Integration of context-dependent durational knowledge into HMM-based speech recognition

被引：0
|
作者：
Wang, X
tenBosch, LFM
Pols, LCW
机构：
来源：
ICSLP 96 - FOURTH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, VOLS 1-4 | 1996年
关键词：
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
This paper presents research on integrating context-dependent durational knowledge into HMM-based speech recognition. The first part of the paper presents work on obtaining relations between the parameters of the context-free HMMs and their durational behaviour, in preparation for the context-dependent durational modelling presented in the second part. Duration integration is realised via rescoring in the post-processing step of our N-best monophone recogniser. We use the multi-speaker TIMIT database for our analyses.
引用
收藏
页码：1073 / 1076
页数：4
相关论文
共 50 条
  • [1] Context-Dependent Labels for an HMM-Based Speech Synthesis System for Malay
    Mustafa, Mumtaz B.
    Don, Zuraidah M.
    Knowles, Gerry
    2013 INTERNATIONAL CONFERENCE ORIENTAL COCOSDA HELD JOINTLY WITH 2013 CONFERENCE ON ASIAN SPOKEN LANGUAGE RESEARCH AND EVALUATION (O-COCOSDA/CASLRE), 2013,
  • [2] On the use of context-dependent modeling units for HMM-based offline handwriting recognition
    Fink, Gernot A.
    Ploetz, Thomas
    ICDAR 2007: NINTH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION, VOLS I AND II, PROCEEDINGS, 2007, : 729 - 733
  • [3] Context-dependent substroke model for HMM-based on-line handwriting recognition
    Tokuno, J
    Inami, N
    Matsuda, S
    Nakai, M
    Shimodaira, H
    Sagayama, S
    EIGHTH INTERNATIONAL WORKSHOP ON FRONTIERS IN HANDWRITING RECOGNITION: PROCEEDINGS, 2002, : 78 - 83
  • [4] Context-dependent substroke model for HMM-based on-line handwriting recognition
    Graduate School of Information Science, Japan Advanced Institute of Science and Technology, Japan
    不详
    Proc. Int. Workshop Front. Handwriting Recogn. IWFHR, (78-83):
  • [5] Context-dependent additive log F0 model for HMM-based speech synthesis
    Zen, Heiga
    Braunschweiler, Norbert
    INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 2039 - 2042
  • [6] Pitch dependent phone modelling for HMM-based speech recognition
    Singer, H.
    Sagayama, S.
    Journal of the Acoustical Society of Japan (E) (English translation of Nippon Onkyo Gakkaishi), 1994, 15 (02):
  • [7] An HMM-based speech recognition IC
    Han, W
    Hon, KW
    Chan, CF
    Lee, T
    Choy, CS
    Pun, KP
    Ching, PC
    PROCEEDINGS OF THE 2003 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, VOL II: COMMUNICATIONS-MULTIMEDIA SYSTEMS & APPLICATIONS, 2003, : 744 - 747
  • [8] Error-driven HMM-based chunk tagger with context-dependent lexicon
    Zhou, GD
    Su, R
    PROCEEDINGS OF THE 2000 JOINT SIGDAT CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND VERY LARGE CORPORA, 2000, : 71 - 79
  • [9] Peripheral features for HMM-based speech recognition
    Fukuda, T
    Takigawa, M
    Nitta, T
    2001 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS I-VI, PROCEEDINGS: VOL I: SPEECH PROCESSING 1; VOL II: SPEECH PROCESSING 2 IND TECHNOL TRACK DESIGN & IMPLEMENTATION OF SIGNAL PROCESSING SYSTEMS NEURALNETWORKS FOR SIGNAL PROCESSING; VOL III: IMAGE & MULTIDIMENSIONAL SIGNAL PROCESSING MULTIMEDIA SIGNAL PROCESSING - VOL IV: SIGNAL PROCESSING FOR COMMUNICATIONS; VOL V: SIGNAL PROCESSING EDUCATION SENSOR ARRAY & MULTICHANNEL SIGNAL PROCESSING AUDIO & ELECTROACOUSTICS; VOL VI: SIGNAL PROCESSING THEORY & METHODS STUDENT FORUM, 2001, : 129 - 132
  • [10] Context-dependent classes in a hybrid recurrent network-HMM speech recognition system
    Kershaw, D
    Robinson, T
    Hochberg, M
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 8: PROCEEDINGS OF THE 1995 CONFERENCE, 1996, 8 : 750 - 756
12345