arXiv cs.AI· Phillip Long, Yongyi Zang, Qihui Yang, Christodoulos Benetatos, Junfei Liu, Randal Leistikow, Julian McAuley, Perry R. Cook·· 1 天前AI 评分31
TAPE：学习通用音频效果表示
TAPE: Learning General Audio Effect Representations
AI 导读
TAPE（Transformations of Audio Parameter Embeddings）仅凭处理后的参考音频即可估计其信号处理链，并将其参数应用到另一段未处理录音。
正文 · 原文
Abstract:Musicians and mixing engineers often can decipher the signal processing chain they hear on a reference recording, then adapt it to new material. We present TAPE (Transformations of Audio Parameter Embeddings), which estimates this processing from the processed reference audio alone. An encoder trained to identify processors in eight major effect families maps the reference to an embedding. A differentiable digital signal processing (DSP) chain decodes the embedding into editable parameters in one forward pass and applies them to a different unprocessed recording. Its modules are equalization, compression, waveshaping, a small residual network, and reverberation. TAPE achieves lower spectral error than DeepAFx-ST, the previous state of the art for single-step regression, and lower spectral error than per-example search over a chain approximating ST-ITO's, while running 275$\times$ faster than that search. Because the decoder outputs DSP parameters, its chain can also run causally: a C++ implementation with the trained weights processed 128-sample buffers 1.8$\times$ faster than real time, with no missed deadlines.
| Comments: | Submitted to Transactions of Machine Learning Research; 25 pages, 5 figures, 18 tables |
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Audio and Speech Processing (eess.AS) |
| Cite as: | arXiv:2610.40759 [cs.SD] |
| (or arXiv:2610.40759v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40759 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Phillip Long [view email]
[v1]
Thu, 29 Oct 2026 17:17:15 UTC (2,951 KB)
来源：arXiv cs.AI · arxiv.org