用选择性状态空间模型建模光学压缩器的时间相关响应

View PDF HTML (experimental)

Abstract:This paper presents a method for modeling optical dynamic range compressors using deep neural networks with Selective State Space models. The proposed approach surpasses previous methods based on recurrent layers by employing a Selective State Space block to encode the input audio. It features a refined technique integrating Feature-wise Linear Modulation and Gated Linear Units to adjust the network dynamically, conditioning the compression's attack and release phases according to external parameters. The proposed architecture is well-suited for low-latency and real-time applications, crucial in live audio processing. The method has been validated on the analog optical compressors TubeTech CL 1B and Teletronix LA-2A, which possess distinct characteristics. Evaluation is performed using quantitative metrics and subjective listening tests, comparing the proposed method with other state-of-the-art models. Results show that our black-box modeling methods outperform all others, achieving accurate emulation of the compression process for both seen and unseen settings during training. We further show a correlation between this accuracy and the sampling density of the control parameters in the dataset and identify settings with fast attack and slow release as the most challenging to emulate.

Comments:	in Journal of the Audio Engineering Society vol. 73, 2025
Subjects:	Sound (cs.SD); Artificial Intelligence (cs.AI); Audio and Speech Processing (eess.AS)
Cite as:	arXiv:2408.12549 [cs.SD]
	(or arXiv:2408.12549v4 [cs.SD] for this version)
	https://doi.org/10.48550/arXiv.2408.12549 arXiv-issued DOI via DataCite
Related DOI:	https://doi.org/10.17743/jaes.2022.0194 DOI(s) linking to related resources

Submission history

From: Riccardo Simionato [view email]
[v1] Thu, 22 Aug 2024 17:03:08 UTC (9,937 KB)
[v2] Thu, 29 Aug 2024 09:46:54 UTC (9,937 KB)
[v3] Thu, 16 Jan 2025 14:26:40 UTC (10,063 KB)
[v4] Tue, 6 Oct 2026 08:39:07 UTC (9,942 KB)