Performance of HMM-based speech recognizers with discriminative state-weights

被引：0
|
作者：
Korea Advanced Inst of Science and, Technology, Taejon, Korea, Republic of [1 ]
机构：
来源：
Speech Commun | / 3卷 / 197-205期
关键词：
D O I：
暂无
中图分类号：
学科分类号：
摘要：
Speech recognition
引用
收藏
相关论文
共 50 条
  • [41] Modified Viterbi Scoring for HMM-Based Speech Recognition
    Jo, Jihyuck
    Kim, Han-Gyu
    Park, In-Cheol
    Jung, Bang Chul
    Yoo, Hoyoung
    INTELLIGENT AUTOMATION AND SOFT COMPUTING, 2019, 25 (02): : 351 - 358
  • [42] Analysis and HMM-based synthesis of hypo and hyperarticulated speech
    Picart, Benjamin
    Drugman, Thomas
    Dutoit, Thierry
    COMPUTER SPEECH AND LANGUAGE, 2014, 28 (02): : 687 - 707
  • [43] Optimal Number of States in HMM-Based Speech Synthesis
    Hanzlicek, Zdenek
    TEXT, SPEECH, AND DIALOGUE, TSD 2017, 2017, 10415 : 353 - 361
  • [44] Normalized training for HMM-based visual speech recognition
    Nankaku, Yoshihiko
    Tokuda, Keiichi
    Kitamura, Tadashi
    Kobayashi, Takao
    ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 2006, 89 (11): : 40 - 50
  • [45] HMM-Based Cue Parameters Estimation for Speech Enhancement
    Deng, Feng
    Bao, Chang-chun
    Jia, Mao-shen
    2016 10TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING (ISCSLP), 2016,
  • [46] Simplified scoring methods for HMM-based speech recognition
    Paramonov, Pavel
    Sutula, Nadezhda
    SOFT COMPUTING, 2016, 20 (09) : 3455 - 3460
  • [47] A trainable excitation model for HMM-based speech synthesis
    Maia, R.
    Toda, T.
    Zen, H.
    Nankaku, Y.
    Tokuda, K.
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1125 - +
  • [48] Normalized training for HMM-based visual speech recognition
    Nankaku, Y
    Tokuda, K
    Kitamura, T
    Kobayashi, T
    2000 INTERNATIONAL CONFERENCE ON IMAGE PROCESSING, VOL III, PROCEEDINGS, 2000, : 234 - 237
  • [49] Speaker interpolation for HMM-based speech synthesis system
    Yoshimura, Takayoshi, 2000, Acoustical Soc Jpn, Tokyo, Japan (21):
  • [50] Contextual Additive Structure for HMM-Based Speech Synthesis
    Takaki, Shinji
    Nankaku, Yoshihiko
    Tokuda, Keiichi
    IEEE JOURNAL OF SELECTED TOPICS IN SIGNAL PROCESSING, 2014, 8 (02) : 229 - 238
12345