Bootstrap Averaging for Model-Based Source Separation in Reverberant Conditions

Abstract

Abstract-Recently proposed model-based methods use timefrequency (T-F) masking for source separation, where the T-F masks are derived from various cues described by a frequency domain Gaussian Mixture Model (GMM). These methods work well for separating mixtures recorded in low-to-medium level of reverberation, however, their performance degrades as the level of reverberation is increased. We note that the relatively poor performance of these methods under reverberant conditions can be attributed to the high variance of the frequency-dependent GMM parameter estimates. To address this limitation, a novel bootstrap-based approach is proposed to improve the accuracy of expectation maximization (EM) estimates of a frequencydependent GMM based on an a priori chosen initialization scheme. It is shown how the proposed technique allows us to construct time-frequency masks which lead to improved model-based source separation for reverberant speech mixtures. Experiments and analysis are performed on speech mixtures formed using real room-recorded impulse responses.

A Scene Recognition and Semantic Analysis Approach to Unhealthy Sitting Posture Detection during Screen-Reading

“…Given a Gaussian-Mixture model, the goal is to maximize the likelihood function with respect to the parameters. An elegant powerful method for finding the maximum likelihood solution for models with latent variables is called the Expectation-Maximization algorithm, or EM algorithm [ 7 ]. Some initial magnitudes for means , covariances , and mixing coefficients are selected by us.…”

“…Unhealthy sitting posture not only increases the risk of occupational musculoskeletal disease, i.e., lumbar disease and cervical disease but it is closely related to the incidence of myopia. According to the study by the National Institute for Occupational Safety and Health (NIOSH) on musculoskeletal disease and occupational factors, unhealthy sitting postures caused by incorrect postures of the trunk and neck are closely related to human skeletal diseases [ 6 , 7 ]. Lis et al [ 8 ] found that working in an unhealthy sitting posture for more than five hours would increase the probability of contracting backache and sciatica.…”

Speech enhancement methods based on binaural cue coding

“…Considering the fact that the prior information of speech and noise can improve speech quality, our former works [26,27] have shown an effectiveness of using binaural inter-channel cues between speech and noise to enhance speech. In previous studies based on the cue parameter [28][29][30][31][32][33][34][35][36][37][38][39], the binaural inter-channel cues [28][29][30][31][32][33][34][35][36][37] have been used to estimate ideal T-F mask in binaural computational auditory scene analysis (CASA) systems and have shown a good performance in binaural speech processing. In the BCC technique [40][41][42], the binaural inter-channel cues were viewed as the side information, which was combined with a down-mixed audio signal to recover the left channel and right channel audio signals.…”