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

被引：0
|
作者：
Shen, Haifeng [1 ]
Liu, Gang [1 ]
Guo, Jun [1 ]
机构：
[1] Beijing Univ Posts & Telecommun, Beijing 100876, Peoples R China
来源：
ARTIFICIAL INTELLIGENCE REVIEW | 2009年 / 32卷 / 1-4期
关键词：
Robust speech recognition; Mixed environment compensation; MAP; EM;
D O I：
10.1007/s10462-009-9130-9
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
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：11
相关论文
共 50 条
  • [1] Mixed environment compensation based on maximum a posteriori estimation for robust speech recognition
    Haifeng Shen
    Gang Liu
    Jun Guo
    [J]. Artificial Intelligence Review, 2009, 32 : 1 - 11
  • [2] Environment compensation based on maximum a posteriori estimation for improved speech recognition
    Shen, HF
    Guo, J
    Liu, G
    Huang, PM
    Li, QX
    [J]. MICAI 2005: ADVANCES IN ARTIFICIAL INTELLIGENCE, 2005, 3789 : 854 - 862
  • [3] Feature compensation based on independent noise estimation for robust speech recognition
    Lu, Yong
    Lin, Han
    Wu, Pingping
    Chen, Yitao
    [J]. EURASIP JOURNAL ON AUDIO SPEECH AND MUSIC PROCESSING, 2021, 2021 (01)
  • [4] Feature compensation based on independent noise estimation for robust speech recognition
    Yong Lü
    Han Lin
    Pingping Wu
    Yitao Chen
    [J]. EURASIP Journal on Audio, Speech, and Music Processing, 2021
  • [5] A Variational Approach to Robust Maximum Likelihood Estimation for Speech Recognition
    Omar, Mohamed Kamal
    [J]. INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1049 - 1052
  • [6] Robust telephone speech recognition based on channel compensation
    Han, JQ
    Gao, W
    [J]. PATTERN RECOGNITION, 1999, 32 (06) : 1061 - 1067
  • [7] Eigen-MLLR Environment/Speaker Compensation for Robust Speech Recognition
    Liao, Yuan-Fu
    Fang, Hung-Hsiang
    Hsu, Chi-Hui
    [J]. INTERSPEECH 2008: 9TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2008, VOLS 1-5, 2008, : 1249 - 1252
  • [8] IMPULSE RESPONSE ESTIMATION FOR ROBUST SPEECH RECOGNITION IN A REVERBERANT ENVIRONMENT
    Ravanelli, Mirco
    Sosi, Alessandro
    Svaizer, Piergiorgio
    Omologo, Maurizio
    [J]. 2012 PROCEEDINGS OF THE 20TH EUROPEAN SIGNAL PROCESSING CONFERENCE (EUSIPCO), 2012, : 1668 - 1672
  • [9] Maximum likelihood joint estimation of channel and noise for robust speech recognition
    Zhao, YX
    [J]. 2000 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, PROCEEDINGS, VOLS I-VI, 2000, : 1109 - 1112
  • [10] COMBINING EIGENVOICE SPEAKER MODELING AND VTS-BASED ENVIRONMENT COMPENSATION FOR ROBUST SPEECH RECOGNITION
    Ou, Zhijian
    Deng, Kan
    [J]. 2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2012, : 4673 - 4676
12345