• Journal of the Korea Computer Industry Society
• /
• v.5 no.2
• /
• pp.269-274
• /
• 2004

Noisy speech recognition is one of most important problems in speech recognition. In this paper, a method which efficiently removes the mixed noise with speech, is proposed. The proposed method is based on the ICA to separate the mixed noise. ICA(Independent component analysis) is a signal processing technique, whose goal is to express a set of random variables as linear combinations of components that are statistically as independent from each other as possible.

• The Journal of the Korea Contents Association
• /
• v.6 no.12
• /
• pp.89-95
• /
• 2006

The performance of blind source separation(BSS) using independent component analysis (ICA) declines significantly in a reverberant environment. A post-processing method proposed in this paper was designed to remove the residual component precisely. The proposed method used modified NLMS(normalized least mean square) filter in frequency domain, to estimate cross-talk path that causes residual cross-talk components. Residual cross-talk components in one channel is correspond to direct components in another channel. Therefore, we can estimate cross-talk path using another channel input signals from adaptive filter. Step size is normalized by input signal power in conventional NLMS filter, but it is normalized by sum of input signal power and error signal power in modified NLMS filter. By using this method, we can prevent misadjustment of filter weights. The estimated residual cross-talk components are subtracted by non-stationary spectral subtraction. The computer simulation results using speech signals show that the proposed method improves the noise reduction ratio(NRR) by approximately 3dB on conventional FDICA.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.12 no.1
• /
• pp.43-50
• /
• 2016

This paper is on an acoustic echo canceller solving the double-talk problem by using the blind signal separation technology. The acoustic echo canceller may be deteriorated or diverged during the double-talk period. So we use the blind signal separation to detect the double talking by separating the near-end speech signal from the mixed microphone signal. The blind signal separation extracts the near-end signal from dual microphones by the iterative computations using the 2nd order statistical character in the closed reverberation environment. By this method, the acoustic echo canceller operates irrespective of the double-talking. We verified performances of the proposed acoustic echo canceller in the computer simulations. The results show that the acoustic echo canceller with this algorithm detects the double-talk periods well, and then operates stably without diverging of the coefficients after ending the double-talking. The merits are in the simplicity and stability.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.8 no.3
• /
• pp.125-131
• /
• 2012

This paper is on a stereo acoustic echo canceller with the blind signal separation. The convergence speed of the stereo acoustic echo canceller is deteriorated due to mixing two residual signals in the update signal of each echo canceller. To solve this problem, we are to use the blind signal separation(BSS) method separating the mixed signals. The blind signal separation method can extracts the source signals by means of the iterative computations with two input signals. We had verified performances of the proposed acoustic echo canceller for stereo through simulations. The results of simulations show that the acoustic echo canceller for stereo using this algorithm operates stably without divergence in the normal state. And, when the speech signals were inputted, this echo canceller achieved about 3dB higher ERLE in the case of using the BSS algorithm than the case of not using the BSS algorithm. But this echo canceller didn't get good performances in the case of inputting the white noises as stereo signals.

• 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.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.10 no.3
• /
• pp.143-149
• /
• 2014

This paper is on the blind signal separation(BSS) method by the geometric method. To separate the signal sources, we use Hough transform and BSS. Hough transform is a geometric method which let us know the local informations of the signal. We find the orientations of signals by Hough transform and know the number of signal sources. When the number of sensors is more than the number of sources. the BSS algorithm can separate the mixtures well in the time domain. This algorithm has a good performance in converging fast. We had checked up the quality of the algorithm after separating the mixed signals. The results of simulations show that this BSS method has the abnormal waveforms due to unconverging coefficients in the beginning, and stably has the separated waveforms which almost equal to the sources in the most period.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.6
• /
• pp.22-31
• /
• 2000

In this paper, we propose a method for removing noise components in the feature extraction process for robust speech recognition. This method is based on blind separation using independent component analysis (ICA). Given two noisy speech recordings the algorithm linearly separates speech from the unwanted noise signal. To apply ICA as closely as possible to the feature level for recognition, a new spectral analysis is presented. It modifies the computation of band energies by previously averaging out fast Fourier transform (FFT) points in several divided ranges within one met-scaled band. The simple analysis using sample variances of band energies of speech and noise, and recognition experiments showed its noise robustness. For noisy speech signals recorded in real environments, the proposed method which applies ICA to the new spectral analysis improved the recognition performances to a considerable extent, and was particularly effective for low signal-to-noise ratios (SNRs). This method gives some insights into applying ICA to feature levels and appears useful for robust speech recognition.