让音频自编码器动态调整帧率，提升压缩效率与质量
Elastic Time: Dynamic Frame Rate Bottlenecks for Neural Audio Coding
- 引入轻量级预测器，动态决定跳过哪些帧
- 推理时可灵活控制码率，比基线更高效
- 适合需要长上下文或生成任务的音频建模
神经音频自编码器已成为压缩、特征提取和生成的核心组件。然而，尽管现有系统支持可变码率，绝大多数模型仍采用固定隐层帧率，对信息密度差异大的区域分配相同时间预算，导致序列过长。本文提出 Elastic Time，一种动态帧率瓶颈机制，将固定帧率自编码器转换为动态版本。该方法学习一个轻量级隐层预测器，用于判断哪些帧可跳过并后续重建，从而在推理时实现高效的贪心边界选择。实验表明，该方法可在部署时实现码率控制，并在效率-质量权衡上优于基线。整体上，提供了一种灵活调节音频自编码器时间分辨率的机制，有助于提升生成和长上下文任务的建模效率。
原文摘要 · Abstract (English)
Neural audio autoencoders have become a core component of compression, feature extraction, and generation. However, while existing systems support variable bitrate, the vast majority of models still operate at a fixed latent frame-rate, allocating equal temporal budget to regions with very different information density, which can result in unnecessarily long sequences. We introduce Elastic Time, a dynamic frame-rate bottleneck that converts fixed-frame-rate autoencoders to dynamic ones. Our method learns a lightweight latent predictor used to decide which frames can be skipped and later reconstructed, enabling efficient greedy boundary selection at inference. Experiments show our method enables deployment-time rate control while improving efficiency-quality tradeoffs relative to baselines. Overall, we provide a flexible mechanism for adjusting temporal resolution in audio autoencoders, potentially facilitating more efficient downstream modeling for generation and long-context tasks.
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。