Semi-Blind Source Separation for Nonlinear Acoustic Echo Cancellation (2020-10-25T00:00:00.000000Z)

TL;DR

The proposed semi-blind source separation (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.

Abstract

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).

Authors

Hongsheng Chen

2 papers

Jing Lu

4 papers

Guoliang Cheng

2 papers

TL;DR

Abstract

Authors

References37 items

Enhanced Online IVA with Switched Source Prior for Speech Separation

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

Efficient Nonlinear Acoustic Echo Cancellation by Dual-stage Multi-channel Kalman Filtering

Effective Improvement of Under-Modeling Frequency-Domain Kalman Filter

Online IVA with Adaptive Learning for Speech Separation Using Various Source Priors

Efficient nonlinear acoustic echo cancellation by partitioned-block Significance-Aware Hammerstein Group Models

Blind acoustic echo cancellation without double-talk detection

On semi-blind estimation of echo paths during double-talk based on nonstationarity

Memory Proportionate APA with Individual Activation Factors for Acoustic Echo Cancellation

Significance-aware Hammerstein group models for nonlinear acoustic echo cancellation

Functional Link Adaptive Filters for Nonlinear Acoustic Echo Cancellation

State-Space Frequency-Domain Adaptive Filtering for Nonlinear Acoustic Echo Cancellation

Learning Echo Paths During Continuous Double-Talk Using Semi-Blind Source Separation

An Algorithm for Intelligibility Prediction of Time–Frequency Weighted Noisy Speech

Fourier expansion of hammerstein models for nonlinear acoustic system identification

Batch-Online Semi-Blind Source Separation Applied to Multi-Channel Acoustic Echo Cancellation

Real-Time Independent Vector Analysis for Convolutive Blind Source Separation

A short-time objective intelligibility measure for time-frequency weighted noisy speech

Fast and Robust Adaptation of DFT-Domain Volterra Filters in Diagonal Coordinates Using Iterated Coefficient Updates

Acoustic Echo Cancellation Using a Pseudocoherence Function in the Presence of Memoryless Nonlinearity

Barge-in- and noise-free spoken dialogue interface based on sound field control and semi-blind source separation

Scaled Natural Gradient Algorithms for Instantaneous and Convolutive Blind Source Separation

Frequency-domain adaptive Kalman filter for acoustic echo control in hands-free telephones

Orthogonalized power filters for nonlinear acoustic echo cancellation

Nonlinear acoustic echo cancellation using adaptive orthogonalized power filters

Acoustic Echo and Noise Control: A Practical Approach

Acoustic echo cancellation using nonlinear cascade filters

Combined blind/nonblind source separation based on the natural gradient

Adaptation of a memoryless preprocessor for nonlinear acoustic echo cancelling

Acoustic echo cancellation using NLMS-neural network structures

Image method for efficiently simulating small‐room acoustics

USE OF DECORRELATION PROCEDURE FOR SOURCE AND ECHO SUPPRESSION

COEFFICIENT PRUNING FOR HIGHER-ORDER DIAGONALS OF VOLTERRA FILTERS REPRESENTING WIENER-HAMMERSTEIN MODELS

Blind Source Separation Exploiting Higher-Order Frequency Dependencies

Methods for objective and subjective assessment of quality Perceptual evaluation of speech quality ( PESQ ) : An objective method for end-to-end speech quality assessment of narrow-band telephone networks and speech codecs

NONLINEAR ECHO CANCELLATION FOR HANDS-FREE SPEAKERPHONES

Blind signal separation : statistical principles

Field of Study

Journal Information

Name

Page

Volume

Venue Information

Name

Type

URL

Alternate Names