Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization

TL;DR

This paper introduces novel supervised and unsupervised speech enhancement algorithms based on Bayesian nonnegative matrix factorization, which outperform existing methods and do not require prior noise models.

Contribution

It proposes a Bayesian NMF framework for speech enhancement, including a noise model learning scheme and a hybrid HMM approach to address noise mismatch issues.

Findings

BNMF-based methods outperform state-of-the-art algorithms

The hybrid BNMF-HMM approach effectively handles unknown noise types

Online noise model learning enables unsupervised speech enhancement

Abstract

Reducing the interference noise in a monaural noisy speech signal has been a challenging task for many years. Compared to traditional unsupervised speech enhancement methods, e.g., Wiener filtering, supervised approaches, such as algorithms based on hidden Markov models (HMM), lead to higher-quality enhanced speech signals. However, the main practical difficulty of these approaches is that for each noise type a model is required to be trained a priori. In this paper, we investigate a new class of supervised speech denoising algorithms using nonnegative matrix factorization (NMF). We propose a novel speech enhancement method that is based on a Bayesian formulation of NMF (BNMF). To circumvent the mismatch problem between the training and testing stages, we propose two solutions. First, we use an HMM in combination with BNMF (BNMF-HMM) to derive a minimum mean square error (MMSE) estimator for the speech signal with no information about the underlying noise type. Second, we suggest a scheme to learn the required noise BNMF model online, which is then used to develop an unsupervised speech enhancement system. Extensive experiments are carried out to investigate the performance of the proposed methods under different conditions. Moreover, we compare the performance of the developed algorithms with state-of-the-art speech enhancement schemes using various objective measures. Our simulations show that the proposed BNMF-based methods outperform the competing algorithms substantially.