Wavelet speech enhancement based on nonnegative matrix factorization

TL;DR

This paper introduces a novel speech enhancement technique combining discrete wavelet packet transform and nonnegative matrix factorization, which improves speech quality and intelligibility without signal distortion.

Contribution

The study proposes a new DWPT-NMF based method that avoids spectrogram distortion and enhances speech signals more effectively than traditional STFT-NMF approaches.

Findings

Outperforms traditional STFT-NMF in speech quality

Enhances speech intelligibility in noisy environments

Maintains signal integrity without distortion

Abstract

For most of the state-of-the-art speech enhancement techniques, a spectrogram is usually preferred than the respective time-domain raw data since it reveals more compact presentation together with conspicuous temporal information over a long time span. However, the short-time Fourier transform (STFT) that creates the spectrogram in general distorts the original signal and thereby limits the capability of the associated speech enhancement techniques. In this study, we propose a novel speech enhancement method that adopts the algorithms of discrete wavelet packet transform (DWPT) and nonnegative matrix factorization (NMF) in order to conquer the aforementioned limitation. In brief, the DWPT is first applied to split a time-domain speech signal into a series of subband signals without introducing any distortion. Then we exploit NMF to highlight the speech component for each subband. Finally, the enhanced subband signals are joined together via the inverse DWPT to reconstruct a noise-reduced signal in time domain. We evaluate the proposed DWPT-NMF based speech enhancement method on the MHINT task. Experimental results show that this new method behaves very well in prompting speech quality and intelligibility and it outperforms the convnenitional STFT-NMF based method.