A new technique is proposed to solve the blind source separation (BSS) given only a single channel observation. The basis functions and the density of the coefficients of source signals learned by ICA are used as the ...A new technique is proposed to solve the blind source separation (BSS) given only a single channel observation. The basis functions and the density of the coefficients of source signals learned by ICA are used as the prior knowledge. Based on the learned prior information the learning rules of single channel BSS are presented by maximizing the joint log likelihood of the mixed sources to obtain source signals from single observation, in which the posterior density of the given measurements is maximized. The experimental results exhibit a successful separation performance for mixtures of speech and music signals.展开更多
Speech signals in frequency domain were separated based on discrete wavelet transform (DWT) and independent component analysis (ICA). First, mixed speech signals were decomposed into different frequency domains by DWT...Speech signals in frequency domain were separated based on discrete wavelet transform (DWT) and independent component analysis (ICA). First, mixed speech signals were decomposed into different frequency domains by DWT and the subbands of speech signals were separated using ICA in each wavelet domain; then, the permutation and scaling problems of frequency domain blind source separation (BSS) were solved by utilizing the correlation between adjacent bins in speech signals; at last, source signals were reconstructed from single branches. Experiments were carried out with 2 sources and 6 microphones using speech signals at sampling rate of 40 kHz. The microphones were aligned with 2 sources in front of them, on the left and right. The separation of one male and one female speeches lasted 2.5 s. It is proved that the new method is better than single ICA method and the signal to noise ratio is improved by 1 dB approximately.展开更多
In this paper, we applied RobustICA to speech separation and made a comprehensive comparison to FastICA according to the separation results. Through a series of speech signal separation test, RobustICA reduced the sep...In this paper, we applied RobustICA to speech separation and made a comprehensive comparison to FastICA according to the separation results. Through a series of speech signal separation test, RobustICA reduced the separation time consumed by FastICA with higher stability, and speeches separated by RobustICA were proved to having lower separation errors. In the 14 groups of speech separation tests, separation time consumed by RobustICA was 3.185 s less than FastICA by nearly 68%. Separation errors of FastICA had a float between 0.004 and 0.02, while the errors of RobustlCA remained around 0.003. Furthermore, compared to FastICA, RobustlCA showed better separation robustness. Experimental results showed that RohustICA was successful to apply to the speech signal separation, and showed superiority to FastlCA in speech separation.展开更多
This paper addresses the problem of Blind Source Separation (BSS) and presents a new BSS algorithm with a Signal-Adaptive Activation (SAA) function (SAA-BSS). By taking the sum of absolute values of the normalized kur...This paper addresses the problem of Blind Source Separation (BSS) and presents a new BSS algorithm with a Signal-Adaptive Activation (SAA) function (SAA-BSS). By taking the sum of absolute values of the normalized kurtoses as a contrast function, the obtained signal-adaptive activation function automatically satisfies the local stability and robustness conditions. The SAA-BSS exploits the natural gradient learning on the Stiefel manifold, and it is an equivariant algorithm with a moderate computational load. Computer simulations show that the SAA-BSS can perform blind separation of mixed sub-Gaussian and super-Gaussian signals and it works more efficiently than the existing algorithms in convergence speed and robustness against outliers.展开更多
The paper proposes a robust digital audio watermarking scheme using blind source separation(BSS) based on the global optimization of independency metric(IM),which is formulated as a generalized eigenvalue(GE) problem....The paper proposes a robust digital audio watermarking scheme using blind source separation(BSS) based on the global optimization of independency metric(IM),which is formulated as a generalized eigenvalue(GE) problem.Compared with traditional information-theoretical approaches used in digital audio watermarking,such as fast independent component analysis(FastICA),the proposed scheme has lower complexity without timeconsuming iteration steps used in FastICA.To make full use of the multiresolution characteristic of discrete wavelet transform(DWT) and the energy compression characteristic of discrete cosine transform(DCT),the watermark is embedded in the middle DWT-DCT coefficients and the independent component analysis(ICA) approach based on IM is used in the detecting scheme.Simulation results based on Stirmark for Audio v02 show that the proposed scheme has strong robustness as well as the imperceptibility and security.展开更多
基金Sponsored by the Research Foundation of Shanghai Municipal Education Commission(Grant No06FZ012 and 06FZ028)
文摘A new technique is proposed to solve the blind source separation (BSS) given only a single channel observation. The basis functions and the density of the coefficients of source signals learned by ICA are used as the prior knowledge. Based on the learned prior information the learning rules of single channel BSS are presented by maximizing the joint log likelihood of the mixed sources to obtain source signals from single observation, in which the posterior density of the given measurements is maximized. The experimental results exhibit a successful separation performance for mixtures of speech and music signals.
基金Supported by Tianjin Municipal Science and Technology Commission (No.09JCYBJC02200)
文摘Speech signals in frequency domain were separated based on discrete wavelet transform (DWT) and independent component analysis (ICA). First, mixed speech signals were decomposed into different frequency domains by DWT and the subbands of speech signals were separated using ICA in each wavelet domain; then, the permutation and scaling problems of frequency domain blind source separation (BSS) were solved by utilizing the correlation between adjacent bins in speech signals; at last, source signals were reconstructed from single branches. Experiments were carried out with 2 sources and 6 microphones using speech signals at sampling rate of 40 kHz. The microphones were aligned with 2 sources in front of them, on the left and right. The separation of one male and one female speeches lasted 2.5 s. It is proved that the new method is better than single ICA method and the signal to noise ratio is improved by 1 dB approximately.
基金National Natural Science Foundation of Chinagrant number:61271082,61201029,61102094
文摘In this paper, we applied RobustICA to speech separation and made a comprehensive comparison to FastICA according to the separation results. Through a series of speech signal separation test, RobustICA reduced the separation time consumed by FastICA with higher stability, and speeches separated by RobustICA were proved to having lower separation errors. In the 14 groups of speech separation tests, separation time consumed by RobustICA was 3.185 s less than FastICA by nearly 68%. Separation errors of FastICA had a float between 0.004 and 0.02, while the errors of RobustlCA remained around 0.003. Furthermore, compared to FastICA, RobustlCA showed better separation robustness. Experimental results showed that RohustICA was successful to apply to the speech signal separation, and showed superiority to FastlCA in speech separation.
基金Supported by the major program of the National Natural Science Foundation of China (No.60496311)the Chinese Postdoctoral Science Foundation (No.2004035061)the Foundation of Intel China Research Center.
文摘This paper addresses the problem of Blind Source Separation (BSS) and presents a new BSS algorithm with a Signal-Adaptive Activation (SAA) function (SAA-BSS). By taking the sum of absolute values of the normalized kurtoses as a contrast function, the obtained signal-adaptive activation function automatically satisfies the local stability and robustness conditions. The SAA-BSS exploits the natural gradient learning on the Stiefel manifold, and it is an equivariant algorithm with a moderate computational load. Computer simulations show that the SAA-BSS can perform blind separation of mixed sub-Gaussian and super-Gaussian signals and it works more efficiently than the existing algorithms in convergence speed and robustness against outliers.
基金the Scientific Research Foundation for the Returned Overseas Chinese Scholars,State Education Ministry of Chinathe National Natural Science Foundation of China (No. 60802058)
文摘The paper proposes a robust digital audio watermarking scheme using blind source separation(BSS) based on the global optimization of independency metric(IM),which is formulated as a generalized eigenvalue(GE) problem.Compared with traditional information-theoretical approaches used in digital audio watermarking,such as fast independent component analysis(FastICA),the proposed scheme has lower complexity without timeconsuming iteration steps used in FastICA.To make full use of the multiresolution characteristic of discrete wavelet transform(DWT) and the energy compression characteristic of discrete cosine transform(DCT),the watermark is embedded in the middle DWT-DCT coefficients and the independent component analysis(ICA) approach based on IM is used in the detecting scheme.Simulation results based on Stirmark for Audio v02 show that the proposed scheme has strong robustness as well as the imperceptibility and security.
