• DocumentCode
    3407145
  • Title

    Uyghur morpheme-based language models and ASR

  • Author

    Ablimit, Mijit ; Neubig, Graham ; Mimura, Masato ; Mori, Shinsuke ; Kawahara, Tatsuya ; Hamdulla, Askar

  • Author_Institution
    Sch. of Inf., Kyoto Univ., Kyoto, Japan
  • fYear
    2010
  • fDate
    24-28 Oct. 2010
  • Firstpage
    581
  • Lastpage
    584
  • Abstract
    Uyghur language is an agglutinative language in which words are formed by suffixes attaching to a stem (or root). Because of the explosive nature in vocabulary of the agglutinative languages, several morpheme-based language models are built and experiments are implemented. Morpheme is the smallest meaning bearing unit. In this research, morpheme is referred to any of prefix, stem, or suffix. As a result, a large vocabulary ASR system is built on the basis of Julius system. Several ASR results on language models based on different units (word, morpheme, and syllable) are compared.
  • Keywords
    natural language processing; vocabulary; ASR; Julius system; Uyghur morpheme-based language model; agglutinative language; meaning bearing unit; vocabulary; Error analysis; Hidden Markov models; Joining processes; Speech recognition; Surface morphology; Training; Vocabulary; Uyghur; language modeling ASR; morpheme segmenter;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Signal Processing (ICSP), 2010 IEEE 10th International Conference on
  • Conference_Location
    Beijing
  • Print_ISBN
    978-1-4244-5897-4
  • Type

    conf

  • DOI
    10.1109/ICOSP.2010.5656065
  • Filename
    5656065