• DocumentCode
    2570729
  • Title

    A speech processing strategy of cochlear implants based on tonal information of Chinese language

  • Author

    Nie, Kaibao ; Lan, Ning ; Gao, Shangkai

  • Author_Institution
    Dept. of Electr. Eng., Tsinghua Univ., Beijing, China
  • Volume
    6
  • fYear
    1998
  • fDate
    29 Oct-1 Nov 1998
  • Firstpage
    3154
  • Abstract
    Chinese language is significantly different from other languages such as English. It is known as a tonal language with explicit variation of pitch in the pronunciation of words. The objective of this paper is to develop a speech processing strategy for cochlear implant based on characteristics of Chinese language. The paper discusses first the characteristics of Chinese speech signals, and then presents simulation results on the effect of pitch variation in speech perception. Results show that adding tonal information to a CIS (Continuous Interleaved Sampling) speech processor will offer an improved intelligibility of spoken Chinese. Based on the CIS strategy, a novel speech processor with dynamic modulation of stimulation rate is proposed for cochlear implants for use with Chinese deaf people
  • Keywords
    hearing aids; medical signal processing; prosthetics; pulse modulation; speech intelligibility; speech processing; speech synthesis; Chinese language; FES stimulation rate; cochlear implants; continuous interleaved sampling processor; dynamic modulation; explicit variation of pitch; improved intelligibility; pulse modulation; speech perception; speech processing strategy; speech synthesis; tonal information; word pronunciation; Cochlear implants; Computational Intelligence Society; Data mining; Deafness; Frequency; Natural languages; Signal sampling; Speech analysis; Speech processing; Speech synthesis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Engineering in Medicine and Biology Society, 1998. Proceedings of the 20th Annual International Conference of the IEEE
  • Conference_Location
    Hong Kong
  • ISSN
    1094-687X
  • Print_ISBN
    0-7803-5164-9
  • Type

    conf

  • DOI
    10.1109/IEMBS.1998.746162
  • Filename
    746162