R. Nishimura et al., SPEECH ENHANCEMENT USING SPECTRAL SUBTRACTION WITH WAVELET TRANSFORM, Electronics and communications in Japan. Part 3, Fundamental electronic science, 81(1), 1998, pp. 24-31
For speech enhancement based on spectral estimation/analysis, an analy
tic technique by which speech signals can he easily distinguished from
noise is desired. The wavelet transform (WT) is an analysis tool for
which various types of basis functions can be used. By selecting a pro
per fundamental wavelet. speech energy can be effectively localized in
the space transformed by the WT. In this article, we apply the WT to
the spectral subtraction technique, originally defined as using the sh
ort-time Fourier transform (STFT), and evaluate the effectiveness of i
ts outcome. Considering the structure of the human voice, we use Gabor
and Daubechies wavelets as well as a decaying sinusoid as the fundame
ntal wavelet. The results of computer simulations show that the S/N ra
tio was improved by the proposed method employing the decaying sinusoi
d as compared with conventional spectral subtraction. In articulation
tests with Japanese nonsense monosyllables, however, no significant di
fference could be observed. (C) 1998 Scripta Technica.