迈向稀疏且可解释的音频编解码器
Toward a Sparse and Interpretable Audio Codec
AI总结：
本文提出一种概念验证音频编码器，将音频表示为稀疏事件及其发生时间，并利用物理假设建模起音与共振，以获得比传统块编码更直观、可解释的表示。
摘要：
当前广泛使用的现代音频编解码器，如 Ogg Vorbis 和 MP3，以及较新的“神经”编解码器（如 Meta 的 Encodec 或 Descript Audio Codec），大多基于块编码：音频被划分为重叠的、固定大小的“帧”，然后进行压缩。尽管这些方法通常能产生出色的重建效果，并可用于文本转音频等下游任务，但它们无法生成直观、可直接解释的表示。在本工作中，我们提出了一个概念验证音频编码器，将音频表示为一组稀疏的事件及其发生时间。我们利用基于物理的初步假设来建模起音过程，以及乐器本身和演奏所在房间的物理共振，以期鼓励形成稀疏、简洁且易于解释的表示。
英文摘要：
Most widely-used modern audio codecs, such as Ogg Vorbis and MP3, as well as more recent "neural" codecs like Meta's Encodec or the Descript Audio Codec are based on block-coding; audio is divided into overlapping, fixed-size "frames" which are then compressed. While they often yield excellent reproductions and can be used for downstream tasks such as text-to-audio, they do not produce an intuitive, directly-interpretable representation. In this work, we introduce a proof-of-concept audio encoder that represents audio as a sparse set of events and their times-of-occurrence. Rudimentary physics-based assumptions are used to model attack and the physical resonance of both the instrument being played and the room in which a performance occurs, hopefully encouraging a sparse, parsimonious, and easy-to-interpret representation.
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。
