多阶段音乐源修复与BandSplit-RoFormer分离及HiFi++ GAN
Multi-Stage Music Source Restoration with BandSplit-RoFormer Separation and HiFi++ GAN
AI总结：
本文提出多阶段音乐源修复方法，结合BandSplit-RoFormer分离与HiFi++ GAN修复，实现高质量音乐声部恢复。
摘要：
音乐源修复（MSR）旨在从完全混合和母带处理的音频中恢复原始未处理的乐器声部，其中生产效果和分布伪影违反了常见的线性混合假设。本技术报告介绍了CP-JKU团队为2025年MSR ICASSP挑战赛设计的系统。我们的方法将MSR分解为分离和修复两个阶段。首先，一个单通道BandSplit-RoFormer分离器预测八个声部以及一个辅助其他声部，并通过三阶段课程学习进行训练，从4声部预热微调（使用LoRA）逐步扩展到8声部通过头扩展实现。其次，我们应用了一个训练为通用型的HiFi++ GAN波形修复器，然后将其专门化为八个乐器专用专家。
英文摘要：
Music Source Restoration (MSR) targets recovery of original, unprocessed instrument stems from fully mixed and mastered audio, where production effects and distribution artifacts violate common linear-mixture assumptions. This technical report presents the CP-JKU team's system for the MSR ICASSP Challenge 2025. Our approach decomposes MSR into separation and restoration. First, a single BandSplit-RoFormer separator predicts eight stems plus an auxiliary other stem, and is trained with a three-stage curriculum that progresses from 4-stem warm-start fine-tuning (with LoRA) to 8-stem extension via head expansion. Second, we apply a HiFi++ GAN waveform restorer trained as a generalist and then specialized into eight instrument-specific experts.
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。
