• DocumentCode
    430203
  • Title

    Tone recognition for Chinese speech: a comparative study of Mandarin and Cantonese

  • Author

    Peng, Gang ; Hongying Zheng ; Wang, William S Z

  • Author_Institution
    Dept. of Electron. Eng., Chinese Univ. of Hong Kong, Shatin, China
  • fYear
    2004
  • fDate
    15-18 Dec. 2004
  • Firstpage
    233
  • Lastpage
    236
  • Abstract
    The paper presents a comparative study on automatic continuous tone recognition for Mandarin and Cantonese. Compared with Mandarin, Cantonese has a much more complex tone system. The effects of F0 normalization on the tone recognition of Mandarin and Cantonese are studied. Furthermore, the two tone systems are compared from an engineering point of view. Tone recognition accuracies of 71.50% and 83.06% have been obtained for Cantonese and Mandarin respectively. These results compare favorably with results reported for other tone recognition experiments on the same (for Cantonese) and similar (for Mandarin) databases.
  • Keywords
    linguistics; natural languages; speech processing; speech recognition; Cantonese; Chinese speech recognition; Mandarin; automatic continuous tone recognition; normalization; Automatic speech recognition; Hidden Markov models; Natural languages; Neural networks; Spatial databases; Speech recognition; Testing; Training data;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Chinese Spoken Language Processing, 2004 International Symposium on
  • Print_ISBN
    0-7803-8678-7
  • Type

    conf

  • DOI
    10.1109/CHINSL.2004.1409629
  • Filename
    1409629