• DocumentCode
    1463786
  • Title

    Speech feature extracted from adaptive wavelet for speech recognition

  • Author

    Chang, Sungwook ; Kwon, Y. ; Yang, Sung-il

  • Author_Institution
    Dept. of Control & Instrum. Eng., Hanyang Univ., Seoul, South Korea
  • Volume
    34
  • Issue
    23
  • fYear
    1998
  • fDate
    11/12/1998 12:00:00 AM
  • Firstpage
    2211
  • Lastpage
    2213
  • Abstract
    The speech signal is decomposed through adapted local trigonometric transforms. The decomposed signal is classified by M uniform sub-bands for each subinterval. The energy of each sub-band is used as a speech feature. This feature is applied to vector quantisation and the hidden Markov model. The new speech feature shows a slightly better recognition rate than the cepstrum for speaker independent speech recognition. The new speech feature also shows a lower standard deviation between speakers than does the cepstrum
  • Keywords
    adaptive signal processing; feature extraction; hidden Markov models; speaker recognition; speech processing; vector quantisation; wavelet transforms; adapted local trigonometric transforms; adaptive wavelet; decomposed signal; feature extraction; hidden Markov model; recognition rate; speaker independent speech recognition; speech feature; standard deviation; uniform sub-bands; vector quantisation;
  • fLanguage
    English
  • Journal_Title
    Electronics Letters
  • Publisher
    iet
  • ISSN
    0013-5194
  • Type

    jour

  • DOI
    10.1049/el:19981486
  • Filename
    739591