Speech Enhancement by Spectral Subtraction Based on Subspace Decomposition

Takahiro Murakami, Tetsuya Hoya, Yoshihisa Ishida

Abstract:

This paper presents a novel algorithm for spectral subtraction (SS). The method is derived from a relation between the spectrum
obtained by the discrete Fourier transform (DFT) and that by a subspace
decomposition method. By using the relation, it is shown that a noise re
duction algorithm based on subspace decomposition is led to an SS method
in which noise components in an observed signal are eliminated by sub
tracting variance of noise process in the frequency domain. Moreover, it is
shown that the method can significantly reduce computational complexity
in comparison with the method based on the standard subspace decomposi
tion. In a similar manner to the conventional SS methods, our method also
exploits the variance of noise process estimated from a preceding segment
where speech is absent, whereas the noise is present. In order to more reli
ably detect such non-speech segments, a novel robust voice activity detec
tor (VAD) is then proposed. The VAD utilizes the spread of eigenvalues of
an autocorrelation matrix corresponding to the observed signal. Simulation
results show that the proposed method yields an improved enhancement
quality in comparison with the conventional SS based schemes.