Application of speech conversion to alaryngeal speech enhancement

Author

Bi, Ning ; Qi, Yingyong

Author_Institution

Qualcomm Inc., San Diego, CA, USA

Volume

5

Issue

2

fYear

1997

fDate

3/1/1997 12:00:00 AM

Firstpage

97

Lastpage

105

Abstract

Two existing speech conversion algorithms were modified and used to enhance alaryngeal speech. The modifications were aimed at reducing the spectral distortion (bandwidth increase) in a vector-quantization (VQ) based system and the spectral discontinuity in a linear multivariate regression (LMR) based system. Spectral distortion was compensated for by formant enhancement using the chirp z-transform and cepstral weighting. Spectral discontinuity was alleviated using overlapping clusters during the construction of the conversion mapping function. The modified VQ and LMR algorithms were used to enhance alaryngeal speech. The results of perceptual evaluation indicated that listeners generally preferred to listen to the alaryngeal speech samples enhanced by the modified conversions over original samples

Keywords

Z transforms; cepstral analysis; speech coding; speech enhancement; speech intelligibility; speech processing; speech synthesis; vector quantisation; LMR algorithms; VQ based system; alaryngeal speech enhancement; alaryngeal speech samples; cepstral weighting; chirp z-transform; conversion mapping function; formant enhancement; linear multivariate regression based system; modified conversions; overlapping clusters; perceptual evaluation; spectral discontinuity; spectral distortion reduction; speech analysis; speech conversion algorithms; speech synthesis; vector quantization; Bandwidth; Land mobile radio; Larynx; Linear predictive coding; Multivariate regression; Noise reduction; Speech analysis; Speech enhancement; Speech synthesis; Vector quantization;

fLanguage

English

Journal_Title

Speech and Audio Processing, IEEE Transactions on

Publisher

ieee

ISSN

1063-6676

Type

jour

DOI

10.1109/89.554771

Filename

554771