Code Drift：迈向幂等神经音频编解码器
Code Drift: Towards Idempotent Neural Audio Codecs
AI总结：
针对神经音频编解码器被忽视的幂等性问题，研究发现现有模型多次编码后音频退化，通过微调提升幂等性且不影响下游性能，扩展其在文件压缩和迭代生成中的应用。
摘要：
神经编解码器在低比特率下对音频信号的高保真压缩方面表现出强大性能，其生成的基于token的表示在生成建模中尤为有用。尽管多数研究聚焦于压缩比和感知透明度的提升，但近期工作很大程度上忽视了另一个理想的编解码器属性——幂等性，即多次编码下压缩输出的稳定性。我们发现最先进的神经编解码器表现出不同程度的幂等性，部分编解码器仅经过三次编码后音频输出就显著退化。我们研究了低幂等性的可能原因，并设计了一种通过微调编解码器模型来提高幂等性的方法。随后我们考察了幂等性对简单条件生成建模任务的影响，发现可在不负面影响下游建模性能的前提下提高幂等性，这可能扩展神经编解码器在实际文件压缩和迭代生成建模工作流中的实用性。
英文摘要：
Neural codecs have demonstrated strong performance in high-fidelity compression of audio signals at low bitrates. The token-based representations produced by these codecs have proven particularly useful for generative modeling. While much research has focused on improvements in compression ratio and perceptual transparency, recent works have largely overlooked another desirable codec property -- idempotence, the stability of compressed outputs under multiple rounds of encoding. We find that state-of-the-art neural codecs exhibit varied degrees of idempotence, with some degrading audio outputs significantly after as few as three encodings. We investigate possible causes of low idempotence and devise a method for improving idempotence through fine-tuning a codec model. We then examine the effect of idempotence on a simple conditional generative modeling task, and find that increased idempotence can be achieved without negatively impacting downstream modeling performance -- potentially extending the usefulness of neural codecs for practical file compression and iterative generative modeling workflows.
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。
