Comparison of single channel blind dereverberation methods for speech signals

Official URL: http://risc01.sabanciuniv.edu/record=b1640295 (Table of Contents)

Reverberation is an effect caused by echoes from objects when an audio wave travels from an audio source to a listener. This channel effect can be modeled by a finite impulse response lter which is called a room impulse response (RIR) in case of speech recordings in a room. Reverberation especially with a long filter causes high degradation in recorded speech signals and may affect applications such as Automatic Speech Recognition (ASR), hands-free teleconferencing and many others significantly. It may even cause ASR performance to decrease even in a system trained using a database with reverberated speech. If the reverberation environment is known, the echoes can be removed using simple methods. However, in most of the cases, it is unknown and the process needs to be done blind, without knowing the reverberation environment. In the literature, this problem is called the blind dereverberation problem. Although, there are several methods proposed to solve the blind dereverberation problem, due to the difficulty caused by not knowing the signal and the filter, the echoes are hard to remove completely from speech signals. This thesis aims to compare some of these existing methods such as Laplacian based weighted prediction error (L-WPE), Gaussian weighted prediction error (G-WPE), NMF based temporal spectral modeling (NMF+N-CTF), delayed linear prediction (DLP) and proposes a new method that we call sparsity penalized weighted least squares (SPWLS). In our experiments, we obtained the best results with L-WPE followed by G-WPE methods, whereas the new SPWLS method initialized with G-WPE method obtained slightly better signal-to-noise ratio and perceptual quality values when the room impulse responses are long.