• DocumentCode
    508375
  • Title

    Spectral Analysis for Emotion Recognition by NMF Features

  • Author

    Jeong, Kyungjoong ; Song, Jaiyoun ; Jeong, Hong

  • Author_Institution
    Adv. Signal Process. Lab., Pohang Univ. of Sci. & Technol., Pohang, South Korea
  • Volume
    5
  • fYear
    2009
  • fDate
    14-16 Aug. 2009
  • Firstpage
    121
  • Lastpage
    125
  • Abstract
    In this paper, we propose a new algorithm, which is using NMF features and which is different from traditional algorithms using temporal variations of the spectrogram. The proposed algorithm has been tested in several different ways by varying NMF and the speech database. The experimental results show performance of 90% and classification success of 77% for speaker dependent and independent cases, respectively.
  • Keywords
    emotion recognition; spectral analysis; NMF features; emotion recognition; spectral analysis; spectrogram; speech database; Emotion recognition; Feature extraction; Laboratories; Signal processing algorithms; Spatial databases; Spectral analysis; Spectrogram; Speech analysis; Speech processing; Testing; Emotion recognition; Feature extraction; Non-negative matrix factorization; Spectral analysis;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Natural Computation, 2009. ICNC '09. Fifth International Conference on
  • Conference_Location
    Tianjin
  • Print_ISBN
    978-0-7695-3736-8
  • Type

    conf

  • DOI
    10.1109/ICNC.2009.638
  • Filename
    5366996