The 2nd Clarity Enhancement Challenge for Hearing Aid Speech Intelligibility Enhancement: Overview and Outcomes

The 2nd Clarity Enhancement Challenge for Hearing Aid Speech Intelligibility Enhancement: Overview and Outcomes
复制标题

DOI:
10.1109/icassp49357.2023.10094918
复制
发表时间:
2023-06
期刊:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子:
--
通讯作者:
M. Akeroyd;W. Bailey;J. Barker;T. Cox;J. Culling;S. Graetzer;G. Naylor;Zuzanna Podwinska;Zehai Tu
M. Akeroyd;W. Bailey;J. Barker;T. Cox;J. Culling;S. Graetzer;G. Naylor;Zuzanna Podwinska;Zehai Tu
中科院分区:
其他
文献类型:
--
作者:
M. Akeroyd;W. Bailey;J. Barker;T. Cox;J. Culling;S. Graetzer;G. Naylor;Zuzanna Podwinska;Zehai Tu

文献摘要

被引文献

相似文献

本文报告了第二届清晰度增强挑战赛 (CEC2) 的设计和结果,该挑战赛旨在激发助听器语音清晰度增强的新方法。这项挑战是让听众在嘈杂的家庭环境中关注目标说话者。该挑战赛在许多关键方面扩展了上一版本 CEC1:场景有多种干扰源,包括语音、噪音和音乐; Ambisonics 用于模拟听众头部运动;提供目标说话人身份以鼓励说话人提取方法。系统通过 HASPI 清晰度指标和听力障碍听众小组的听力测试进行评估。该论文回顾了提交的 18 个系统,从增强和放大阶段描述了它们。 HASPI 被认为是听众表现的良好预测指标。顶级系统采用精心设计的神经方法,可为复杂场景生成高度清晰的信号,信噪比低至 -12 dB,同时满足 5 毫秒延迟限制的挑战。
This paper reports on the design and outcomes of the 2nd Clarity Enhancement Challenge (CEC2), a challenge for stimulating novel approaches to hearing-aid speech intelligibility enhancement. The challenge was for a listener attending to a target speaker in a noisy, domestic environment. The challenge extends the previous edition, CEC1, in a number of key respects: scenes have multiple interferers including speech, noise and music; ambisonics are used to model listener head movement; target speaker identity is provided to encourage speaker extraction approaches. Systems are evaluated both via the HASPI intelligibility metric and with listening tests using a panel of hearing-impaired listeners. The paper reviews the 18 systems that were submitted describing them in terms of their enhancement and amplification stages. HASPI is seen to be a good predictor of listener performance. The top system, using carefully engineered neural approaches, produces highly intelligible signals for complex scenes with SNRs down to -12 dB while obeying the challenges 5 ms latency constraint.