Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition

Xinhui Hu, Hirofumi Yamamoto, Genichiro Kikui, Yoshinori Sagisaka

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    1 Citation (Scopus)

    Abstract

    In this paper, we analyze Chinese personal names to model their statistical phonotactic characteristics for continuous Chinese speech recognition. The analysis showed languagespecific characteristics of Chinese personal names and strongly suggested the advantage of character-unit oriented modeling. A hierarchical language model was composed by reflecting statistical phonotactic characteristics of Chinese personal names as a lower intra-word model, and ordinary inter-word neighboring characteristics as an upper multi-class composite N-gram model. These two layers of models were trained independently using different language corpora. For the modeling of given names, the syllable without tone information was selected as the unit for training the bi-gram. The properties of either one or two characters of a given name were introduced to simplify the length constraint of the modeling process. For Chinese family names, we simply added them directly in the recognition lexicon, since their numbers are very restricted. The results from Chinese speech recognition experiments revealed that the proposed hierarchical language model greatly improved the identification accuracy of the Chinese given names compared with the conventional wordclass N-gram model.

    Original languageEnglish
    Title of host publicationINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
    Pages1874-1877
    Number of pages4
    Volume4
    Publication statusPublished - 2006
    EventINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP - Pittsburgh, PA
    Duration: 2006 Sep 172006 Sep 21

    Other

    OtherINTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP
    CityPittsburgh, PA
    Period06/9/1706/9/21

    Fingerprint

    Continuous speech recognition
    Speech recognition
    Identification (control systems)
    Composite materials

    Keywords

    • Chinese speech recognition
    • Hierarchical language model
    • Personal name identification

    ASJC Scopus subject areas

    • Computer Science(all)

    Cite this

    Hu, X., Yamamoto, H., Kikui, G., & Sagisaka, Y. (2006). Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition. In INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP (Vol. 4, pp. 1874-1877)

    Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition. / Hu, Xinhui; Yamamoto, Hirofumi; Kikui, Genichiro; Sagisaka, Yoshinori.

    INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. Vol. 4 2006. p. 1874-1877.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Hu, X, Yamamoto, H, Kikui, G & Sagisaka, Y 2006, Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition. in INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. vol. 4, pp. 1874-1877, INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP, Pittsburgh, PA, 06/9/17.
    Hu X, Yamamoto H, Kikui G, Sagisaka Y. Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition. In INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. Vol. 4. 2006. p. 1874-1877
    Hu, Xinhui ; Yamamoto, Hirofumi ; Kikui, Genichiro ; Sagisaka, Yoshinori. / Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition. INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP. Vol. 4 2006. pp. 1874-1877
    @inproceedings{6257383bacf04b46baa7f8c2bb647da8,
    title = "Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition",
    abstract = "In this paper, we analyze Chinese personal names to model their statistical phonotactic characteristics for continuous Chinese speech recognition. The analysis showed languagespecific characteristics of Chinese personal names and strongly suggested the advantage of character-unit oriented modeling. A hierarchical language model was composed by reflecting statistical phonotactic characteristics of Chinese personal names as a lower intra-word model, and ordinary inter-word neighboring characteristics as an upper multi-class composite N-gram model. These two layers of models were trained independently using different language corpora. For the modeling of given names, the syllable without tone information was selected as the unit for training the bi-gram. The properties of either one or two characters of a given name were introduced to simplify the length constraint of the modeling process. For Chinese family names, we simply added them directly in the recognition lexicon, since their numbers are very restricted. The results from Chinese speech recognition experiments revealed that the proposed hierarchical language model greatly improved the identification accuracy of the Chinese given names compared with the conventional wordclass N-gram model.",
    keywords = "Chinese speech recognition, Hierarchical language model, Personal name identification",
    author = "Xinhui Hu and Hirofumi Yamamoto and Genichiro Kikui and Yoshinori Sagisaka",
    year = "2006",
    language = "English",
    isbn = "9781604234497",
    volume = "4",
    pages = "1874--1877",
    booktitle = "INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP",

    }

    TY - GEN

    T1 - Language modeling of Chinese personal names based on character units for continuous Chinese speech recognition

    AU - Hu, Xinhui

    AU - Yamamoto, Hirofumi

    AU - Kikui, Genichiro

    AU - Sagisaka, Yoshinori

    PY - 2006

    Y1 - 2006

    N2 - In this paper, we analyze Chinese personal names to model their statistical phonotactic characteristics for continuous Chinese speech recognition. The analysis showed languagespecific characteristics of Chinese personal names and strongly suggested the advantage of character-unit oriented modeling. A hierarchical language model was composed by reflecting statistical phonotactic characteristics of Chinese personal names as a lower intra-word model, and ordinary inter-word neighboring characteristics as an upper multi-class composite N-gram model. These two layers of models were trained independently using different language corpora. For the modeling of given names, the syllable without tone information was selected as the unit for training the bi-gram. The properties of either one or two characters of a given name were introduced to simplify the length constraint of the modeling process. For Chinese family names, we simply added them directly in the recognition lexicon, since their numbers are very restricted. The results from Chinese speech recognition experiments revealed that the proposed hierarchical language model greatly improved the identification accuracy of the Chinese given names compared with the conventional wordclass N-gram model.

    AB - In this paper, we analyze Chinese personal names to model their statistical phonotactic characteristics for continuous Chinese speech recognition. The analysis showed languagespecific characteristics of Chinese personal names and strongly suggested the advantage of character-unit oriented modeling. A hierarchical language model was composed by reflecting statistical phonotactic characteristics of Chinese personal names as a lower intra-word model, and ordinary inter-word neighboring characteristics as an upper multi-class composite N-gram model. These two layers of models were trained independently using different language corpora. For the modeling of given names, the syllable without tone information was selected as the unit for training the bi-gram. The properties of either one or two characters of a given name were introduced to simplify the length constraint of the modeling process. For Chinese family names, we simply added them directly in the recognition lexicon, since their numbers are very restricted. The results from Chinese speech recognition experiments revealed that the proposed hierarchical language model greatly improved the identification accuracy of the Chinese given names compared with the conventional wordclass N-gram model.

    KW - Chinese speech recognition

    KW - Hierarchical language model

    KW - Personal name identification

    UR - http://www.scopus.com/inward/record.url?scp=44949156540&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=44949156540&partnerID=8YFLogxK

    M3 - Conference contribution

    SN - 9781604234497

    VL - 4

    SP - 1874

    EP - 1877

    BT - INTERSPEECH 2006 and 9th International Conference on Spoken Language Processing, INTERSPEECH 2006 - ICSLP

    ER -