A GMM-based telephone channel classification for Mandarin speech recognition

被引：0
|
作者：
Xu, W [1 ]
Peng, X [1 ]
Wang, BX [1 ]
机构：
[1] Informat & Engn Univ, Zhengzhou 450002, Peoples R China
来源：
2004 7TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, VOLS 1-3 | 2004年
关键词：
speech recognition; GMM discriminability; telephone channel classification;
D O I：
暂无
中图分类号：
TP18 [人工智能理论];
学科分类号：
081104 ; 0812 ; 0835 ; 1405 ;
摘要：
The discriminability of different channel modeled by GMM is qualitatively analyzed in this paper. A GMM-based channel classification and speech recognition system in multi-channel environment is proposed. The channel classifier is used to select a most likely HMM from pre-trained RMMs of each specific telephone channel environment. The selected HMM is used as the reference HMM to recognize each utterance. The experimental results show that the proposed system is an efficient framework to enhance the robustness of speech recognition across different channel environment.
引用
收藏
页码：642 / 645
页数：4
相关论文
共 50 条
  • [21] An RNN-based channel classification for mandarin speech recognition over GSM/PSTN transmission environments
    Hong, WT
    [J]. 2002 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-IV, PROCEEDINGS, 2002, : 1033 - 1036
  • [22] GMM-based speaker age and gender classification in Czech and Slovak
    Pribil, Jiri
    Pribilova, Anna
    Matousek, Jindrich
    [J]. JOURNAL OF ELECTRICAL ENGINEERING-ELEKTROTECHNICKY CASOPIS, 2017, 68 (01): : 3 - 12
  • [23] GMM-based target classification for ground surveillance Doppler radar
    Bilik, I
    Tabrikian, J
    Cohen, A
    [J]. IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS, 2006, 42 (01) : 267 - 278
  • [24] GMM-BASED ITERATIVE ENTROPY CODING FOR SPECTRAL ENVELOPES OF SPEECH AND AUDIO
    Korse, Srikanth
    Fuchs, Guillaume
    Backstrom, Tom
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5689 - 5693
  • [25] GMM-BASED SIGNIFICANCE DECODING
    Abdelaziz, Ahmed Hussen
    Zeiler, Steffen
    Kolossa, Dorothea
    Leutnant, Volker
    Haeb-Umbach, Reinhold
    [J]. 2013 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2013, : 6827 - 6831
  • [26] Evaluation of Synthetic Speech by GMM-Based Continuous Detection of Emotional States
    Pribil, Jiri
    Pribilova, Anna
    Matousek, Jindrich
    [J]. TEXT, SPEECH, AND DIALOGUE (TSD 2019), 2019, 11697 : 264 - 273
  • [27] GMM-based Bhattacharyya kernel Fisher Discriminant Analysis for speaker recognition
    Chao, YH
    Wang, HM
    Chang, RC
    [J]. 2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 649 - 652
  • [28] Estimation of channel bias for telephone speech recognition
    Chien, JT
    Wang, HC
    Lee, LM
    [J]. ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4, 1996, : 1840 - 1843
  • [29] A GMM-Based Target Classification Scheme for a Node in Wireless Sensor Networks
    Kim, Youngsoo
    Jeong, Sangbae
    Kim, Daeyoung
    [J]. IEICE TRANSACTIONS ON COMMUNICATIONS, 2008, E91B (11) : 3544 - 3551
  • [30] 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
12345