A Progressive Neural Network for Acoustic Echo Cancellation

Chen, Zhuangqi; Xia, Xianjun; Sun, Siyu; Wang, Ziqian; Chen, Cheng; Xie, Guoliang; Zhang, Pingjian; Xiao, Yijian

doi:10.1109/icassp49357.2023.10096411

Cited by 6 publications

(3 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• There is a PCC=0.49 between using additional datasets and the overall scale. Only one team added additional data (LibriSpeech [50]), though they were the first-place team [51]. • The first-place entry showed that personalized AEC did increase performance, but only by a small amount (improving the final score by 0.002).…”

Section: Results and Analysismentioning

confidence: 99%

ICASSP 2023 Acoustic Echo Cancellation Challenge

Cutler,

Saabas,

Pärnamaa

et al. 2024

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

The ICASSP 2023 Acoustic Echo Cancellation Challenge is intended to stimulate research in acoustic echo cancellation (AEC), which is an important area of speech enhancement and is still a top issue in audio communication. This is the fourth AEC challenge and it is enhanced by adding a second track for personalized acoustic echo cancellation, reducing the algorithmic + buffering latency to 20 ms, as well as including a full-band version of AECMOS [1]. We open source two large datasets to train AEC models under both single talk and double talk scenarios. These datasets consist of recordings from more than 10,000 real audio devices and human speakers in real environments, as well as a synthetic dataset. We open source an online subjective test framework and provide an objective metric for researchers to quickly test their results. The winners of this challenge were selected based on the average mean opinion score (MOS) achieved across all scenarios and the word accuracy (WAcc) rate.

show abstract

Section: Results and Analysismentioning

confidence: 99%

ICASSP 2023 Acoustic Echo Cancellation Challenge

Cutler,

Saabas,

Pärnamaa

et al. 2024

IEEE Open J. Signal Process.

View full text Add to dashboard Cite

show abstract

“…The first approach will be a basic normalized least means square (NLMS) filter after [3], as it has been widely used in AEC. Variations of this method are still frequently deployed in modern systems and subject to research [7], [8]. A further description of the specific model used here is given in Appendix A.…”

Section: B Echo Control (Ec) Methods Under Testmentioning

confidence: 99%

“…Recently, there has also been a great number of approaches employing deep neural networks (DNNs), either as a fully learned EC [10]- [14], as a residual (deep) echo 1 https://github.com/ifnspaml/EC-Evaluation-Toolbox suppression postfilter after a linear AEC [8], [15], [16], or as a hybrid approach combining parts of classical approaches with deep learning components [9], [17]. The most prominent recently published work is likely Microsoft's Deep-VQE model [14], performing AES, noise suppression, and speech dereverberation in a single network, thereby presenting a solution to challenging tasks that previously required a multi-stage network for good near-end speech preservation [11], [12].…”

Section: Introductionmentioning

confidence: 99%

Convergence and Performance Analysis of Classical, Hybrid, and Deep Acoustic Echo Control

Seidel,

Mowlaee,

Fingscheidt

2024

IEEE/ACM Trans. Audio Speech Lang. Process.

View full text Add to dashboard Cite

Acoustic echo cancellation (AEC) and suppression (AES) are widely researched topics. However, only few papers about hybrid or deep acoustic echo control provide a solid comparative analysis of their methods as it was common with classical signal processing approaches. There can be distinct differences in the behaviour of an AEC/AES model which cannot be fully represented by a single metric or test condition, especially when comparing classical signal processing and machine-learned approaches. These characteristics include convergence behaviour, reliability under varying speech levels or far-end signal types, as well as robustness to adverse conditions such as harsh nonlinearities, room impulse response switches or continuous changes, or delayed echo. A first contribution of this article is to present an extended set of test conditions and metrics that yields a proper characterization of an AEC/AES model and provides researchers with a useful toolbox to benchmark their systems. Second, we evaluate multiple AEC/AES models, each representing a classical, machine-learned, or hybrid paradigm, in various test conditions. We provide an analysis and new insights into their strengths and weaknesses and identify limitations of common metrics in some cases. Our entire toolbox of evaluation metrics and testing conditions is available on GitHub 1 .

show abstract