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.

翻译：音乐源修复（MSR）旨在从完全混音和母带处理后的音频中恢复原始、未经处理的乐器音轨，其中制作效果与发行伪影违背了常见的线性混合假设。本技术报告介绍了CP-JKU团队为ICASSP 2025 MSR挑战赛设计的系统。我们的方法将MSR分解为分离与修复两个阶段。首先，采用单一的BandSplit-RoFormer分离器预测八个音轨及一个辅助的“其他”音轨，并通过三阶段课程学习进行训练：从基于LoRA的4音轨热启动微调开始，逐步通过头部扩展过渡到8音轨分离。其次，我们应用一个先训练为通用模型、再针对八种乐器专门化的HiFi++ GAN波形修复器作为专家系统。