arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04552eess.AS
收藏

用于噪声鲁棒前端的灵活多通道语音增强

Flexible Multichannel Speech Enhancement for Noise-Robust Frontend

Ante Jukić, Jagadeesh Balam, Boris Ginsburg

AI总结:

本文提出一种灵活多通道语音增强系统,结合适用于任意通道配置的神经掩码估计器和自动参考选择多通道滤波器,在多种阵列几何结构上达到与专用系统相当的性能,并显著提升随机麦克风配置下的ASR鲁棒性。

摘要:

本文提出了一种灵活的多通道语音增强系统,主要目标是提高自动语音识别(ASR)在噪声条件下的鲁棒性。所提出的系统结合了一个适用于不同通道数和配置的灵活神经掩码估计器,以及一个具有自动参考选择功能的多通道滤波器。本文提出了一种变换-关注-拼接(transform-attend-concatenate)层来处理掩码估计器中的跨通道信息,实验表明该层对任意麦克风配置均有效。所展示的评估证明了该灵活系统在多种已见和未见紧凑阵列几何结构上的有效性,其性能可与固定配置专用系统相匹配。此外,在随机放置麦克风的配置中,观察到ASR性能显著提升。

英文摘要:

This paper proposes a flexible multichannel speech enhancement system with the main goal of improving robustness of automatic speech recognition (ASR) in noisy conditions. The proposed system combines a flexible neural mask estimator applicable to different channel counts and configurations and a multichannel filter with automatic reference selection. A transform-attend-concatenate layer is proposed to handle cross-channel information in the mask estimator, which is shown to be effective for arbitrary microphone configurations. The presented evaluation demonstrates the effectiveness of the flexible system for several seen and unseen compact array geometries, matching the performance of fixed configuration-specific systems. Furthermore, a significantly improved ASR performance is observed for configurations with randomly-placed microphones.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑