• 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 the Acoustical Society of Korea
• /
• v.40 no.5
• /
• pp.503-514
• /
• 2021

Reverberation in speech signals tends to significantly degrade the performance of the Blind Source Separation (BSS) system. Especially in online systems, the performance degradation becomes severe. Methods based on joint diagonalizability constraints have been recently developed to tackle the problem. To improve the quality of separated speech, in this paper, we add the proposed de-reverberation method to the online BSS algorithm based on the constraints in reverberant environments. Through experiments on the WSJCAM0 corpus, the proposed method was compared with the existing online BSS algorithm. The performance evaluation by the Signal-to-Distortion Ratio and the Perceptual Evaluation of Speech Quality demonstrated that SDR improved from 1.23 dB to 3.76 dB and PESQ improved from 1.15 to 2.12 on average.

• 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.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.39 no.2
• /
• pp.10-20
• /
• 2002

Various blind source separation (BSS) and independent component analysis (ICA) algorithms have been developed. However, comparison study for BSS/ICA algorithms has not been extensively carried out yet. The main objective of this paper is to compare various promising BSS/ICA algorithms in terms of several factors such as robustness to sensor noise, computational complexity, the conditioning of the mixing matrix, the number of sensors, and the number of training patterns. We propose several benchmarks which are useful for the evaluation of the algorithm. This comparison study will be useful for real-world applications, especially EEG/MEG analysis and separation of miked speech signals.

• Journal of information and communication convergence engineering
• /
• v.10 no.2
• /
• pp.175-180
• /
• 2012

This paper presents a blind watermark detection scheme for an additive watermark embedding model. The proposed estimation-correlation-based watermark detector first estimates the embedded watermark by exploiting non-Gaussian of the real-world audio signal and the mutual independence between the host-signal and the embedded watermark and then a correlation-based detector is used to determine the presence or the absence of the watermark. For watermark estimation, blind source separation (BSS) based on independent component analysis (ICA) is used. Low watermark-to-signal ratio (WSR) is one of the limitations of blind detection with the additive embedding model. The proposed detector uses two-stage processing to improve the WSR at the blind detector; the first stage removes the audio spectrum from the watermarked audio signal using linear predictive (LP) filtering and the second stage uses the resulting residue from the LP filtering stage to estimate the embedded watermark using BSS based on ICA. Simulation results show that the proposed detector performs significantly better than existing estimation-correlationbased detection schemes.

• The Journal of the Acoustical Society of Korea
• /
• v.27 no.1E
• /
• pp.30-34
• /
• 2008

An improvement to the existing blind signal separation (BSS) method has been made in this paper. The proposed method models the inherent signal dependency observed in acoustic object to separate the real-world convolutive sound mixtures. The frequency domain approach requires solving the well known permutation problem, and the problem had been successfully solved by a vector representation of the sources whose multidimensional joint densities have a certain amount of dependency expressed by non-spherical distributions. Especially for speech signals, we observe strong dependencies across neighboring frequency bins and the decrease of those dependencies as the bins become far apart. The non-spherical joint density model proposed in this paper reflects this property of real-world speech signals. Experimental results show the improved performances over the spherical joint density representations.

• Proceedings of the IEEK Conference
• /
• 2000.07a
• /
• pp.241-244
• /
• 2000

This paper addresses a new method of blind source separation (BSS) when sources are nonstationary signals. Our method requires only multiple correlation matrices of the observed data at several time-windowed data frames to estimate the mixing matrix. In contrast to most existing BSS methods where higher-order statistics is necessary, our method is based on only second-order statistics. In the framework of correlation matching, we develop a new BSS algorithm. The useful behavior of the proposed method is verified by numerical experiments.

• Journal of Broadcast Engineering
• /
• v.9 no.1
• /
• pp.9-16
• /
• 2004

In this paper, we present a speech enhancement method as a pre-processor for voice commander under car environment. For the friendly and safe use of voice commander in a running car, non-stationary audio signals such as music and non-candidate speech should be reduced. Ow technique is a two microphone-based one. It consists of two parts Blind Source Separation (BSS) and Kalman filtering. Firstly, BSS is operated as a spatial filter to deal with non-stationary signals and then car noise is reduced by kalman filtering as a temporal filter. Algorithm Performance is tested for speech recognition. And the results show that our two microphone-based technique can be a good candidate to a voice commander.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.27-34
• /
• 2006

In this study, we propose this new algorithm that generates score function in ICA(Independent Component Analysis) using entropy theory. To generate score function, estimation of probability density function about original signals are certainly necessary and density function should be differentiated. Therefore, we used kernel density estimation method in order to derive differential equation of score function by original signal. After changing formula to convolution form to increase speed of density estimation, we used FFT algorithm that can calculate convolution faster. Proposed score function generation method reduces the errors, it is density difference of recovered signals and originals signals. In the result of computer simulation, we estimate density function more similar to original signals compared with Extended Infomax and Fixed Point ICA in blind source separation problem and get improved performance at the SNR(Signal to Noise Ratio) between recovered signals and original signal.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.10
• /
• pp.4814-4834
• /
• 2018

This paper presents an architecture for wireless sensor networks (WSNs) with blind source separation (BSS) applied to retrieve the received mixing signals of the sink nodes first. The little-to-no need of prior knowledge about the source signals of the sink nodes in the BSS method is obviously advantageous for WSNs. The optimization problem of the BSS of multiple independent source signals with complex and noncircular distributions from observed sensor nodes is considered and addressed. This paper applies Castella's reference-based scheme to Novey's negentropy-based algorithms, and then proposes a novel fast fixed-point (FastICA) algorithm, defined as the reference-signal negentropy complex FastICA (RSNT-cFastICA) for complex-valued noncircular-distribution source signals. The proposed method for the sink nodes is substantially more efficient than Novey's quasi-Newton algorithm in terms of computational speed under large numbers of samples, can effectively improve the power consumption effeciency of the sink nodes, and is significantly beneficial for WSNs and wireless communication networks (WCNs). The effectiveness and performance of the proposed method are validated and compared with three related BSS algorithms through theoretical analysis and simulations.