评测神经语音编解码器在噪声下的鲁棒性，发现其性能差异显著。
Probing the Robustness Properties of Neural Speech Codecs
- 系统测试多种噪声下编解码器表现，揭示鲁棒性差异。
- 发现编解码器存在非线性失真，影响噪声环境下的稳定性。
- 适合关注语音模型落地与抗噪设计的研究者。
神经语音编解码器革新了语音编码技术，在实现更高压缩率的同时保持音频保真度。除压缩外，它们还成为语音分词策略，推动语音处理任务的范式转变。然而，其在噪声环境中的鲁棒性尚未充分研究，影响其在真实场景中的泛化能力。本文系统评估了神经语音编解码器在多种噪声条件下的表现，揭示了其鲁棒性存在显著差异。进一步分析其线性特性，发现非线性失真部分解释了鲁棒性差异。最后通过频响分析识别影响音质的关键因素。研究为编解码器行为理解与未来设计提供关键洞见，并强调噪声鲁棒性对实际应用的重要性。
原文摘要 · Abstract (English)
Neural speech codecs have revolutionized speech coding, achieving higher compression while preserving audio fidelity. Beyond compression, they have emerged as tokenization strategies, enabling language modeling on speech and driving paradigm shifts across various speech processing tasks. Despite these advancements, their robustness in noisy environments remains underexplored, raising concerns about their generalization to real-world scenarios. In this work, we systematically evaluate neural speech codecs under various noise conditions, revealing non-trivial differences in their robustness. We further examine their linearity properties, uncovering non-linear distortions which partly explain observed variations in robustness. Lastly, we analyze their frequency response to identify factors affecting audio fidelity. Our findings provide critical insights into codec behavior and future codec design, as well as emphasizing the importance of noise robustness for their real-world integration.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。