Acoustic echo cancellation using blind source separation

In the recent past, blind source separation (BSS) algorithms using multivariate statistical data analysis technique have been successfully used for source identification and separation in the field of biomedical and statistical signal processing. Recently numbers of different BSS techniques have been developed. With BSS methods being the feasible method for source separation and decomposition of biosignals, it is important to compare the different techniques and determine the most suitable method for the applications. This paper presents the performance of five BSS algorithms (SOBI, TDSEP, FastICA, JADE and Infomax) for decomposition of sEMG to identify subtle finger movements. It is observed that BSS algorithms based on second-order statistics (SOBI and TDSEP) gives better performance compared to algorithms based on higher-order statistics (FastICA, JADE and infomax).

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.

Blind Source Separation (BSS) algorithms based on the noise-free model are not applicable when the Signal Noise Ratio (SNR) is low. In view of this situation, our solution is to denoise the mixtures with additive white Gaussian noise firstly, and then use BSS algorithms. This paper proposes a piecewise Empirical Mode Decomposition (EMD) thresholding approach to denoise mixtures with strong noise. This approach can distinguish the noise-dominated IMFs and signal-dominated IMFs, and then respectively apply different thresholdings methods. Simulation results show that compared with the Wavelet denoising, the proposed approach has a better denoising performance, and can remarkably enhance the separation performance of BSS algorithms, especially when the signal SNR is low.

In this paper, a single channel Kalman filtering in the spectral domain is proposed for acoustic echo and noise cancellation (AENC). An augmented extended Kalman filter is used in this work which is suitable for processing general complex-valued nonlinear and nonstationary signals. The near-end speech and background noise are modelled to make the filter robust against double-talk and against noise. In this work, the approach for echo cancellation does not depend on double-talk detector (DTD) to model the echo path, when signals other than the echoed far-end signal are present. The performance evaluations are conducted over the NOIZEUS corpus. The experimental results demonstrate that the ideal Kalman filter (with near-end speech parameters) outperforms other enhancement methods of echo cancellation in terms of subjective and objective measures. The non-ideal Kalman filter (when near-end speech parameters are obtained by an EM algorithm) also shows promising results after the ideal Kalman filter.

The existence of noise, sound scattering and reverberation in active sonar echo signal makes it very difficult to extract the target echo signal. This paper uses the convolution blind source separation algorithm to process the active sonar echo signal. The signal is transferred to the frequency-domain by sliding the STFT. The JADE blind source separation algorithm is used in the frequency domain, and the signal is finally inverted to the time domain through the ISTFT. The separation effect is compared and evaluated through similarity coefficients, time-domain waveforms, and time-frequency diagrams. The simulation results show that this method has a good effect on the separation of active sonar echo signals.

In the field of camera-based photoplethysmography the application of blind source separation (BSS) techniques has extensively stressed to cope with frequently occurring artifacts and noise. Although said techniques can help to extract the cardiac component from a mixture of input sources, permutation indeterminacy inherit to BSS techniques often introduces inaccuracies or requires manual intervention. The current contribution focuses on methods to automatically select the cardiac component from the output of BSS techniques applied to camera-based photoplethysmograms. To that end, we propose simple Markov models to describe and subsequently identify cardiac components. It is shown that good results can be obtained by combining different simple Markov models.

An acoustic echo canceller (AEC) is often used to eliminate acoustic echoes generated in a hands-free communication system. AEC approximates the echo path using an adaptive filter and eliminates the acoustic echo by subtracting the echo replica generated using the filter from the observed signal. However, conventional adaptive algorithms for updating filters fail to estimate during double talk periods when both acoustic echo and near-end speech are observed. In recent years, it was shown that blind source separation (BSS) can be used for echo cancellation during double talk period. However, the convergence speed is slower than the convergence speed of the conventional method. In our previous research we proposed combining conventional AEC and BSS, where BSS was used as preprocessor of adaptive filter to perform echo cancellation. Since there is room for improvement in the echo cancellation performance in previous research, in this paper we propose a new approach using BSS alternative output as AEC input. Simulation results show that the proposed system is effective for echo path estimation when echo path fluctuation occurs during double talk period.

This work presents the application of Blind Source Separation (BSS) Algorithms on Dual-band IR Spectrogram for breast cancer detection and tracing the effect of long-term chemotherapy for breast-cancer patients. We take Dual-band IR Spectrogram's RAW Data as an input to the BSS algorithms. Integrated into the back-end processor of a Dual-band IR Sensor and Readout Circuit Platform, our Improved Neighbor-based BSS algorithm operated on Dual-band IR Spectrogram provides a better breast cancer detection. Considering the demarcating degree, our Improved Neighbor-based BSS algorithm is approximately 15% better than other algorithms. As to the correctness rate, our improved algorithm approximately increases 10% compared with other algorithms.

Signal estimation from functional magnetic resonance imaging data (fMRI) is a difficult and challenging task that involves carefully chosen models that can be validated by domain experts. Blind source separation (BSS) techniques such as principal component analysis (PCA), independent component analysis (ICA), and tensor decomposition have been proposed for estimating the task-fMRI signals. However, few studies have investigated their efficacy for classifying different tasks. This paper proposes yet another novel method to validate the signal estimation using predictive performance of the methods. Three commonly used BSS techniques are used for estimating signals (spatio-temporal maps) from task-fMRI. The dataset (consisting of 4 tasks) is taken from the Human Connectome Project (HCP). The extracted temporal signals are used to train a classifier that classifies two different tasks. For a binary classification, a Constrained-PARAFAC tensor decomposition achieves 92% accuracy for differentiating gambling vs. relational tasks. In addition, results for other binary task classifications are also presented. Overall, the proposed Constrained-PARAFAC performs better in prediction performance compared to PCA and ICA.

Blind source separation (BSS) algorithms are often categorized as either narrowband or broadband algorithms depending on whether their respective cost functions aim at individual DFT bins or the entire broadband signal. In this contribution, we present comparable general natural gradient-based formulations of both concepts based on the TRINICON framework. As a distinctive feature, narrowband algorithms imply an internal permutation and scaling problem. We show that the common DOA estimation-based methods for aligning the permutations effectively rely on geometric a-priori knowledge, and we explain why they need to be complemented by additional repair mechanisms for robust BSS. The latter can already be viewed as approximations of the generic TRINICON broadband algorithm. As a conclusion, we propose to always use a generic broadband algorithm as a starting point for the design of new BSS algorithms.

This letter proposes a novel method of a highly secured time domain cryptosystem to provide security for mobile voice calls. Using a modified version of blind source separation (BSS) algorithms, the proposed cryptosystem provides a complete solution for highly secured communications between the two ends of any voice call without the need for modifying the existing mobile network infrastructure. Moreover, this system can be easily connected to any type of mobile equipment. To overcome the bandwidth expansion usually associated with BSS algorithms, the proposed system uses a modified key generation process to limit the bandwidth occupied by the encrypted speech signal. Evaluation of the modified encryption and decryption algorithms proved the validity of these changes for speech signals in terms of signal to noise ratio and residual intelligibility.

This paper describes a novel modification to the well-known natural gradient or INFOMAX algorithm for blind source separation that largely mitigates its divergence problems. The modified algorithm imposes an a posteriori scalar gradient constraint that adds little computational complexity to the algorithm and exhibits fast convergence and excellent performance for fixed step size values that are largely independent of input signal magnitudes and initial separation matrix estimates. Evaluation of the approach for the separation of instantaneous and convolutive source mixtures using both time- and frequency-domain implementations shows its excellent separation behavior.

An acoustic echo canceler (AEC) is often employed to remove the acoustic echoes generated in hands-free communication systems. The AEC cancels the acoustic echoes by approximating the echo-path with the use of an adaptive filter and subtracting the pseudo echoes generated by the filter from the observed signal. The conventional adaptive algorithm for updating the filter, however, fails in estimation of the echo-path during double-talk when both the acoustic echo and the near-end speech are observed. Recently it has been shown that the blind source separation (BSS) can be employed to perform the echo cancelation during the double-talk; however, the convergence speed is slower than that of the conventional method. In this paper, a system is proposed that combines the conventional AEC and BSS; essentially, BSS is employed as a preprocessor for the adaptive filter performing the echo cancelation. Simulation results show that the proposed system is effective for the echo-path estimation during the double-talk as well as during variation in the echo path.

Different standards to measure the sound power of a machine can be chosen. Historically, in a place with extremely loud background noise, the intensity standard (UNE-EN ISO 9614-X) has been used because there is not enough signal-to-noise relation for the pressure method (UNE-EN ISO 374x). Nevertheless, in some cases, the interfering intensity will make the measurement impossible. To solve this problem for both techniques, a new methodology based on the use of blind source separation algorithms is proposed in order to allow an estimation of the signals of the primary sources from some mixed signals and, therefore, to calculate the sound power of the machine of interest. To make the estimated signals as similar as possible to the real signals of the machine under test, different preprocessing techniques (FFT, DCT, cepstrum or wavelets) have been used before the blind source separation algorithms. Once the tests have been conducted for every machine, it is possible to establish at least one process, or combination to obtain results similar to those obtained using the international standards. Finally, since the signals can be scaled at the output of the blind source separation algorithms, one possible signal correction scheme is analyzed.

The indirect method of using a passing vehicle to identify modal properties of a girder bridge has become attractive recently. Compared to the direct method, which requires a lot of sensors installed directly on the bridge itself, the indirect method only requires a single sensor installed on the vehicle to indirectly measure the response of the bridge. However, it is difficult to eliminate the adverse effect of road surface roughness. An indirect approach based on blind source separation is proposed for the first time in this study to identify the bridge element stiffness where two movable vehicles are used. Two identical vehicles stay at rest at the designated measurement points and their vertical accelerations are collected. After one measurement, the two vehicles move to other designated measurement points and the accelerations are collected again. The same procedure is repeated until the two vehicles have moved over all the designated measurement points. Then the blind source separation technique is employed to extract the fundamental mode shape of the bridge and the improved direct stiffness method is adopted to estimate the bridge element stiffness based on the collected data, which are used to monitor the health of the bridge structure and to maintain structure safety and natural symmetry. The proposed method only requires the output response of the vehicle due to the involvement of the blind separation technique. In addition, the proposed method can overcome the adverse effect of road surface roughness because the vehicles only move between two measurements and they stay at rest during one measurement. Numerical simulation was conducted to validate the proposed method, and the effect of various factors such as bridge damping ratio and measurement noise was investigated. Field measurement on Min-Xie bridge in Chongqing city was also carried out to further investigate the feasibility of the proposed method and showed that it can perform well in extracting the fundamental mode shape and evaluating bridge element stiffness.