANCEMENT FOR ROBUST SPEECH RECOGNITION IN MOTORCYCLE ENVIRONMENT
    Mporas, Iosif
    Ganchev, Todor
    Kocsis, Otilia
    Fakotakis, Nikos
    [J]. INTERNATIONAL JOURNAL ON ARTIFICIAL INTELLIGENCE TOOLS, 2010, 19 (02) : 159 - 173
  • [28] Maximum entropy confidence estimation for speech recognition
    White, Christopher
    Droppo, Jasha
    Acero, Alex
    Odell, Julian
    [J]. 2007 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL IV, PTS 1-3, 2007, : 809 - +
  • [29] Matrix quantization error compensation for robust speech recognition based on neural networks
    Asghar, S
    Cong, L
    [J]. INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED PROCESSING TECHNIQUES AND APPLICATIONS, VOL VI, PROCEEDINGS, 1999, : 2850 - 2855
  • [30] On-line feature and acoustic model space compensation for robust speech recognition in car environment
    Miguel, Antonio
    Buera, Luis
    Lleida, Eduardo
    Ortega, Alfonso
    Saz, Oscar
    [J]. 2007 IEEE INTELLIGENT VEHICLES SYMPOSIUM, VOLS 1-3, 2007, : 518 - 523
12345