面向复杂声学环境的通用离散语音编解码器：重建与下游任务一致性研究
Towards General Discrete Speech Codec for Complex Acoustic Environments: A Study of Reconstruction and Downstream Task Consistency
AI总结：
该研究提出新颖的ERSB基准，通过评估鲁棒重建与下游任务一致性，揭示神经语音编解码器在复杂声学环境下的性能退化，为其未来提升环境鲁棒性指明方向。
摘要：
神经语音编解码器在重建纯净语音信号方面表现出色；然而，它们在复杂声学环境及下游信号处理任务中的有效性仍有待深入探索。在本研究中，我们引入了一个名为Environment-Resilient Speech Codec Benchmark (ERSB)的新颖基准，以系统评估神经语音编解码器是否具备环境鲁棒性。具体而言，我们评估了两项关键能力：(1)鲁棒重建，衡量对语音与非语音声学细节的保留程度；(2)下游任务一致性，确保使用重建语音替代原始语音时，下游信号处理任务的偏差最小化。我们的综合实验表明，复杂声学环境会显著降低信号重建与下游任务一致性。本研究突出了当前语音编解码器的局限性，并提出了提升其环境鲁棒性的未来方向。
英文摘要：
Neural speech codecs excel in reconstructing clean speech signals; however, their efficacy in complex acoustic environments and downstream signal processing tasks remains underexplored. In this study, we introduce a novel benchmark named Environment-Resilient Speech Codec Benchmark (ERSB) to systematically evaluate whether neural speech codecs are environment-resilient. Specifically, we assess two key capabilities: (1) robust reconstruction, which measures the preservation of both speech and non-speech acoustic details, and (2) downstream task consistency, which ensures minimal deviation in downstream signal processing tasks when using reconstructed speech instead of the original. Our comprehensive experiments reveal that complex acoustic environments significantly degrade signal reconstruction and downstream task consistency. This work highlights the limitations of current speech codecs and raises a future direction that improves them for greater environmental resilience.
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。
