Comparison of Conventional Enhancement and Separation Methods in Indoor Environments

Abstract

Speech enhancement is an important pre-processing step in a wide diversity of practical fields related to speech signals, and many signal-enhancement methods, such as fixed beamforming and adaptive beamforming, have already been proposed for speech enhancement. However, lack of comprehensive and quantitative performance evaluation of current enhancement methods when multi-speeches exist simultaneously, it is difficult to choose an appropriate enhancement method in a practical application. This work aims to study the implementation of several enhancement methods for multi-speech enhancement in indoor environment of T60 = 0 s and T60 = 0.3 s. We first propose and compare two types of enhancement approaches. The first type is the basic enhancement methods, including the delay-and-sum beamforming (DSB), minimum variance distortionless response (MVDR), linearly constrained minimum variance (LCMV), and independent component analysis (ICA); The second type is the improved enhancement methods, including the robust MVDR and LCMV, realized by eigen decomposition and diagonal loading. In addition, the online enhancement performance based on the iteration of single-frame speech signals is then researched. The experimental results show that the enhancement effect of LCMV and ICA is relatively more stable in the case of the basic enhancement methods; in the case of the improved enhancement algorithms, the methods which employed diagonal loading iterations are better. In the case of the online enhancement, the DSB with frequency masking yields the best performance on the signal-to-interferences ratio (SIR) and possesses the capacity to suppress interferences.