探究神经语音编解码器的鲁棒性特性
Probing the Robustness Properties of Neural Speech Codecs
AI总结：
本文系统评估了神经语音编解码器在噪声环境下的鲁棒性，通过分析其线性特性和频率响应，揭示了影响鲁棒性和音频保真度的关键因素，为未来编解码器设计提供了重要见解。
摘要：
神经语音编解码器彻底改变了语音编码，在保持音频保真度的同时实现了更高的压缩率。除了压缩之外，它们还作为分词策略，实现了语音上的语言建模，并推动了各种语音处理任务的范式转变。尽管取得了这些进展，它们在噪声环境中的鲁棒性仍未得到充分探索，引发了对其在现实场景中泛化能力的担忧。在这项工作中，我们系统地评估了神经语音编解码器在各种噪声条件下的表现，揭示了其鲁棒性方面的重要差异。我们进一步检查了它们的线性特性，发现了非线性失真，这部分解释了观察到的鲁棒性差异。最后，我们分析了它们的频率响应，以识别影响音频保真度的因素。我们的发现为编解码器行为和未来的编解码器设计提供了关键见解，并强调了噪声鲁棒性对于其在现实世界中集成的重要性。
英文摘要：
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.
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。
