Improvements in recognition of conversational telephone speech

被引:6
|
作者
Peskin, B [1 ]
Newman, M [1 ]
McAllaster, D [1 ]
Nagesha, V [1 ]
Richards, H [1 ]
Wegmann, S [1 ]
Hunt, M [1 ]
Gillick, L [1 ]
机构
[1] Dragon Syst Inc, Newton, MA 02460 USA
关键词
D O I
10.1109/ICASSP.1999.758060
中图分类号
O42 [声学];
学科分类号
070206 ; 082403 ;
摘要
This paper describes recent changes in Dragon's speech recognition system which have markedly improved performance on conversational telephone speech. Key changes include: the conversion to modified PLP-based cepstra from mel-cepstra; the replacement of our usual IMELDA transformation by a new transform using "semi-tied covariance"; a new multi-pass adaptation protocol; probabilities on alternate pronunciations in the lexicon; the addition of word-boundary tags in our acoustic models and the redistribution of model parameters to build fewer output distributions but with more mixture components per model.
引用
收藏
页码:53 / 56
页数:4
相关论文
共 50 条
  • [31] Recognition of Interest in Human Conversational Speech
    Schuller, Bjoern
    Koehler, Niels
    Mueller, Ronald
    Rigoll, Gerhard
    [J]. INTERSPEECH 2006 AND 9TH INTERNATIONAL CONFERENCE ON SPOKEN LANGUAGE PROCESSING, VOLS 1-5, 2006, : 793 - 796
  • [32] On the limit of English conversational speech recognition
    Tuske, Zoltan
    Saon, George
    Kingsbury, Brian
    [J]. INTERSPEECH 2021, 2021, : 2062 - 2066
  • [33] Techniques for Rapid and Robust Topic Identification of Conversational Telephone Speech
    Wintrode, Jonathan
    Kulp, Scott
    [J]. INTERSPEECH 2009: 10TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2009, VOLS 1-5, 2009, : 1515 - 1518
  • [34] Conversational quality evaluation of artificial bandwidth extension of telephone speech
    Pulakka, Hannu
    Laaksonen, Laura
    Yrttiaho, Santeri
    Myllyla, Ville
    Alku, Paavo
    [J]. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA, 2012, 132 (02): : 848 - 861
  • [35] Telephone speech recognition applications at IRST
    Falavigna, D
    Gretter, R
    [J]. 1998 IEEE 4TH WORKSHOP INTERACTIVE VOICE TECHNOLOGY FOR TELECOMMUNICATIONS APPLICATIONS - IVTTA '98, 1998, : 27 - 30
  • [36] Robust speech recognition in telephone network
    Han, MS
    Park, GB
    Park, JG
    Han, JQ
    [J]. PROGRESS IN CONNECTIONIST-BASED INFORMATION SYSTEMS, VOLS 1 AND 2, 1998, : 1103 - 1106
  • [37] Densely Connected Networks for Conversational Speech Recognition
    Han, Kyu J.
    Chandrashekaran, Akshay
    Kim, Jungsuk
    Lane, Ian
    [J]. 19TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2018), VOLS 1-6: SPEECH RESEARCH FOR EMERGING MARKETS IN MULTILINGUAL SOCIETIES, 2018, : 796 - 800
  • [38] THE MICROSOFT 2017 CONVERSATIONAL SPEECH RECOGNITION SYSTEM
    Xiong, W.
    Wu, L.
    Alleva, F.
    Droppo, J.
    Huang, X.
    Stolcke, A.
    [J]. 2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 5934 - 5938
  • [39] THE MICROSOFT 2016 CONVERSATIONAL SPEECH RECOGNITION SYSTEM
    Xiong, W.
    Droppo, J.
    Huang, X.
    Seide, F.
    Seltzer, M.
    Stolcke, A.
    Yu, D.
    Zweig, G.
    [J]. 2017 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2017, : 5255 - 5259
  • [40] LINGUISTIC PROCESSOR IN A CONVERSATIONAL SPEECH RECOGNITION SYSTEM
    SHIKANO, K
    KOHDA, M
    [J]. REVIEW OF THE ELECTRICAL COMMUNICATIONS LABORATORIES, 1978, 26 (11-1): : 1505 - 1520