Rigid Motion Model for Audio Source Separation

Blind source separation plays an important role in extracting the source components from one or more mixture(s) of the sources received by a sensor or receiver. It is blind since no other information besides the observed mixture signals is available. In presence of only one observed mixture, it is known as single channel blind source separation (SCBSS). This paper proposes a method of SCBSS based on variational mode decomposition (VMD) and principal component analysis (PCA). The observed signal is decomposed into a number of modes simultaneously using VMD. Then, PCA is used to select the corresponding source components from the decomposed modes. An example illustrating the separation of a sinusoid and speech signal by our proposed method has been presented. Cross-correlation coefficient has been used to measure the performance of the VMD-PCA algorithm. Our method has been compared with the single channel independent component analysis (SCICA) and ensemble empirical mode decomposition-principal component analysis-independent component analysis (EEMD-PCA-ICA) methods in terms of quality of performance and computational complexity.

With the increasing investment in the construction of power facilities and the use of higher voltage level, the noise generated by high voltage substation has become an unavoidable issue. The noise of the high-voltage substation is a mixture which is mixed by different noise sources. The mixed noise must be separated to several independent noise signals firstly for researching. An algorithm combined with the Wavelet Transform and the Sparse Component Analysis was presented in this paper which can separate the single channel mixed noise signal of high-voltage substation. The single channel blind source separation can be changed to the underdetermined blind source separation by setting two augmented signals which are the low-frequency part and the high-frequency part separated from the original noise signal by the Wavelet Transform. Then the signals of different noise sources can be separated by the Sparse Component Analysis. It is proved by the simulation and experiment in 330kV high-voltage substation that the algorithm can solve not only the underdetermined blind source separation, but also the single-channel blind source separation effectively.

Massive multiple input multiple output (MIMO) is the key technology in the 5G communication network. Blind source separation (BSS) plays an important role in MIMO communication when information about the transmitted signals or channel is not available. Independent component analysis (ICA) is one of the well-known BSS technique applied in MIMO wireless communication. Existing BSS techniques like ICA assumes number of receiving antennas to be greater than or equal to the number of transmit antennas and hence cannot be applied to multiple input single output (MISO) communication scenario, that happens during downlink massive MIMO communication. In single channel blind source separation (SCBSS) the source signals are retrieved from a single observed mixture (single channel or single receiving antenna) of the source signals. In this paper, we investigate the application of SCBSS to MISO communication system. Using ensemble empirical mode decomposition (EEMD), the MISO communication system is converted to a pseudo MIMO system followed by the application of principal component analysis (PCA) and ICA algorithms to separate the transmitted signals. The algorithm is successfully applied to 2 X 1 MISO system and with a slight modification to n X 1 MISO system. Simulation results are provided to validate the performance of the algorithm.

Single channel blind source separation (SCBSS) is an important method to separate source signals only from one received signal without any prior information. This paper proposes a SCBSS algorithm based on dual-tree complex wavelet transform (DTCWT) and ensemble empirical mode decomposition (EEMD). First, DTCWT is used to decompose the received signal into several decomposed signals. Then some of them with larger energy are decomposed by EEMD into the intrinsic mode functions, which are selected to constitute virtual signals with the received signal. Finally, the source signals are estimated by Fast-ICA from these virtual multichannel signals. The experimental results show that the performance of the proposed algorithm is significantly improved compared with the SCBSS algorithms based on EEMD and DTCWT respectively.

As newer and more reliable ways of construction were developed, civilization began to spread out further and retain functional infrastructure for longer periods of time.[...]

Blind single-channel source separation is a long-standing machine learning and signal processing problem. Traditional blind source separation (BSS) algorithms were proposed to solve this task utilizing multiple signal constraints. Generative adversarial network (GAN) are free from statistical constraints and samples, but the role of adversarial training in the task of BSS has not been fully demonstrated. Therefore, a new separation network model that enables to learn the known separated signal distribution from the stepwise fine estimation of the unknown mixture distribution was presented in this paper, and a self-attention mechanism was introduced to solve the problem of the blurring details of the generated image by the generator which preserves image details in the process of image separation. Compared with the existing single-channel blind source separation algorithm based on generative adversarial network-neural egg separation (NES), the detailed information of this new separation algorithm is more prominent, and the source signal in the mixed image has been separated more effectively, and has better separation performance than the classic blind source separation algorithms.

Feature mode decomposition (FMD) has advantages over the other newer time-frequency methods such as ensemble empirical mode decomposition (EEMD) and variational mode decomposition (VMD) in single channel blind source separation (SCBSS). However, FMD has the defect of needing to determine the precise number of fault sources manually. To solve the above defect of FMD, an adaptive method for determining the number of fault sources based on the shift invariant sparse code (SISC) is proposed. SISC was used to train a set of basis functions from the single channel signal, and the corresponding potential components were reconstructed firstly. Subsequently, the structural similarity of these potential components was used for clustering, and each of the obtained clustering signals represented one kind of fault. Then the number of clustering was determined by minimizing the structural correlation among the clustering signals. It was considered that the source separation had achieved the best effect when the structural difference among the clusters was the largest, and the number of clustering at this time was used as the optimal estimated value, which was used as the modal inputs number of FMD calculation model to realize SCBSS of rolling bearing. Simulation and experimental analysis were carried out to verify the effectiveness of the proposed method, and its superiority was also verified through comparison.

Aiming at the problem that ICA can only be confined to the condition that the number of observed signals is larger than the number of source signals; a single channel blind source separation method combining EEMD, PCA and RobustICA is proposed. Through the eemd decomposition of the single-channel mechanical vibration observation signal the multidimensional IMF components are obtained, and the principal component analysis (PCA) is performed on the matrix of these IMF components. The number of principal components is determined and a new matrix is generated to satisfy the overdetermined blind source separation conditions, the new matrix input RobustICA, to achieve the separation of the source signal. Finally, the isolated signals are respectively analyzed by the envelope spectrum, the fault frequency is extracted, and the fault type is judged according to the prior knowledge. The experiment was carried out by using the simulation signal and the mechanical signal. The results show that the algorithm is effective and can accurately diagnose the location of mechanical fault.

A time–frequency blind signal separation method applicable to underdetermined mixtures of dependent sources

Sequence to point learning based on bidirectional dilated residual network for non-intrusive load monitoring

The paper proposed a new algorithm to estimate source number based on cyclic spectrum and curve clustering. The cyclic amplitude spectrum expressions of common digital communication signals are analyzed. And the vanishing characteristics of the interference in the estimation of cyclic correlation using finite observations are derived. Then the estimation algorithm based on cyclic amplitude spectrum curve clustering is proposed, and its suitable conditions are given. Finally several simulations are carried out, which show the efficiency and feasibility of this algorithm.

The aim of the paper is to separate the phonocardiographic (PCG) signal from the mixture of PCG and speech signals. Therefore, genetic algorithm (GA) based filter-banks approach has been used to separate the signal. In this proposed technique, speech signal was modified and then subtracted from mixed signal to obtain the PCG signal. The modification in the speech was performed by modifying the short-time Fourier transform magnitude response. The magnitude response was further decomposed into nine filter-banks, each of bandwidth 50 Hz, upto 450 Hz. The magnitude components in each filter-band were varied with the weights of GA. The phase component was not modified. Extracted PCG signals were evaluated using Mel-frequency cepstral coefficients (MFCCs) based Mahalanobis distance measure and perceptual evaluation of speech quality. It is observed that GA performs well to extract PCG signal form mixture, with population size 30, number of weights 10 and the number of iterations less than 80. The proposed technique shows better accuracy than FastICA, however, the main limitation of the GA-based filter banks is the time complexity arising due to the involvement of iterative behavior.

Long-term monitoring of ECG via wearable monitoring systems has already been widely adopted to detect and prevent heart diseases. However, one of the main issues faced by wearable ECG monitoring systems is that motion artifacts significantly affect the systems' stability and reliability. Therefore, motion artifact reduction is a very challenging task in filtering and processing physiological signals. Based on the existing algorithms and ECG prior knowledge, in this paper, we propose an algorithm, CEEMDAN-IMFx-PCA-CICA, for motion artifact reduction in ambulatory ECG signals using single-channel blind source separation technique. Our algorithm first utilizes CEEMDAN to decompose the mixed signals into IMFs (intrinsic mode function) containing different source signal features, thereby forming new multi-dimensional signals. Using the correlation between IMFx (IMF component with the most ECG features) and each IMF, and PCA are then applied to reduce the dimension of each IMF. Finally, the blind separation of the source ECG signals is achieved by using CICA with IMFx as the constraint reference component. The results of our experiments indicate that our algorithm outperformed CEEMDAN-CICA, CEEMDAN-PCA-CICA, and improved CEEMDAN-PCA-CICA. Besides, the number of iterations of the CICA is significantly reduced; the separated source signal is better; the obtained result is stable. Furthermore, the separated ECG signal has a higher correlation with the source ECG signal and a lower RRMSE, especially in the case of high noise-to-signal ratios.

The cross projection engenders when mixed speech signal is represented over joint dictionary because of the bad distinguishing ability of joint dictionary in single-channel blind source separation (SBSS) using sparse representation theory, which leads to bad separation performance. A new algorithm of constructing joint dictionary with common sub-dictionary is put forward in this paper to this problem. The new dictionary can effectively avoid being projected over another sub-dictionary when a source signal is represented over joint dictionary. In the new algorithm, firstly we learn identify sub-dictionaries using source speech signals corresponding to each speaker. And then we discard similar atoms between two identity sub-dictionaries and construct a common sub-dictionary using these similar atoms. Finally, we combine those three sub-dictionaries together into a joint dictionary. The Euclidean distance among two atoms is used to measure the correlation of them in different identity sub-dictionaries, and similar atoms are searched based on the correlation. In testing stage, each source can be reconstructed with the projection coefficients corresponding to individual sub-dictionary and the common sub-dictionary. Contrast experiments tested in speech database show that the algorithm proposed in this paper performs better, when the Signal-to-Noise Ratio (SNR) is used to measure separation effect. The algorithm set out in this paper has lower time complexity as well.

As for the single-channel overlapped signals, in which the modulation parameters of the component signals are identical or similar, it is still a great challenge to extract the component signals. Aiming at this problem, a single-channel blind source separation (SCBSS) algorithm, constrained by constant modulus, is proposed for the overlapped Gaussian minimum shift keying (GMSK) signals and this algorithm also applies to other overlapped signals with constant modulus (CM), such as binary phase shift keying (BPSK) signals and quadrature phase shift keying(QPSK) signals. By tracking the channels of the component signals, the algorithm can effectively estimate their symbol sequences. Simulation results show that the proposed algorithm can work more robustly and reduce the frame error rate (FER), comparing with the competing algorithms.