DocumentCode
3009978
Title
Arabic speech transformation using MFCC in GMM
Author
Elmanfaloty, Rania ; Korany, N. ; Youssef, El-Sayed A.
Author_Institution
Fac. of Eng., Electr. Eng. Dept., Alexandria Univ., Alexandria, Egypt
fYear
2012
fDate
3-5 July 2012
Firstpage
734
Lastpage
737
Abstract
Voice conversion (VC) is a process which modifies the speech signal produced by one source speaker so that it sounds like another target speaker. In this paper the transformation is determined by using equal Arabic utterances from source and target speakers. A conversion function based on Gaussian mixture model (GMM) is used for transforming the spectral envelope described by Mel Frequency Cepstral Coefficients (MFCC). The quality of the transformed utterances is measured using subjective and objective evaluations.
Keywords
Gaussian processes; speaker recognition; speech processing; Arabic speech transformation; GMM; Gaussian mixture model; MFCC; Mel frequency cepstral coefficients; VC; conversion function; source speaker; speech signal; target speakers; voice conversion; Discrete cosine transforms; Feature extraction; Filter banks; Mel frequency cepstral coefficient; Speech; Training; Vectors;
fLanguage
English
Publisher
ieee
Conference_Titel
Computer and Communication Engineering (ICCCE), 2012 International Conference on
Conference_Location
Kuala Lumpur
Print_ISBN
978-1-4673-0478-8
Type
conf
DOI
10.1109/ICCCE.2012.6271314
Filename
6271314
Link To Document