• DocumentCode
    2066538
  • Title

    Tone Evaluation of Chinese Continuous Speech Based on Prosodic Words

  • Author

    Pan, Yi-Qian ; Wei, Si ; Wang, Ren-Hua

  • Author_Institution
    Man Machine Voice Commun. Lab., Univ. of Sci. & Technol. of China, Hefei, China
  • fYear
    2008
  • fDate
    16-19 Dec. 2008
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    Tonal evaluation of Chinese continuous speech plays an important role in Mandarin Chinese pronunciation test. In this paper, we introduce the Multi- Space Distribution Hidden Markov Model based on prosodic word. The results show that the performance of tonal syllable error rate can be reduced. For the non-standard Chinese Mandarin speech, the correlation between computer score and expert score was improved above 3.0% absolutely, compared with the baseline system without tonal pronunciation test.
  • Keywords
    hidden Markov models; natural language processing; speech processing; Chinese continuous speech; Mandarin Chinese pronunciation test; multi-space distribution hidden Markov model; prosodic words; tonal syllable error rate; tone evaluation; Context modeling; Databases; Error analysis; Face recognition; Frequency; Man machine systems; Natural languages; Speech analysis; Speech recognition; System testing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Chinese Spoken Language Processing, 2008. ISCSLP '08. 6th International Symposium on
  • Conference_Location
    Kunming
  • Print_ISBN
    978-1-4244-2942-4
  • Electronic_ISBN
    978-1-4244-2943-1
  • Type

    conf

  • DOI
    10.1109/CHINSL.2008.ECP.77
  • Filename
    4730331
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=2066538