The Effects of Phoneme Errors in Speaker Adaptation for HMM Speech Synthesis

被引：0
|
作者：
Toth, Balint [1 ]
Fegyo, Tibor [1 ]
Nemeth, Geza [1 ]
机构：
[1] Budapest Univ Technol & Econ, Dept Telecommun & Media Informat, Budapest, Hungary
来源：
12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5 | 2011年
关键词：
speech synthesis; Hidden Markov Model (HMM); Automatic Speech Recognition (ASR); transcription; unsupervised speaker adaptation;
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：
In this paper the phoneme errors in adaptation data of HMM based synthesis is investigated. Phoneme errors are likely to appear in automatic speech recognition (ASR) based transcriptions. The research also investigates the perspective of merely ASR transcription based unsupervised adaptation. To achieve better quality a new method is introduced for selecting an optimal subset of ASR transcription based adaptation data. Quality evaluation of the method was also performed. The results showed that adaptation was successful even on higher than 50% phoneme error rates.
引用
收藏
页码：2816 / +
页数：2
相关论文
共 50 条
  • [1] Frequency Warping for Speaker Adaptation in HMM-based Speech Synthesis
    Gao, Weixun
    Cao, Qiying
    [J]. JOURNAL OF INFORMATION SCIENCE AND ENGINEERING, 2014, 30 (04) : 1149 - 1166
  • [2] PHONEME DEPENDENT SPEAKER EMBEDDING AND MODEL FACTORIZATION FOR MULTI-SPEAKER SPEECH SYNTHESIS AND ADAPTATION
    Fu, Ruibo
    Tao, Jianhua
    Wen, Zhengqi
    Zheng, Yibin
    [J]. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2019, : 6930 - 6934
  • [3] Nearest Neighbor Approach in Speaker Adaptation for HMM-based Speech Synthesis
    Mohammadi, Amir
    Demiroglu, Cenk
    [J]. 2013 21ST SIGNAL PROCESSING AND COMMUNICATIONS APPLICATIONS CONFERENCE (SIU), 2013,
  • [4] CROSS-LINGUAL SPEAKER ADAPTATION FOR HMM-BASED SPEECH SYNTHESIS
    Wu, Yi-Jian
    King, Simon
    Tokuda, Keiichi
    [J]. 2008 6TH INTERNATIONAL SYMPOSIUM ON CHINESE SPOKEN LANGUAGE PROCESSING, PROCEEDINGS, 2008, : 9 - 12
  • [5] Some Aspects of ASR Transcription Based Unsupervised Speaker Adaptation for HMM Speech Synthesis
    Toth, Balint
    Fegyo, Tibor
    Nemeth, Geza
    [J]. TEXT, SPEECH AND DIALOGUE, 2010, 6231 : 408 - 415
  • [6] UNSUPERVISED CROSS-LINGUAL SPEAKER ADAPTATION FOR HMM-BASED SPEECH SYNTHESIS
    Oura, Keiichiro
    Tokuda, Keiichi
    Yamagishi, Junichi
    King, Simon
    Wester, Mirjam
    [J]. 2010 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2010, : 4594 - 4597
  • [7] Analysis of Speaker Adaptation Algorithms for HMM-Based Speech Synthesis and a Constrained SMAPLR Adaptation Algorithm
    Yamagishi, Junichi
    Kobayashi, Takao
    Nakano, Yuji
    Ogata, Katsumi
    Isogai, Juri
    [J]. IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2009, 17 (01): : 66 - 83
  • [8] Speaker Adaptation using Nonlinear Regression Techniques for HMM-based Speech Synthesis
    Hong, Doo Hwa
    Kang, Shin Jae
    Lee, Joun Yeop
    Kim, Nam Soo
    [J]. 2014 TENTH INTERNATIONAL CONFERENCE ON INTELLIGENT INFORMATION HIDING AND MULTIMEDIA SIGNAL PROCESSING (IIH-MSP 2014), 2014, : 586 - 589
  • [9] SPEAKER SIMILARITY EVALUATION OF FOREIGN-ACCENTED SPEECH SYNTHESIS USING HMM-BASED SPEAKER ADAPTATION
    Wester, Mirjam
    Karhila, Reima
    [J]. 2011 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2011, : 5372 - 5375
  • [10] HMM Adaptation for child speech synthesis
    Govender, Avashna
    de Wet, Febe
    Tapamo, Jules-Raymond
    [J]. 16TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2015), VOLS 1-5, 2015, : 1640 - 1644
12345