Improvement of the convergence speed and the tracking ability of the fast Newton type adaptive filtering (FNTF) algorithm

Djendi, Mohamed; Bouchard, M.; Guessoum, Abderrezak; Benallal, Ahmed; Berkani, Daoud

doi:10.1016/j.sigpro.2005.09.012

Cited by 15 publications

(13 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The choice of s1 and s1 is found by simulations. In addition, the choice s1 = 0 and s2 = 0 corresponds to the original numerical stabilization method proposed in [20], which was adapted to the monochannel FNTF algorithm in [16]. In practice, the variables v1 N ,t and v2 N ,t are never zero on account of the machine precision.…”

Section: Numerical Stabilization Of the 2cfntf Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

A new fast Newton‐type adaptive filtering algorithm for stereophonic acoustic echo cancellation (SAEC)

Djendi

Guessoum

2009

Adaptive Control & Signal

Self Cite

View full text Add to dashboard Cite

This paper addresses the problem of acoustic echo cancellation. We propose a new version of the fast Newton transversal filter algorithm for stereophonic acoustic echo cancellation applications. This algorithm can be viewed as an efficient implementation of the extended two-channel fast transversal filter algorithm. Moreover, it fits naturally within the frame of the fast version of the recursive least-squares (RLS) algorithm, applied to the two-channel case. To stabilize the proposed two-channel algorithm, we have adapted and then applied a new numerical stabilization technique that has been proposed recently. The computational complexity of the proposed two-channel algorithm is less than half the complexity of the fastest two-channel RLS versions and very close to that of the two-channel normalized least mean squares algorithm when its predicting part length is chosen to be small. Simulation results and comparisons in term of complexities, convergence speed and tracking with the two-channel algorithms are presented.

show abstract

Section: Numerical Stabilization Of the 2cfntf Algorithmmentioning

confidence: 99%

“…In this contribution, we propose a new stereophonic version of the fast Newton transversal filter algorithm [16,17] that has a good performance in the SAEC applications. This new algorithm works to cancel the issue echo from the propagation of two input signals in the same room as shown in Figure 1.…”

Section: Introductionmentioning

confidence: 99%

A new fast Newton‐type adaptive filtering algorithm for stereophonic acoustic echo cancellation (SAEC)

Djendi

Guessoum

2009

Adaptive Control & Signal

Self Cite

View full text Add to dashboard Cite

show abstract

“…[18][19][20] The most important advantage of the NLMS algorithm is its simplicity and ease of implementation, but it has the drawback of slow convergence speed with correlated signals as in AEC systems. [30][31][32] A major problem of these fast algorithms is the numerical instability that constraints the good behavior of these algorithms. [20][21][22][23] The recursive least square algorithms family and their fast versions have improved the NLMS with correlated signals.…”

Section: Introductionmentioning

confidence: 99%

“…24,25 The most popular fast versions of the recursive least square algorithm are the fast transversal filter [26][27][28][29] and the fast newton transversal filter algorithms. [30][31][32] A major problem of these fast algorithms is the numerical instability that constraints the good behavior of these algorithms. 33,34 Another algorithmic family is the affine projection (AP) algorithm, which can be considered as a generalization of the NLMS family.…”

Section: Introductionmentioning

confidence: 99%

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

Djendi

2017

Adaptive Control & Signal

Self Cite

View full text Add to dashboard Cite

This 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 signalto-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.

show abstract

“…More advanced techniques are then proposed recently in [21,22]. Furthermore, several algorithms have been proposed, in combination with single, two-and multichannel techniques for NR and SE applications, are recently proposed as a new countermeasure for the presented problem [23][24][25][26]. Recently, a particular consideration has been made for the two forward and backward blind source separation structures to be applied to enhance corrupted speech signals and cancel the acoustic noise components.…”

Section: Introductionmentioning

confidence: 99%

A new efficient two-channel backward algorithm for speech intelligibility enhancement: A subband approach

Djendi

Bendoumia

2014

Applied Acoustics

Self Cite

View full text Add to dashboard Cite

Improvement of the convergence speed and the tracking ability of the fast Newton type adaptive filtering (FNTF) algorithm

Cited by 15 publications

References 13 publications

A new fast Newton‐type adaptive filtering algorithm for stereophonic acoustic echo cancellation (SAEC)

A new fast Newton‐type adaptive filtering algorithm for stereophonic acoustic echo cancellation (SAEC)

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

A new efficient two-channel backward algorithm for speech intelligibility enhancement: A subband approach

Contact Info

Product

Resources

About