CodecSep: Prompt-Driven Universal Sound Separation on Neural Audio Codec Latents
CodecSep: 基于提示的通用神经音频编解码器潜在空间声音分离
机构 * Department of Electrical Engineering(电气工程系) ; Indian Institute of Technology, Kanpur(印度理工学院,坎浦尔)
AI总结 CodecSep通过在神经音频编解码器潜在空间中直接提取声源,实现开放词汇声音分离,相比AudioSep在SI-SDR指标上表现更优,且在ViSQOL和MOS-LQS上取得显著提升,同时提供低延迟的代码流部署方案。
Comments main content- 27 pages, total - 53 pages, 12 figure, Accepted by Transactions on Machine Learning Research (TMLR), 2026
Journal ref Transactions on Machine Learning Research, 2026. ISSN 2835-8856