• DocumentCode
    2756827
  • Title

    SVM based recognition of Azerbaijani vowels

  • Author

    Imamverdiyev, Y.N. ; Sukhostat, L.V.

  • Author_Institution
    Inst. of Inf. Technol. of ANAS, Baku, Azerbaijan
  • fYear
    2011
  • fDate
    12-14 Oct. 2011
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    The recognition of vowels in Azerbaijani speech is very important for Azerbaijani speakers. However, it is rather difficult and there has been no efficient method to solve it yet. In this paper, we propose an approach to the recognition of Azerbaijani vowels via the support vector machine (SVM) with the Mel-Frequency Cepstral Coefficients (MFCCs) as the vowel´s features. It is shown by the experiments that this method can reach a high recognition accuracy.
  • Keywords
    cepstral analysis; speaker recognition; support vector machines; Azerbaijani vowels; Mel-frequency cepstral coefficients; SVM based recognition; speaker recognition; speech recognition; support vector machine; Computer languages; Discrete cosine transforms; FCC; Helium; Indium tin oxide; Mel frequency cepstral coefficient; Support vector machines; Azerbaijani vowels; Mel-frequency cepstral coefficients; Support Vector Machines;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Application of Information and Communication Technologies (AICT), 2011 5th International Conference on
  • Conference_Location
    Baku
  • Print_ISBN
    978-1-61284-831-0
  • Type

    conf

  • DOI
    10.1109/ICAICT.2011.6111022
  • Filename
    6111022