Title :
Speech Unit Selection Based on Matching Pursuit
Author :
Hosseinpour, M. ; Ranjbar, M.N. ; Mousavinejad, M.
Author_Institution :
Iran Telecommun. Res. Center, Tehran
Abstract :
This paper introduces a new method based on Matching Pursuit for speech unit selection. We used the Matching Pursuit transform parameters with a comparison algorithm to find the best match for a selected unit in a Text-To-Speech system based on concatenation. We chose Gabor atoms. Also Wigner-Ville distribution implemented for the time-frequency presentation of the transform and we used image processing approach to compare these time-frequency presentations of the acoustic units. On a database of 42 units 92% accuracy was obtained.
Keywords :
Wigner distribution; acoustic signal processing; image matching; speech synthesis; time-frequency analysis; Gabor atoms; Wigner-Ville distribution; image processing approach; matching pursuit; speech unit selection; text-to-speech system; time-frequency presentation; Acoustic waves; Concatenated codes; Electronic mail; Image databases; Image processing; Matching pursuit algorithms; Multimedia computing; Pursuit algorithms; Speech synthesis; Time frequency analysis;
Conference_Titel :
Computer Systems and Applications, 2007. AICCSA '07. IEEE/ACS International Conference on
Conference_Location :
Amman
Print_ISBN :
1-4244-1030-4
Electronic_ISBN :
1-4244-1031-2
DOI :
10.1109/AICCSA.2007.370933
