• Journal of KIISE:Software and Applications
• /
• v.36 no.3
• /
• pp.179-186
• /
• 2009

This paper proposes a target speech extraction which restores speech signal of a target speaker form noisy convolutive mixture of speech and an interference source. We assume that the target speaker is known and his/her utterances are available in the training time. Incorporating the additional information extracted from the training utterances into the separation, we combine convolutive blind source separation(CBSS) and non-negative decomposition techniques, e.g., probabilistic latent variable model. The nonnegative decomposition is used to learn a set of bases from the spectrogram of the training utterances, where the bases represent the spectral information corresponding to the target speaker. Based on the learned spectral bases, our method provides two postprocessing steps for CBSS. Channel selection step finds a desirable output channel from CBSS, which dominantly contains the target speech. Reconstruct step recovers the original spectrogram of the target speech from the selected output channel so that the remained interference source and background noise are suppressed. Experimental results show that our method substantially improves the separation results of CBSS and, as a result, successfully recovers the target speech.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.13 no.2
• /
• pp.107-114
• /
• 2002

The problem of blind signal separation of independent sources consist in retrieving the source from the observation of unknown mixtures of unknown sources. In this paper, we propose a technique for blind signal separation that can extract original signals from their non-stationary mixtures observed in a ordinary room. The proposed method implements blind signal separation by minimizing a non-negative cost function that achieves the minimum when the second-order cross-correlation value of the observed signals becomes zero. The validity of the proposed method has been verified by a computer simulation and experiment that extracts two source signals from their mixtures observed in a normal room.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.44 no.1
• /
• pp.85-93
• /
• 2007

In case that multichannel blind deconvolution (MBD) applies to signals of which autocorrelation has a high level, separated signals are temporally whitened by diagonal elements of a separation filter matrix. In order to reduce this distortion, the algorithms, which are based on either constraining diagonal elements of a separation filter matrix or estimating a separation filter matrix by using linear prediction residual signals, are presented. Still, some problems are generated in these methods, when we separate reverberation of signals themselves or interference signals from mixed signals. To solve these problems, this paper proposes the multichannel blind deconvolution method which divides processing procedure into the stage to separate interference signals and the stage to eliminate a reverberation of signals themselves. In simulation results, we confirm that the proposed algorithm can solve the problems.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.2
• /
• pp.120-130
• /
• 2020

This paper solves the problem in underdetermined convolutive mixture by improving the disadvantages of the multichannel nonnegative matrix factorization technique widely used in blind source separation. In conventional researches based on Spatial Covariance Matrix (SCM), each element composed of values such as power gain of single channel and correlation tends to degrade the quality of the separated sources due to high variance. In this paper, level and frequency normalization is performed to effectively cluster the estimated sources. Therefore, we propose a novel SCM and an effective distance function for cluster pairs. In this paper, the proposed SCM is used for the initialization of the spatial model and used for hierarchical agglomerative clustering in the bottom-up approach. The proposed algorithm was experimented using the 'Signal Separation Evaluation Campaign 2008 development dataset'. As a result, the improvement in most of the performance indicators was confirmed by utilizing the 'Blind Source Separation Eval toolbox', an objective source separation quality verification tool, and especially the performance superiority of the typical SDR of 1 dB to 3.5 dB was verified.