ICASSP 2021 Acoustic Echo Cancellation Challenge: Datasets, Testing Framework, and Results
ICASSP 2021 Acoustic Echo Cancellation Challenge: Datasets, Testing Framework, and Results
复制标题
ICASSP 2021 声学回声消除挑战：数据集、测试框架和结果
DOI：
10.1109/icassp39728.2021.9413457
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Sriram Srinivasan
中科院分区：
文献类型：
--
作者：
K. Sridhar;Ross Cutler;Ando Saabas;Tanel Pärnamaa;Markus Loide;H. Gamper;Sebastian Braun;R. Aichner;Sriram Srinivasan
ICASSP 2021声学回声消除挑战赛旨在促进声学回声消除（AEC）领域的研究，这是语音增强的重要组成部分，仍然是音频通信和会议系统的首要问题。最近的许多AEC研究报告了在训练和测试样本来自相同底层分布的合成数据集上的良好性能。然而，AEC性能通常在真实的录音上显著降低。此外，大多数传统的客观指标，如回声回波损耗增强（ERLE）和语音质量的感知评估（PESQ）不相关的主观语音质量测试中存在的背景噪声和混响在现实环境中发现。在这个挑战中，我们开源了两个大型数据集，以在单端通话和双端通话场景下训练AEC模型。这些数据集包括来自真实的环境中的2,500多个真实的音频设备和人类扬声器的录音，以及一个合成数据集。我们开源了两个大型测试集，并开源了一个在线主观测试框架，供研究人员快速测试他们的结果。这项挑战的获胜者将根据所有不同的单次谈话和双次谈话场景中的平均意见得分（MOS）来选出。
The ICASSP 2021 Acoustic Echo Cancellation Challenge is intended to stimulate research in the area of acoustic echo cancellation (AEC), which is an important part of speech enhancement and still a top issue in audio communication and conferencing systems. Many recent AEC studies report good performance on synthetic datasets where the train and test samples come from the same underlying distribution. However, the AEC performance often degrades significantly on real recordings. Also, most of the conventional objective metrics such as echo return loss enhancement (ERLE) and perceptual evaluation of speech quality (PESQ) do not correlate well with subjective speech quality tests in the presence of background noise and reverberation found in realistic environments. In this challenge, 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 2,500 real audio devices and human speakers in real environments, as well as a synthetic dataset. We open source two large test sets, and we open source an online subjective test framework for researchers to quickly test their results. The winners of this challenge will be selected based on the average Mean Opinion Score (MOS) achieved across all different single talk and double talk scenarios.