Title :
Speech conversion and its application to alaryngeal speech enhancement
Author :
Bi, Ning ; Qi, Yingyong
Author_Institution :
Qualcomm. Inc., San Diego, CA, USA
Abstract :
In this work, two speech conversion algorithms, a vector quantization (VQ) based algorithm and a linear multivariate regression (LMR) based algorithm, were modified. The modifications were aimed at reducing the spectral distortion (bandwidth increase) in the VQ-based algorithm and the spectral discontinuity in the LMR-based algorithm. The modified algorithms were used for the enhancement of alaryngeal speech. Results of perceptual evaluations indicated that listeners generally preferred to listen to the enhanced speech samples
Keywords :
hearing; spectral analysis; speech enhancement; vector quantisation; LMR-based algorithm; VQ-based algorithm; alaryngeal speech enhancement; linear multivariate regression based algorithm; perceptual evaluations; spectral discontinuity; spectral distortion; speech conversion algorithms; vector quantization based algorithm; Bandwidth; Cepstral analysis; Chirp; Land mobile radio; Quantization; Smoothing methods; Speech enhancement; Speech processing; Stability; Transfer functions;
Conference_Titel :
Signal Processing, 1996., 3rd International Conference on
Conference_Location :
Beijing
Print_ISBN :
0-7803-2912-0
DOI :
10.1109/ICSIGP.1996.571190
