PHMM BASED ASYNCHRONOUS ACOUSTIC MODEL FOR CHINESE LARGE VOCABULARY CONTINUOUS SPEECH RECOGNITION

被引：0
|
作者：
Wu, Hao [1 ]
Wu, Xihong [1 ]
Chi, Huisheng [1 ]
机构：
[1] Peking Univ, Minist Educ, Key Lab Machine Percept, Hearing Res Ctr, Beijing 100871, Peoples R China
来源：
2009 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, VOLS 1- 8, PROCEEDINGS | 2009年
关键词：
tonal language; multiple stream; PHMM;
D O I：
暂无
中图分类号：
O42 [声学];
学科分类号：
070206 ; 082403 ;
摘要：
In this paper, we presented an asynchronous multiple stream based Chinese tonal acoustic modeling framework. In this framework, toneless phonetic units and tones are modeled separately with different acoustic features. During the training, and decoding process, a set of models are coupled together with a product hidden Markov models (PHMM) to represent whole tonal phonetic units. Through this, a compound context dependent tonal model can be generated from a few simple models. Experiments show that such model scheme generates more compact and accurate model presentation and brings improvement on the performance for large vocabulary speech recognition tasks.
引用
收藏
页码：4477 / 4480
页数：4
相关论文
共 50 条
  • [41] Specifics of hidden Markov model modifications for large vocabulary continuous speech recognition
    Silingas, D
    Telksnys, L
    INFORMATICA, 2004, 15 (01) : 93 - 110
  • [42] Context Dependent Syllable Acoustic Model for Continuous Chinese Speech Recognition
    Wu, Hao
    Wu, Xihong
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1961 - 1964
  • [43] Towards speech rate independence in large vocabulary continuous speech recognition
    Martinez, F
    Tapias, D
    Alvarez, J
    PROCEEDINGS OF THE 1998 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING, VOLS 1-6, 1998, : 725 - 728
  • [44] End-to-End Training of Acoustic Models for Large Vocabulary Continuous Speech Recognition with TensorFlow
    Variani, Ehsan
    Bagby, Tom
    McDermott, Erik
    Bacchiani, Michiel
    18TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION (INTERSPEECH 2017), VOLS 1-6: SITUATED INTERACTION, 2017, : 1641 - 1645
  • [45] Automatic determination of acoustic model topology using variational Bayesian estimation and clustering for large vocabulary continuous speech recognition
    Watanabe, S
    Sako, A
    Nakamura, A
    IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING, 2006, 14 (03): : 855 - 872
  • [46] Scalable HMM based Inference Engine in Large Vocabulary Continuous Speech Recognition
    Chong, Jike
    You, Kisun
    Yi, Youngmin
    Gonina, Ekaterina
    Hughes, Christopher
    Sung, Wonyong
    Keutzer, Kurt
    ICME: 2009 IEEE INTERNATIONAL CONFERENCE ON MULTIMEDIA AND EXPO, VOLS 1-3, 2009, : 1793 - +
  • [47] Response Probability Based Decoding Algorithm for Large Vocabulary Continuous Speech Recognition
    Yang, Zhanlei
    Chao, Hao
    Liu, Wenju
    12TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION 2011 (INTERSPEECH 2011), VOLS 1-5, 2011, : 1940 - 1943
  • [48] Extra Large Vocabulary Continuous Speech Recognition Algorithm based on Information Retrieval
    Pylypenko, Valeriy
    INTERSPEECH 2007: 8TH ANNUAL CONFERENCE OF THE INTERNATIONAL SPEECH COMMUNICATION ASSOCIATION, VOLS 1-4, 2007, : 1809 - 1812
  • [49] Parallel Scalability in Speech Recognition Inference engines in large vocabulary continuous speech recognition
    You, Kisun
    Chong, Jike
    Yi, Youngmin
    Gonina, Ekaterina
    Hughes, Christopher J.
    Chen, Yen-Kuang
    Sung, Wonyong
    Keutzer, Kurt
    IEEE SIGNAL PROCESSING MAGAZINE, 2009, 26 (06) : 124 - 135
  • [50] A Fast Approximate Acoustic Match for Large Vocabulary Speech Recognition
    Bahl, Lalit R.
    De Gennaro, Steven V.
    Gopalakrishnan, P. S.
    Mercer, Robert L.
    IEEE TRANSACTIONS ON SPEECH AND AUDIO PROCESSING, 1993, 1 (01): : 59 - 67
12345