Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet

Valin, Jean‐Marc; Tenneti, Srikanth V.; Helwani, Karim; Isik, Umut; Krishnaswamy, Arvindh

doi:10.48550/arxiv.2102.05245

Cited by 3 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [2] a similar idea was followed, however, only for a very small subset of the possible combinations, a rather simple feedforward neural network, and without explicit consideration of noise reduction capabilities. Furthermore, an intuitive and often seen input signal combination of a RES/NR network is the pair of enhanced signal E (k) and reference signal X (k), which delivers state of the art performance, e.g., in [4,9]. But as the reference signal does not contain any information about the room characteristics yet, could the estimated echo signal D (k) be a better choice?…”

Section: Experimental Designmentioning

confidence: 99%

“…In the meantime, also fully learned deep AEC approaches were proposed, where a single network incorporates the tasks of AEC, RES, and NR, e.g., [6,7] or further investigated in [8]. Although showing an impressive suppression performance, however, these are often accompanied by some near-end speech degradation and-at least for now-hybrid approaches are still one step ahead as can be seen with the leading model of the AEC Challenge on ICASSP 2021 being a hybrid approach [9].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System

Franzen¹,

Fingscheidt²

2021

Preprint

View full text Add to dashboard Cite

Deep neural network (DNN)-based approaches to acoustic echo cancellation (AEC) and hybrid speech enhancement systems have gained increasing attention recently, introducing significant performance improvements to this research field. Using the fully convolutional recurrent network (FCRN) architecture that is among state of the art topologies for noise reduction, we present a novel deep residual echo suppression and noise reduction with up to four input signals as part of a hybrid speech enhancement system with a linear frequency domain adaptive Kalman filter AEC. In an extensive ablation study, we reveal trade-offs with regard to echo suppression, noise reduction, and near-end speech quality, and provide surprising insights to the choice of the FCRN inputs: In contrast to often seen input combinations for this task, we propose not to use the loudspeaker reference signal, but the enhanced signal after AEC, the microphone signal, and the echo estimate, yielding improvements over previous approaches by more than 0.2 PESQ points.

show abstract

Section: Experimental Designmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System

Franzen¹,

Fingscheidt²

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Hybrid approaches, however, have proven very successful. For a variety of AEC tasks [37]- [45], for example, neural networks are used for residual echo suppression, noise suppression, or related. In a similar vein, neural networks paired with AFs for active noise control tasks have proven successful [46]- [49].…”

Section: Introductionmentioning

confidence: 99%

Meta-AF: Meta-Learning for Adaptive Filters

Casebeer¹,

Bryan²,

Smaragdis³

2022

Preprint

View full text Add to dashboard Cite

Adaptive filtering algorithms are pervasive throughout modern society and have had a significant impact on a wide variety of domains including audio processing, telecommunications, biomedical sensing, astropyhysics and cosmology, seismology, and many more. Adaptive filters typically operate via specialized online, iterative optimization methods such as least-mean squares or recursive least squares and aim to process signals in unknown or nonstationary environments. Such algorithms, however, can be slow and laborious to develop, require domain expertise to create, and necessitate mathematical insight for improvement. In this work, we seek to go beyond the limits of human-derived adaptive filter algorithms and present a comprehensive framework for learning online, adaptive signal processing algorithms or update rules directly from data. To do so, we frame the development of adaptive filters as a metalearning problem in the context of deep learning and use a form of self-supervision to learn online iterative update rules for adaptive filters. To demonstrate our approach, we focus on audio applications and systematically develop meta-learned adaptive filters for five canonical audio problems including system identification, acoustic echo cancellation, blind equalization, multichannel dereverberation, and beamforming. For each application, we compare against common baselines and/or current state-ofthe-art methods and show we can learn high-performing adaptive filters that operate in real-time and, in most cases, significantly out perform all past specially developed methods for each task using a single general-purpose configuration of our method.

show abstract

“…Customized AEC adaptive filters take many forms including algorithms based on sparsity [6], adaptive normalization [7], and adaptive learning-rates [8], as well as data-driven approaches for selecting learning rates automatically [9,10] and based on a meta-stepsize [11,12]. More recently, deep learning techniques have been used as AEC sub-components including learned residual echo suppressors [13,14,15], double-talk detectors [16], and nonlinear distortions blocks [17,18,19,20,21]. These approaches, however, commonly do not use neural network modules that adapt at test In the machine learning literature, there have been exciting developments in meta-learning, automatic machine learning, and learning how to learn methods.…”

Section: Introductionmentioning

confidence: 99%

Auto-DSP: Learning to Optimize Acoustic Echo Cancellers

Casebeer¹,

Bryan²,

Smaragdis³

2021

Preprint

View full text Add to dashboard Cite

Adaptive filtering algorithms are commonplace in signal processing and have wide-ranging applications from single-channel denoising to multi-channel acoustic echo cancellation and adaptive beamforming. Such algorithms typically operate via specialized online, iterative optimization methods and have achieved tremendous success, but require expert knowledge, are slow to develop, and are difficult to customize. In our work, we present a new method to automatically learn adaptive filtering update rules directly from data. To do so, we frame adaptive filtering as a differentiable operator and train a learned optimizer to output a gradient descent-based update rule from data via backpropagation through time. We demonstrate our general approach on an acoustic echo cancellation task (single-talk with noise) and show that we can learn high-performing adaptive filters for a variety of common linear and non-linear multidelayed block frequency domain filter architectures. We also find that our learned update rules exhibit fast convergence, can optimize in the presence of nonlinearities, and are robust to acoustic scene changes despite never encountering any during training.

show abstract

Low-Complexity, Real-Time Joint Neural Echo Control and Speech Enhancement Based On PercepNet

Cited by 3 publications

References 15 publications

Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System

Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System

Meta-AF: Meta-Learning for Adaptive Filters

Auto-DSP: Learning to Optimize Acoustic Echo Cancellers

Contact Info

Product

Resources

About