通过时间引导与迭代优化，提升声源分离的精准度。
On Temporal Guidance and Iterative Refinement in Audio Source Separation
- 用微调Transformer检测声音事件，提供时变引导
- 迭代重用分离结果，逐步提升分离质量
- 在DCASE 2025挑战赛中获任务4第二名
声场景的空间语义分割（S5）旨在准确识别活跃声音类别并从复杂声学混合中精确分离其声源。传统系统采用音频标签+标签条件分离的两阶段流程，但常因缺乏细粒度时间信息而受限。本文提出新方法，增强事件检测与声源分离阶段的协同。首先，微调预训练Transformer以检测活跃声音类别；其次，使用另一实例的该Transformer执行声事件检测（SED），为分离模块提供详细时变指导；第三，引入迭代精炼机制，通过递归复用前一轮分离输出逐步提升分离质量。实验显示，该系统在DCASE Challenge 2025任务4中取得第二名成绩，显著提升音频标签与声源分离性能。代码与模型权重已开源：https://github.com/theMoro/dcase25task4。
原文摘要 · Abstract (English)
Spatial semantic segmentation of sound scenes (S5) involves the accurate identification of active sound classes and the precise separation of their sources from complex acoustic mixtures. Conventional systems rely on a two-stage pipeline - audio tagging followed by label-conditioned source separation - but are often constrained by the absence of fine-grained temporal information critical for effective separation. In this work, we address this limitation by introducing a novel approach for S5 that enhances the synergy between the event detection and source separation stages. Our key contributions are threefold. First, we fine-tune a pre-trained Transformer to detect active sound classes. Second, we utilize a separate instance of this fine-tuned Transformer to perform sound event detection (SED), providing the separation module with detailed, time-varying guidance. Third, we implement an iterative refinement mechanism that progressively enhances separation quality by recursively reusing the separator's output from previous iterations. These advancements lead to significant improvements in both audio tagging and source separation performance, as demonstrated by our system's second-place finish in Task 4 of the DCASE Challenge 2025. Our implementation and model checkpoints are available in our GitHub repository: https://github.com/theMoro/dcase25task4 .
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。