IMPROVED TONE MODELING BY EXPLOITING ARTICULATORY FEATURES FOR MANDARIN SPEECH RECOGNITION

被引：0
|
作者：
Chao, Hao [1 ]
Yang, Zhanlei [1 ]
Liu, Wenju [1 ]
机构：
[1] Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
来源：
2012 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP) | 2012年
关键词：
tone modeling; Mandarin; speech recognition;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
For the same tone pattern, different articulatory characteristics may make the pitch contour change. This paper applies articulatory features, which represent the articulatory information, as well as prosodic features to the tone modeling. Three kinds of tone models are trained to verify the effectiveness of articulatory features. Tone recognition experiments indicate significant improvement can be achieved when using both articulatory features and prosodic features. After the first pass search of a speech recognition system, tone models using new tonal features are employed to rescoring the N-best hypotheses, and a 6.5% relative reduction of character error rate is achieved.
引用
收藏
页码：4741 / 4744
页数：4
相关论文
共 50 条
  • [21] Improved tone recognition for fluent mandarin speech based on new inter-syllabic features and robust pitch extraction
    Lin, WY
    Lee, LS
    ASRU'03: 2003 IEEE WORKSHOP ON AUTOMATIC SPEECH RECOGNITION AND UNDERSTANDING ASRU '03, 2003, : 237 - 242
  • [22] Incorporating Tone Features to Convolutional Neural Network to Improve Mandarin/Thai Speech Recognition
    Hu, Xinhui
    Saiko, Masahiro
    Hori, Chiori
    2014 ASIA-PACIFIC SIGNAL AND INFORMATION PROCESSING ASSOCIATION ANNUAL SUMMIT AND CONFERENCE (APSIPA), 2014,
  • [23] Speech recognition using cepstral articulatory features
    Najnin, Shamima
    Banerjee, Bonny
    SPEECH COMMUNICATION, 2019, 107 : 26 - 37
  • [24] Applying articulatory features to speech emotion recognition
    Zhou, Yu
    Sun, Yanqing
    Yang, Lin
    Yan, Yonghong
    2009 INTERNATIONAL CONFERENCE ON RESEARCH CHALLENGES IN COMPUTER SCIENCE, ICRCCS 2009, 2009, : 73 - 76
  • [25] A quantitative assessment of the importance of tone in mandarin speech recognition
    Ng, T
    Siu, MH
    Ostendorf, M
    IEEE SIGNAL PROCESSING LETTERS, 2005, 12 (12) : 867 - 870
  • [26] Robust Speech Recognition Combining Cepstral and Articulatory Features
    Zha, Zhuan-ling
    Hu, Jin
    Zhan, Qing-ran
    Shan, Ya-hui
    Xie, Xiang
    Wang, Jing
    Cheng, Hao-bo
    PROCEEDINGS OF 2017 3RD IEEE INTERNATIONAL CONFERENCE ON COMPUTER AND COMMUNICATIONS (ICCC), 2017, : 1401 - 1405
  • [27] Tone variation modeling for fluent mandarin tone recognition based on clustering
    Lin, WY
    2004 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOL I, PROCEEDINGS: SPEECH PROCESSING, 2004, : 933 - 936
  • [28] Whispery speech recognition using adapted articulatory features
    Jou, SC
    Schultz, T
    Waibel, A
    2005 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1-5: SPEECH PROCESSING, 2005, : 1009 - 1012
  • [29] Speech and tone recognition for a Mandarin e-learning system
    Su, Wei
    Miao, Zhenjiang
    TENCON 2006 - 2006 IEEE REGION 10 CONFERENCE, VOLS 1-4, 2006, : 1248 - +
  • [30] Tone Recognition of Mandarin Speech using BP Neural Network
    Xie, Zhaoqiang
    Miao, Zhenjiang
    Geng, Jie
    PROCEEDINGS OF 2010 INTERNATIONAL SYMPOSIUM ON IMAGE ANALYSIS AND SIGNAL PROCESSING, 2010, : 199 - 203
12345