Forward Blind Source Separation Research Articles

New two-microphone simplified sub-band forward algorithm based on separated variable step-sizes for acoustic noise reduction

This paper presents an extended two-microphone adaptive filtering algorithm implemented on the sub-band simplified forward technique using new separated variable step-sizes parameters (denoted SSF-SVS: Simplified Sub-band Forward Separated Variable Step-sizes). This algorithm is proposed to reduce the acoustic noise and enhance the quality of estimated speech signal. Firstly, a sub-signal decomposition processing strategy is used to facilitating effective noise reduction with very fast convergence rate using two analysis filter banks. Secondly, a two-microphone simplified forward blind source separation (BSS) structure updated by the normalized least-mean-square algorithm (NLMS) for extracting the estimated speech signal. To guarantee a very fast convergence rate with high level of enhanced speech quality, thirdly we proposed new separated variable step-sizes parameters for controlling the adaptation of sub-band filters. The concept involves suggesting individual variable step-size parameter for each adaptive sub-filter, which are updated independently using the input sub-signal and the estimated output sub-signal. Experimental results confirm significant improvements in terms of convergence rate based on the mean square error criterion (MSE) in diverse acoustical environments. In other hand, the good performance of the proposed SSF-SVS algorithm in terms of speech quality is verified by on output signal-to-noise ratio (Output-SNR). The proposed algorithm compared with six two-microphone adaptive filtering algorithms in term of convergence rate, speech quality and computational complexity.

Adaptive Subband Forward Blind Source Separation Algorithms Based on Kalman Mechanism

Adaptive Subband Forward Blind Source Separation Algorithms Based on Kalman Mechanism

Hybrid PSO-NLMS (HPSO-NLMS) algorithm for blind speech quality enhancement in time domain

Speech intelligibility enhancement by adaptive two-channel filtering algorithms in the time domain is a fundamental problem in the areas of signal processing application. In this paper, we address this problem and suggest a new adaptive hybrid algorithm combined with Forward blind source separation (FBSS) structure to retrieve a speech signal from noisy observations. Usually, the Normalized Least Mean Square algorithm (NLMS) is widely used in adaptive filtering application, however conventional NLMS presents difficulties to solve the trade-off between the speed of convergence and the low steady state error. Recently, numerous variable step-size NLMS (VNLMS) algorithms were proposed to solve this trade-off, our proposed algorithm falls within the same type of algorithm. The proposed Hybrid PSO-NLMS (HPSO-NLMS) algorithm is a combination of the NLMS and the Particle Swarm Optimization algorithms (PSO), where we use PSO to obtain the appropriate NMLS step size at each iteration. We integrate the new HPSO-NLMS in the FBSS structure, and compare their performances to conventional NLMS and PSO algorithms. We show that the proposed algorithm can produce better noise reduction performance, in terms of several objective metric such as the system misalignment (SM), the Segmental signal to noise Ratio (SegSNR) and the segmented mean square error (SegMSE).

New sub-band proportionate forward adaptive algorithm for noise reduction in acoustical dispersive-and-sparse environments

In this study, we address the problem of acoustic noise reduction by two-channel forward adaptive filtering algorithm. In noise reduction applications, the normalized least mean square (NLMS) algorithm is recently implemented on the two-channel blind source separation (BSS) technique. Exactly in this paper, we propose a new implementation of two-channel forward BSS technique based on proportionate adaptive filtering algorithm in sub-band form. This new implementation is proposed exactly to resolve the problem of proportionate forward NLMS algorithm in term of convergence rate and speech quality when the acoustic environment is characterized by dispersive or sparse impulse responses. To prove the good performance of our proposed sub-band proportionate Forward NLMS algorithm (SP-FNLMS), we compare its performances with the full-band proportionate and non-proportionate versions exactly in four acoustical environments, more dispersive, dispersive, sparse and finally more sparse.

A new joint noise reduction and echo suppression system based on FBSS and automatic voice activity detector

In hands-free communication framework, the main drawback affecting the system is the presence of the acoustic noise and echo interferences. To address these problems at the same time, we propose a new joint noise reduction and echo suppression system based on forward blind source separation (FBSS) structure and automatic voice activity detection (AVAD). To deal with the acoustic echo issue, we propose to use an echo suppressor (ES) based on the single channel normalized least mean square (SCNLMS) algorithm. In order to obtain an accurate estimate of the echo signal, the punctual noise is pre-processed by a noise reduction (NR) process, where, for the NR process, we propose to use the two channel normalized least mean square (TCNLMS) algorithm based on the FBSS structure. The FBSS structure uses often manual voice activity detection (MVAD) mechanism to separate speech from noise, but this is not practice in real situations. To overcome the use of the MVAD, we propose a system that uses a new automatic voice activity detection (automatic VAD) mechanism based on signal-to-noise-ratio (SNR) estimation. The obtained results in terms of objective criteria have shown the efficiency of the proposed system in dealing with both interferences at the same time.

Efficient subband fast adaptive algorithm based-backward blind source separation for speech intelligibility enhancement

This paper addresses the problem of speech intelligibility enhancement by subband adaptive filtering algorithms in a blind framework. Recently in Djendi and Sayoud (Int J Speech Technol 22:391–406, 2019), we have proposed a subband adaptive algorithm based on the forward blind source separation structure that is efficient for acoustic noise reduction and speech intelligibility enhancement applications. In this paper, we propose a novel subband domain implementation of the backward blind source separation structure combined with a modified version of the fast normalized least mean square (FNLMS) algorithm. The new proposed subband algorithm is efficient in improving the speech signal intelligibility without introducing any distortion at the output. A fair comparison of the proposed backward subband FNLMS algorithm with other fullband type algorithms is presented. This comparison is based on the evaluation of several objective criteria. The obtained results show the best performance of the proposed subband algorithm in terms of speed convergence.

Efficient Sparse Blind Source Separation Algorithm for two- Channel Acoustic Noise Reduction

Recently, the acoustic noise reduction problem is treated by twochannel forward blind source separation (BSS) techniques combined with normalized least mean square algorithm (T-FNLMS). The TFNLMS algorithm shows good performances in two-channel convolutive dispersive mixture. In this paper, we propose new BSS structure based on the two-channel sparse normalized least mean square algorithm (TS-NLMS). The TS-NLMS algorithm is proposed exactly when the convolutive mixing system is characterized by sparse impulse responses. To confirm the good performance of this proposed algorithm, intensive experiments are done in acoustic noise reduction.

A new adaptive solution based on joint acoustic noise and echo cancellation for hands-free systems

In this paper, we address the problem of joint acoustic noise and echo cancellations for hands-free systems. The problem of acoustic echo cancelation (AEC) in the presence of background noise is a real challenge for any actual system. In this paper, we propose a new system that combines both processes, i.e. ANC and AEC. In our approach, we propose a two-stages procedure as follows: in the first stage, we propose to use the forward blind source separation (FBSS) structure to cancel the background noise components that is superimposed to the acoustic echo signal in the same environment, this FBSS structure uses the two-channel normalized least mean square (TC-NLMS) adaptive algorithm to cancel the background noise from the primary signal. In the second step, we propose to use an AEC system based on a single channel NLMS (SC-NLMS) algorithm to efficiently suppress the acoustic echo signal. This new combination between the FBSS and the AEC system allows reducing the acoustic echo signal to lower mean square values (MSE) in the permanent regime, this behavior will not be possible without FBSS. The performance properties of the proposed algorithm in such environment (i.e. presence of background plus acoustic echo signals in the same time) is evaluated with competitive algorithm with various objective criteria (ERLE, SegSNR, and GainMSE).

A new dual subband fast NLMS adaptive filtering algorithm for blind speech quality enhancement and acoustic noise reduction

This paper discusses the problem of acoustic noise reduction and speech enhancement through the forward blind source separation structure. Recently we have proposed a new combination between the forward blind source separation structure and the fast normalized least mean square algorithm that provides an efficient dual algorithm for noise reduction and speech enhancement applications. In this paper we propose a new subband implementation of this recent dual algorithm, this last allows improving the speed convergence behavior of the previous proposed algorithm in its fullband form. The performance of the proposed dual subband algorithm is compared with its fullband version of the dual fast normalized least mean square algorithm and the classical fullband dual normalized least mean square algorithm, and the two channel subband forward algorithm in terms of several objective criteria. The obtained results show the good performances of the proposed dual subband algorithm.

A new robust forward BSS adaptive algorithm based on automatic voice activity detector for speech quality enhancement

This paper presents a new adaptive blind source separation (BSS) algorithm for acoustic noise reduction and speech enhancement applications in a car framework. The forward BSS structure is often used to separate speech from noise and enhances the speech signal at the output processing. The drawback of most speech enhancement methods that are based on BSS structures is the use of a manual voice activity detection (VAD) system to control the source separation process. In this work, we propose a new algorithm based on the forward BSS structure and an automatic VAD (AVAD) system. The new AVAD system uses an adaptive approach based on a modified normalized least mean square (NLMS) adaptive algorithm to get a new speech enhancement algorithm. This proposed algorithm allows to: (i) reduce the computational complexity of previous techniques based on AVAD system; (ii) enhance the quality of the output speech signal. We have carried out intensive experiments on the proposed algorithm and others state of the art algorithms that use VAD or AVAD systems. In this paper, we show the efficiency of the proposed algorithm in terms of objective and subjective criteria.

New efficient two channel forward set-membership partial-update NLMS algorithms for blind speech enhancement and acoustic noise reduction

This paper addresses the problem of speech enhancement by partial adaptive algorithms combined with the forward blind source separation (FBSS) structure. We propose three new two-channel forward partial update algorithms: (i) The first algorithm is based on the use of the correlation properties to adapt and control the variable step-size parameter of adaptive cross-filters of the FBSS structure, this algorithm is called the two channel correlated set membership partial update NLMS (TC-SM-PU-NLMScor). (ii) The second algorithm is based on the use of a new coefficients update relations to control the normalization energy of the adaptive NLMS cross filters of the FBSS structure. This algorithm is called the two channel set member ship partial update regularized NLMS (TC-SM-PU-RNLMS). (iii) The third algorithm is a combination of proposed 1 (TC-SM-PU-NLMScor) and proposed 2 (TC-SM-PU-RNLMS), this algorithm is called the two channel correlated set membership partial update regularized NLMS (TC-SM-PU-RNLMScor). In this paper, we show the obtained results of the comparison between the three proposed algorithms and the original two channel correlated set membership partial NLMS (TC-SM-PU-NLMS) algorithm. This comparison is expressed in terms of objective criteria as the System Mismatch (SM), the Segmental Mean Square Error (SegMSE) and the Segmental SNR (SegSNR).

Two-channel forward NLMS algorithm combined with simple variable step-sizes for speech quality enhancement

This paper addresses the problem of speech quality enhancement by adaptive two-channel filtering algorithms. Recently, the forward blind source separation structure has been proposed and combined with normalized least-mean-square algorithm (FNLMS). The main drawback of two-channel FNLMS algorithm is its poor performance in steady state regime when the fixed step-sizes values are selected large. However, the slow convergence rate is observed with the small fixed step-size values. In this paper, we propose three new combinations of the basic FNLMS algorithm with simple variable step-sizes approaches, for improving both the steady state values and convergence rate (noted TVSF for Two-channel Variable Step-size Forward). In these modifications, we propose new configuration of two-channel forward structure by three simple and efficient variable step-sizes estimations. To confirm the good performance of three proposed TVSF algorithms compared with the classical fixed-step-size version, we have carried out several simulations in very noisy situations using several criteria.

A dual fast NLMS adaptive filtering algorithm for blind speech quality enhancement

This paper addresses the problem of acoustic noise reduction and speech enhancement in new telecommunications systems by adaptive filtering algorithms. Recently, a particular attention has been made to the blind source separation (BSS) approach applied for the separation of speech and noise components. The BSS application has inherits the good properties of the adaptive filtering algorithm to give more intelligible enhanced speech signal in term of quality. In this paper, we propose a new dual forward BSS algorithm that is based on signal prediction to give an automatic algorithm with a very fine behavior at the output. This algorithm is called the dual fast normalized least mean square (DFNLMS) algorithm. This algorithm has been tested in various noisy conditions and has shown its superiority in terms of the following objective criteria: cepstral distance (CD), segmental signal-to-noise-ratio (SegSNR), segmental mean square error (SegMSE), and system mismatch (SM). A comparison with other competitive and state-of-the-art algorithms is also presented in this paper.

A new two‐microphone Gauss‐Seidel pseudo affine projection algorithm for speech quality enhancement

SummaryThis study addresses the problem of speech quality enhancement by adaptive and nonadaptive filtering algorithms. The well‐known two‐microphone forward blind source separation (TM‐FBSS) structure has been largely studied in the literature. Several two‐microphone algorithms combined with TM‐FBSS have been recently proposed. In this study, we propose 2 contributions: In the first, a new two‐microphone Gauss‐Seidel pseudo affine projection (TM‐GSPAP) algorithm is combined with TM‐FBSS. In the second, we propose to use the new TM‐GSPAP algorithm in speech enhancement. Furthermore, we show the efficiency of the proposed TM‐GSPAP algorithm in speech enhancement when highly noisy observations are available. To validate the good performances of our algorithm, we have evaluated the adaptive filtering properties in computational complexity and convergence speed performance by system mismatch criteria. A fair comparison with adaptive and nonadaptive noise reduction algorithms are also presented. The adaptive algorithms are the well‐known two‐microphone normalized least mean square algorithm, and the recently published two‐microphone pseudo affine projection algorithm. The nonadaptive algorithms are the one‐microphone spectral subtraction and the two‐microphone Wiener filter algorithm. We evalute the quality of the output speech signal in each algorithm by several objective and subjective criteria as the segmental signal‐to‐noise ratio, cepstral distance, perceptual evaluation of speech quality, and the mean opinion score. Finally, we validate the superior performances of the proposed algorithm with physically measured signals.

A new regularized forward blind source separation algorithm for automatic speech quality enhancement

Abstract This paper addresses the problem of speech enhancement and acoustic noise reduction by adaptive filtering algorithms in a moving car through blind source separation (BSS) structures. In this paper we propose a new regularized forward blind source separation (RFBSS) algorithm that does not need voice activity detection (VAD) systems, and allows getting efficient speech enhancement performances with low complexity. The proposed RFBSS algorithm is compared with recent and classical speech enhancement algorithms in different noisy conditions. This comparison is evaluated in terms of Cepstral distance (CD), the system mismatch (SM) and the Segmental signal-to-noise ratio (SegSNR) criteria. The obtained results show the efficiency of the proposed algorithm and its superiority in comparison with competitive algorithms in speech enhancement applications.

An efficient frequency-domain adaptive forward BSS algorithm for acoustic noise reduction and speech quality enhancement

In this paper, we consider the speech enhancement and acoustic noise reduction problem in a moving car through a blind source separation scheme employing two loosely spaced microphones. We propose a new efficient frequency domain-symmetric adaptive decorrelation (FD-SAD) algorithm that removes punctual noise components from noisy speech signals. The FD-SAD algorithm is combined with the forward blind source separation FBSS structure to enhance the performances of its time-domain symmetric adaptive decorelating (TD-SAD) version. The proposed algorithm has a good tracking behaviour and fast convergence speed even in very noisy conditions with loosely spaced microphones. Intensive experiments have been done on the newly proposed algorithm in terms of the Segmental Signal-to-Noise-Ratio (SegSNR), the System Mismatch (SM), the Segmental Mean Square Error (SegMSE), and the Cepstral Distance (CD) criteria. The comparison results with the state-of-the-art algorithms have highlighted the excellent performance of the proposed algorithm, and have shown its ability to completely remove the correlated noise components from speech signal even in very noisy conditions when controlled by a voice activity detector.

Improved subband-forward algorithm for acoustic noise reduction and speech quality enhancement

This paper addresses the problem of speech enhancement and acoustic noise reduction by adaptive filtering algorithms. Recently, we have proposed a new Forward blind source separation algorithm that enhances very noisy speech signals with a subband approach. In this paper, we propose a new variable subband step-sizes algorithm that allows improving the previous algorithm behaviour when the number of subband is selected high. This new proposed algorithm is based on recursive formulas to compute the new variable step-sizes of the cross-coupling filters by using the decorrelation criterion between the estimated sub-signals at each subband output. This new algorithm has shown an important improvement in the steady state and the mean square error values. Along this paper, we present the obtained simulation results by the proposed algorithm that confirm its superiority in comparison with its original version that employs fixed step-sizes of the cross-coupling adaptive filters and with another fullband algorithm.

A wavelet-based forward BSS algorithm for acoustic noise reduction and speech enhancement

In this paper, we address the problem of noise reduction and speech enhancement by adaptive filtering algorithm. Recently, the well known forward blind source separation (FBSS) structure has been largely studied and intensively used to reduce acoustic noise components and to enhance speech signal. The FBSS structure is often combined with adaptive algorithms to accelerate the adaptation of the cross-filters, and to improve noise suppression at the output. In this paper, we propose to use a wavelet transform decomposition in the FBSS structure by using a two-channel forward wavelet symmetric adaptive decorrelating (WFSAD) algorithm. The proposed WFSAD algorithm provides a better compromise between time and frequency resolution and improves robustness of the noise reduction process when compared with the classical two-channel forward symmetric adaptive decorrelating (FSAD) algorithm. Simulation results prove the efficiency of the proposed WFBSS algorithm in comparison with conventional ones in terms of several objective and subjective criteria.

A two-sensor Gauss–Seidel fast affine projection algorithm for speech enhancement and acoustic noise reduction

This paper deals with the problem of noise reduction and speech enhancement by adaptive filtering using two-sensor configuration. The well-known Gauss–Seidel fast affine projection (GSFAP) algorithm is used in various applications such as acoustic echo cancelation (AEC), and adaptive noise control. In this paper, we use the GSFAP algorithm in noise reduction and speech enhancement application. Moreover, we derive a new two-sensor GSFAP (TS-GSFAP) algorithm for speech enhancement and acoustic noise reduction application. The application of the proposed TS-GSFAP algorithm to the forward blind source separation (FBSS) structure leads to a significant improvement of the output speech signals quality even in noisy conditions. A fair comparison of the proposed TS-GSFAP algorithm with other standard two-sensor type algorithms is presented. This comparison is based on the evaluation of several objective and subjective criteria such as: the segmental signal-to-noise ratio (SegSNR), the Cepstral distance (CD) and the system mismatch (SM), the perceptual evaluation of speech quality (PESQ), and the mean opinion score (MOS) criteria. The obtained results show the good performances of the proposed TS-GSFAP algorithm.

New automatic forward and backward blind sources separation algorithms for noise reduction and speech enhancement

In this paper, we consider the speech enhancement problem in a moving car through a blind source separation (BSS) scheme involving two spaced microphones. The forward and backward blind source separation structures often use manual voice activity detector (MVAD) systems to control the adaptation of the separating adaptive filters. In this paper, we propose two new automatic voice activity detector (AVAD) systems that allow adapting the original forward and backward BSS structures automatically. The proposed AVAD systems are based on the use of the forward BSS structure to estimate the optimal values of the separating adaptive filters step-sizes. Moreover, the new proposed algorithms are stable and could be used even in very noisy conditions. Intensive experiments are carried out with these two new proposed algorithms to validate their good performances in speech enhancement and noise reduction applications. The presented experiments are based on the system mismatch, the cepstral distance and the output signal-to-noise ratio criteria evaluations. The obtained results show the good performances of the proposed algorithms in comparison with their original versions, where manual VAD systems are used.