Nonlinear Acoustic Echo Cancellation Research Articles

Nonlinear acoustic echo cancellation based on pipelined Hermite filters

This paper introduces a new class of nonlinear filters for nonlinear acoustic echo cancellation (NLAEC) based on Hermite nonlinear filters (HNFs), which is a sub-class of linear-in-the-parameters nonlinear filters (LIPNFs). Specifically, the basis functions of HNFs include cross-terms of the expanded inputs at different time instants, and are mutually orthogonal for white normally distributed input signals. Although HNFs yield good performance for NLAEC, they suffer from high computational complexity. To tackle this problem, a computationally efficient pipelined variant of HNFs is introduced. The pipelined HNFs (PHNFs) include a nonlinear part followed by a linear one such that the input space is first expanded nonlinearly and then cast by a linear mapping to the output space. Experimental results using both synthesized and real data, and involving several nonlinear scenarios show the effectiveness of the proposed approach.

Hybrid metaheuristic method of ABC kernel filtering for nonlinear acoustic echo cancellation

This research work uses nonlinear kernel adaptive filtering to eliminate echo, a type of voice that is undesirable and communicated over the microphone. Adaptive filters enable the detection of time-varying potentials and the tracking of the signal’s dynamic changes. In this work, a hybrid metaheuristic technique that combines the Artificial Bee Colony (ABC) with the Kernel Adaptive Improved Proportionate and Normalized Least Mean Square (KIPNLMS) filter is developed to significantly boost echo cancellation efficiency. The unique adaptive filter based on sub-filter and proportionate adaptation is combined in the advanced technique, which presents an improved Non-linear Acoustic Echo Cancellation (NAEC) framework. An essential part of kernel techniques is that they translate the information on to a high-dimensional feature space, where linear filtering is performed. In the initial space, the arithmetic operations are carried out by evaluating inner products among pairs of input patterns, also known as kernels. Along with the ABC step size regulation technique, kernel-based adaptive filtering improves Signal to Noise Ratio (SNR) and accelerates convergence. The algorithm's effectiveness is assessed through simulation using signal Echo Return Loss Enhancement (ERLE). The performance of Kernel LMS, Kernal Normalized LMS (KNLMS), Kernal Proportionate NLMS, and KIPNLMS algorithms are compared. In contrast to typical kernel adaptive filters, the suggested ABC-KIPNLMS increases the ERLE more than 10 dB compared to other algorithms.

Integrating automated machine learning and interpretability analysis in architecture, engineering and construction industry: A case of identifying failure modes of reinforced concrete shear walls

Machine learning (ML) has been recognized by researchers in the architecture, engineering, and construction (AEC) industry but undermined in practice by (i) complex processes relying on data expertise and (ii) untrustworthy ‘black box’ models. As a result, ML results of complex non-linear AEC problems, such as the failure mechanism of reinforced concrete (RC) shear walls, are not comparable with empirical and mechanics-based models. This paper aims to integrate automated ML (AutoML) and interpretability analysis to study the failure mechanism of RC shear walls. In this study, we collected a dataset of 351 comprehensive samples for the failure mode identification of RC shear walls. First, the AutoML model trained using the dataset outperformed a set of conventional ML methods in terms of the F1 accuracy score. Then, three model-agnostic interpretability analysis methods confirmed the trustworthiness of the AutoML model. The contribution of this paper is three-fold. First, AutoML sheds light on the automatic identification of failure modes of RC shear walls. Second, the interpretability analysis can validate ‘black-box’ ML models against long-established domain knowledge in solving non-linear AEC problems. Third, for AEC industrial practitioners, the whole process is automatic, accurate, less reliant on data expertise, and interpretable.

Semi-blind source separation using convolutive transfer function for nonlinear acoustic echo cancellation.

The recently proposed semi-blind source separation (SBSS) method for nonlinear acoustic echo cancellation (NAEC) outperforms adaptive NAEC in attenuating the nonlinear acoustic echo. However, the multiplicative transfer function (MTF) approximation makes it unsuitable for real-time applications, especially in highly reverberant environments, and the natural gradient makes it hard to balance well between fast convergence speed and stability. In this paper, two more effective SBSS methods based on auxiliary-function-based independent vector analysis (AuxIVA) and independent low-rank matrix analysis (ILRMA) are proposed. The convolutive transfer function approximation is used instead of the MTF so that a long impulse response can be modeled with a short latency. The optimization schemes used in AuxIVA and ILRMA are carefully regularized according to the constrained demixing matrix of NAEC. The experimental results validate significantly better echo cancellation performances of the proposed methods.

Research on Dual-Channel Nonlinear Acoustic Echo Cancellation in α-Stable Distributed Noise Environment

Research on Dual-Channel Nonlinear Acoustic Echo Cancellation in α-Stable Distributed Noise Environment

M-estimate affine projection spline adaptive filtering algorithm: Analysis and implementation

This paper investigates the M-estimate affine projection spline adaptive filtering (MAPSAF) algorithm, which utilizes a modified Huber function with robustness against impulsive interference, and employs historical regression data to update the weight and the knot vector estimates for nonlinear filtering tasks. The detailed convergence and steady-state analyses of MAPSAF are also carried out in the mean and mean-square senses. In addition, an improved MAPSAF by exploiting the combined step sizes, called the CSS-MAPSAF algorithm, is derived to speed up the convergence on the premise of low steady-state misalignment. Numerical experiments in nonlinear system identification and nonlinear acoustic echo cancellation problems corroborate the theoretical performance analysis and the superiority of the proposed algorithms.

Cascaded RLS Adaptive Filters Based on a Kronecker Product Decomposition

The multilinear system framework allows for the exploitation of the system identification problem from different perspectives in the context of various applications, such as nonlinear acoustic echo cancellation, multi-party audio conferencing, and video conferencing, in which the system could be modeled through parallel or cascaded filters. In this paper, we introduce different memoryless and memory structures that are described from a bilinear perspective. Following the memory structures, we develop the multilinear recursive least-squares algorithm by considering the Kronecker product decomposition concept. We have performed a set of simulations in the context of echo cancellation, aiming both long length impulse responses and the reverberation effect.

A family of split kernel adaptive filtering algorithms for nonlinear stereophonic acoustic echo cancellation

A family of split kernel adaptive filtering algorithms for nonlinear stereophonic acoustic echo cancellation

Nonlinear stereophonic acoustic echo cancellation using sub-filter based adaptive algorithm

The nonlinear echo path resulting from the unwarranted acoustic echo and nonlinear distortion will degrade the echo cancellation performance of a stereophonic acoustic echo cancellation system. Techniques proposed in the literature rely on the assumption of a linear echo path. In this paper, a nonlinear stereophonic acoustic echo cancellation framework is proposed to address the problem of nonlinear distortion in stereophonic acoustic cancellation systems with a better trade-off between convergence and steady-state performance. The proposed approach uses the functional link-based adaptive filtering to deal with the nonlinear distortion in combination with the sub-filter approach to enhance the convergence performance. In addition to that, the convergence analysis of the proposed algorithm is presented in this paper. Simulations carried out using echo return loss enhancement and magnitude squared coherence as performance metrics using speech and colored noise input demonstrate the proposed framework's ability to improve the echo cancellation performance in the presence of distortion.

Multiple sub filter based proportionate filtering for nonlinear acoustic echo cancellation

This paper presents a multiple sub-filter-based improved nonlinear acoustic echo cancellation (NAEC) framework to enhance the echo cancellation performance of the NAEC in the presence of nonlinear distortion. The proposed algorithm uses a novel combination of adaptive multiple sub-filter approach and proportionate filtering to enhance the convergence rate of the existing proportionate functional link-based NAEC algorithm by reducing the adaption time needed for updating the coefficients of the adaptive filter. In addition to that, the convergence and the steady-state analysis of the proposed algorithm are presented. The proposed NAEC framework is subjected to speech signal input corrupted with both white as well as colored noise as background noise and the colored noise input at low-to–high SNR conditions for a comprehensive analysis of the echo cancellation performance. The experimental results comprising of the echo return loss enhancement, spectrograms, and the perceptual evaluation of speech quality demonstrate the improvements brought by the proposed algorithm. At all signal-to-noise ratio conditions, the proposed algorithm has shown a 4 dB improvement in mean echo return loss enhancement compared to the existing algorithms validating the improvement in the proposed NAEC scheme’s performance.

Performance analysis of an improved split functional link adaptive filtering algorithm for nonlinear AEC

In the process of nonlinear acoustic echo cancellation (NAEC), the eradication of echo becomes challenging due to the nonlinear distortion introduced by the low-cost hands-free communication devices. To mitigate the effect of these artifacts, various NAEC adaptive filtering algorithms are existing which find their applicability in different echoed environments. But, there exists a scope to improve the echo return loss enhancement (ERLE) performance and the rate of convergence for adaptive NAEC algorithms. These improvements can be achieved with further optimization of key parameters in existing mean square error based adaptive algorithms and by proposing a novel combination of linear and nonlinear adaptive filters. In this paper, a split functional link-based adaptive filter (SFLAF) is proposed with an improved optimized -normalized least mean square adaptive algorithm for NAEC. In addition to that, the convergence and steady-state analyses of the proposed algorithm were presented in this paper. The performance of the proposed algorithm is compared to existing SFLAF based NAEC algorithms, and improvements are presented. The colored noise signal, clean speech, and speech signal corrupted with white noise are subjected as inputs to the proposed NAEC framework under different signal-to-noise ratios. The ERLE, spectrograms, and perceptual evaluation of sound quality are used as the performance indices for the comparison of the proposed algorithm with its counterparts. An average improvement of 3 dB is observed in the case of the proposed algorithm compared to its counterparts.

Semi-Blind Source Separation for Nonlinear Acoustic Echo Cancellation

The mismatch between the numerical and actual nonlinear models is a challenge to nonlinear acoustic echo cancellation (NAEC) when the nonlinear adaptive filter is utilized. To alleviate this problem, we combine a basis-generic expansion of the memoryless nonlinearity into semi-blind source separation (SBSS). By regarding all the basis functions of the far-end input signal as the known equivalent reference signals, an SBSS updating algorithm is derived following the constrained scaled natural gradient strategy. Unlike the commonly utilized adaptive algorithm, the proposed SBSS is based on the independence between the near-end signal and the reference signals, and is less sensitive to the mismatch of nonlinearity between the numerical and actual models. Experimental results show that the proposed method outperforms conventional methods in terms of echo return loss enhancement (ERLE) and near-end speech quality evaluated by perceptual evaluation of speech quality (PESQ) and short-time objective intelligibility (STOI).

Combined functional link adaptive filter for nonlinear acoustic echo cancellation

The usage of low-quality components in communicating devices may introduce nonlinearity in the audio signals. The degree of nonlinearity may vary over time due to the nonstationary nature of audio signals. In the presence of nonlinear audio signals, the performance of an acoustic echo cancellation (AEC) scheme is impacted by two major limitations. The first one is related to the modeling accuracy, and the second one is related to the adaptation performance. The issue of modeling accuracy exists because the available nonlinear AEC (NAEC) schemes consider the nonlinearity as time-invariant and employ a fixed architecture to model the echo path. The adaptation performance issue occurs due to the conflicting requirements of fast convergence and low steady-state error. There is a need for an architecture that not only models the nonlinearity efficiently but also provides better performance in terms of convergence. In this paper, three new architectures convex combination functional link adaptive filter (CC-FLAF), improved CC-FLAF (ICC-FLAF), and variable step size CC-FLAF (VSSCC-FLAF) are proposed to overcome the above limitations. The proposed architectures are based on the combination of adaptive filters and variable step size approach. Computer simulations demonstrate the effectiveness of proposed architectures, in improving the nonlinear modeling performance for NAEC applications.

The wavelet transform-domain adaptive filter for nonlinear acoustic echo cancellation

The usage of low-quality components in communicating devices introduces acoustic nonlinearity. The presence of nonlinearity creates challenges in noise cancellation applications, especially the acoustic echo cancellation (AEC) that requires an adaptive filter of a very high order. However, the functional link adaptive filter (FLAF) algorithm models the acoustic nonlinearity efficiently but shows slow convergence performance due to a very high filter order. To improve the convergence performance of the FLAF, the wavelet transform-domain FLAF (WTD-FLAF) is proposed for nonlinear AEC (NAEC) applications. The convergence rate is improved by decomposing a higher-order adaptive filter into smaller-order subfilters. The convergence speed improvement is gained at the expense of increased computational complexity. A low complexity version of the WTD-FLAF, named as selective update WTD-FLAF (SU-WTD-FLAF) algorithm, is also presented. The SU-WTD-FLAF algorithm is based on the selective coefficient update approach. Computer simulations demonstrate that the convergence performance of the proposed algorithms outperforms the standard FLAF.

Nonlinear Acoustic Echo Canceller to Combat Sigmoid-Type Nonlinearities Under Noisy Environment

This paper presents a nonlinear-acoustic-echo-cancellation (NAEC) technique to tackle sigmoid-type nonlinearities under noisy environment. The nonlinear echo in acoustic systems is inevitable due to the inherent nonlinear characteristics of amplifiers and/or loudspeakers, which deteriorates the quality of speech as well as audio signal reception. Here, the sigmoid-type nonlinearity is modelled by incorporating two control parameters, which determine the shaping- and clipping-parameter values of the saturation curve at a particular room temperature. These control parameters are adjusted by utilizing the variable-step-size (VSS) least-mean-square (LMS) algorithm to enhance the convergence rate and tracking capability of presented NAEC. Furthermore, the impulse response of a room (indoor channel) in the acoustic echo path is modelled as a tap-delay-line finite-impulse-response filter, whose tap-coefficients are estimated by utilizing a modified recursive-least-squares (RLS) algorithm (involving the noise statistics) at the different values of signal-to-noise-ratio (SNR), when correlated as well as uncorrelated input signals are processed. Simulation results demonstrate the efficiency and efficacy of above mentioned adaptive NAEC technique using the VSS-LMS and modified RLS algorithms in terms of the high convergence rate as well as high value of echo-return-loss-enhancement (ERLE) factor. Both the elevating value of shaping-parameter (i.e., increasing nonlinearity level) and the alleviating value of SNR adversely affect the performance of all NAECs. However, the VSS-LMS and modified RLS algorithm based presented adaptive NAEC outperforms the traditional VSS-LMS and normalized-least-mean-square (NLMS) algorithm based NAEC under similar conditions.

Nonlinear acoustic echo cancellation with kernelized adaptive filters

A well-known problem in speech communication is the occurrence of acoustic echo in hands-free telephony. There are several classical adaptive filters that have been used as a stand alone approach for linear acoustic echo cancellation(AEC). A common assumption in most AEC techniques is that the echo path is linear. However, in real scenarios, owing to distortions introduced by other acoustic artefacts in handheld devices, the echo path is nonlinear. Therefore, there is a need to employ a nonlinear echo canceller. In this paper, a kernel expansion on a family of adaptive filtering algorithms based on least mean square filter is proposed. Kernel methods help model the nonlinear echo path and attain global minimum easily by finding the optimal set of filter weights. The simulations are carried out for speech signal with and without noise under different signal-to-noise ratio values. The results show that the proposed method achieves a significant improvement in a nonlinear acoustic echo cancellation environment in terms of echo return loss enhancement.

Channel Sparsity Aware Function Expansion Filters Using the RLS Algorithm for Nonlinear Acoustic Echo Cancellation

In this paper, we propose a channel sparsity aware sequential recursive least squares (sparse SEQ-RLS) algorithm for function expansion filters with applications in nonlinear echo cancellation. The algorithm is developed based on a diagonal channel structure from the Volterra filter and updating dominant coefficients taking into consideration of sparse elements in the diagonal channel. The third-order Volterra, third-order even mirror Fourier nonlinear (EMFN), and functional link artificial neural network (FLANN) filters are developed according to the sparse SEQ-RLS algorithm. The computation complexity for the upper bound is analyzed to validate the efficiency for each proposed filter. Computer simulation results demonstrate that all proposed function expansion filters with the sparse SEQ-RLS algorithm are effective for nonlinear echo cancellation. In general, the EMFN filter provides better performance compared to the Volterra and FLANN filters.

A Neural Network-Based Nonlinear Acoustic Echo Canceller

In this letter, we introduce a novel approach for nonlinear acoustic echo cancellation. The proposed approach uses the principle of transfer learning to train a neural network that approximates the nonlinear function responsible for the nonlinear distortions and generalizes this network to different acoustic conditions. The topology of the proposed network is inspired by the conventional adaptive filtering approaches for nonlinear acoustic echo cancellation. The network is trained to model the nonlinear distortions using the conventional error backpropagation algorithm. In deployment, and in order to account for any variation or discrepancy between training and deployment conditions, only a subset of the network's parameters is adapted using the significance-aware elitist resampling particle filter. The proposed approach is evaluated and verified using synthesized nonlinear distortions and real nonlinear distortions recorded by a commercial mobile phone.

State-Space Microphone Array Nonlinear Acoustic Echo Cancellation Using Multi-Microphone Near-End Speech Covariance

Nonlinear acoustic echo cancellation AEC is a highly challenging task in a single-microphone; hence, the AEC technique with a microphone array has also been considered to more effectively reduce the residual echo. However, these algorithms track only a linear acoustic path between the loudspeaker and the microphone array. This study proposes a microphone array form of the single-microphone nonlinear AEC NAEC algorithm in the reverberant condition. We extend a single-microphone-based model of the nonlinear acoustic echo to the microphone array case and propose the modeling of the acoustic transfer function ATF vector extended with a power series using a state-space equation. The Kalman filter is also adapted to optimally and recursively estimate the ATF vector. Furthermore, low-rank approximation and multi-microphone Wiener filtering are applied to estimate the multi-microphone near-end speech covariance, which results in the microphone array NAEC algorithm showing a consistently outstanding performance under severe signal-to-echo ratio SER and highly reverberant conditions. Consequently, our approach outperforms conventional methods regarding echo reduction and near-end speech quality for a wide range of SER and reverberation conditions.

Collaborative block-delay Volterra filters for nonlinear acoustic echo cancellation

A new nonlinear adaptive filtering strategy, collaborative block-delay Volterra filters (CBDVF), is proposed for nonlinear acoustic echo cancellation (NAEC). This paper focuses on the theoretical reasonability and practical feasibility of the proposed algorithm. Specifically, a practice-friendly adaptive filtering architecture is designed to ensure that the linear filter is considered a priority to play the most important role in estimating the echo path while the nonlinear filters will further perfect the modeling nonlinearities. A CBDVF is obtained by a combination of linear filter and different nonlinear filtering blocks of different time-delay length, where the nonlinear time-delay blocks are activated or deactivated automatically and adaptively to fulfil their tasks via some adaptive shrinkage factors. Theoretical performance analysis is also conducted to characterize the stability condition of the proposed algorithm. Simulations with an acoustic echo cancellation problem demonstrate the effectiveness of the proposed CBDVF. Moreover, the evaluation for CBDVF is completed for a real NAEC scenario.