Mohamed Djendi

A new adaptive filtering subband algorithm for two-channel acoustic noise reduction and speech enhancement

This paper addresses the problem of acoustic noise reduction and speech enhancement by adaptive filtering algorithms. Most speech enhancement methods and algorithms which use adaptive filtering structure are generally expressed in fullband form. One of these widespread structures is the Forward Blind Source Separation Structure (FBSS). This FBSS structure is often used to separate speech form noise and therefore enhance the speech signal at the processing output. In this paper, we propose a new subband implementation of this FBSS structure. In order to give more robustness to the proposed structure, we adapt then we apply to this subband structure a new combination of criteria based on the system mismatch and the smoothing filtering errors minimizations. The combination between this proposed subband structure with this optimal criteria allows to obtain a new two-channel subband forward (2CSF) algorithm that improves the convergence speed of the cross adaptive filters which are used to separate speech from noise. Objective tests under various environments are presented showing the good behavior of the proposed 2CSF algorithm.

Two-channel variable-step-size forward-and-backward adaptive algorithms for acoustic noise reduction and speech enhancement

This paper addresses the problem of speech enhancement and acoustic noise reduction by adaptive filtering algorithms. Recently, forward-and-backward (FB) blind-source-separation (BSS) structures have been proposed to solve acoustic noise reduction and speech enhancement problems. The FB structures use the least-mean-square (LMS) algorithm in combination with two BSS structures and are implemented with fixed-step-size to control the convergence behavior of the cross-coupling adaptive filters. In this paper, we propose two new two-channel variable-step-size FB algorithms (2C-VSSF and 2C-VSSB) that improve the previous LMS-based algorithm in the transient and the steady-state phases. These two new proposed FB algorithms are based on recursive formulas, which lead to efficient estimation of the optimal step-sizes of the cross-coupling filters. These proposed algorithms show significant improvement in the steady-state and transient mean-square-error (MSE) values. We present simulation results of the proposed 2C-VSSF and 2C-VSSB algorithms that confirm the superiority and good performance in comparison with the original versions, which use fixed-step-sizes. We propose two new two-channel variable-step-sizes forward and backward algorithmsThese two new algorithms improve their previous fixed-step-sizes based LMS algorithm.The convergence speed and the steady-state values characteristics are improved.These new proposed algorithms have shown a very important improvement in the steady-state and in the mean-square-error values (convergence speed).

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

Display Omitted We propose two new automatic VAD algorithms of types forward and backward BSS.The cross-adaptive filters are adapted automatically thanks to the proposed techniques.The proposed automatic algorithms are used to separate speech form noise and therefore enhance the speech signal intelligibility.The proposed algorithms show very good performances even in very noisy conditions. 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.

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

We propose a new subband implementation of the Forward BSS algorithm.We proposed a new two-channel variable step-size techniques adapted to the proposed FBSS algorithm.The new FBSS algorithm is used to separate speech form noise and therefore enhance the speech signal intelligibility.The new algorithm improves the steady state values of the cross adaptive filters which are used by the FBSS algorithm. 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.

An efficient stabilized fast Newton adaptive filtering algorithm for stereophonic acoustic echo cancellation SAEC

This paper addresses the field of stereophonic acoustic echo cancellation (SAEC) by adaptive filtering algorithms. Recently, we have proposed a new version of the fast Newton transversal FNTF algorithm for SAEC applications. In this paper, we propose an efficient modification of this algorithm for the same applications. This new algorithm uses a new proposed and simplified numerical stabilization technique and takes into account the cross-correlation between the inputs of the channels. The basic idea is to introduce a small nonlinearity into each channel that has the effect of reducing the inter-channel coherence while not being noticeable for speech due to self masking. The complexity of the proposed algorithm does not alter the complexity of the original version and is kept less than half the complexity of the fastest two-channel FTF filter version. Simulation results and comparisons with the extended two-channel normalized least mean square NLMS and FTF algorithms are presented.

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

We propose a new Frequency-domain adaptive decorrelating algorithm.The proposed algorithm improves convergence speed even with long adaptive filters.The new algorithm is efficient in Speech quality Enhancement and Acoustic Noise Reduction applications.The proposed algorithm distorts less the speech signal at the output. 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. Display Omitted

A Frequency Domain Adaptive Decorrelating Algorithm for Speech Enhancement

In this paper, we propose a new frequency domain-symmetric adaptive decorrelating (FD-SAD) algorithm to cancel punctual noise components from noisy observations. The proposed FD-SAD is combined with the forward blind source separation (FBSS) structure to enhance the performances of the time-domain symmetric adaptive decorelating (TD-SAD) algorithm. The new FD-SAD algorithm shows a fast convergence speed and good tracking behaviour even in very noisy conditions.

Performance analysis of under-modelling stereophonic acoustic echo cancellation by adaptive filtering LMS algorithm

This paper addresses the field of stereophonic acoustic echo cancellation (SAEC) with adaptive filtering algorithms. In SAEC applications, using the least mean square (LMS) algorithm, it is usually assumed that the lengths of the adaptive filters are equal to that of the unidentified system responses. Although, in many realistic situations, under-modelled lengths adaptive filters, whose lengths are less than that of the unidentified systems (under-modelled systems), are employed, and analysis results for the exact modelled stereophonic LMS algorithm are not automatically appropriate to the under-modeled lengths. In this paper, we present a statistical analysis of the under-modeled stereophonic LMS algorithm. Exact expressions and deterministic recursive equations to the mean coefficients behavior of the adaptive LMS filters are derived to completely characterize and assess the performances (transient and steady-state) of the under-modeling stereophonic LMS algorithm. The expected theoretical behaviour is compared with Monte Carlo simulations and practical experimental results, showing a very good agreement.

An efficient wavelet-based adaptive filtering algorithm for automatic blind speech enhancement

In this paper, we address the problem of speech enhancement by adaptive filtering algorithms. A particular attention has been paid to the backward blind source separation (BBSS) algorithm and its use in crosstalk resistant speech enhancement applications. In this paper, we propose to implement the BBSS algorithm in the wavelet-domain. The proposed backward wavelet BBSS (WBBSS) algorithm is then used in speech enhancement application when important crosstalk interferences are presents. The new WBBSS algorithm shows better performances in terms of convergence speed and steady state in comparison with the classical BBSS one. The performances properties of the proposed algorithm are evaluated in term of segmental SNR (SegSNR), segmental mean square error (SegMSE), and cepstral distance (CD) criteria. The obtained results have confirmed the best performance of the proposed WBBSS algorithm in a lot of situations when blind noisy observations are available.

A new dual forward BSS based RLS (DFRLS) algorithm for speech enhancement

This paper addresses the speech enhancement problem with adaptive filtering algorithms. We propose a new dual forward blind source separation (FBSS) algorithm based on the use of the recursive least square algorithm to update the cross-filters of the forward structure. This algorithm inherits the good characteristics of the combination between the FBSS and the good properties of the RLS algorithm. In this work, we propose to use the DFRLS algorithm in speech enhancement and acoustic noise reduction application. This proposed algorithm shows good characteristics in comparison with dual forward normalized least mean square (DFNLMS) algorithm is terms of various objective criteria as the segmental signal to noise ratio (SegSNR), the cepstral distance (CD), the system mismatch (SM) and the segmental mean square error (SegMSE).