DTT-BSR: 基于GAN的DTTNet与RoPE变换器增强的音乐源恢复
DTT-BSR: GAN-based DTTNet with RoPE Transformer Enhancement for Music Source Restoration
AI总结:
DTT-BSR通过结合RoPE变换器和双路径RNN,提升音乐源恢复的生成保真度和语义对齐,实现高效高精度的信号重建。
摘要:
音乐源恢复(MSR)旨在从混音和 mastering 录制中恢复未经处理的声部。挑战在于既要分离重叠的声源,又要重建受压缩和混响等生产效果退化的信号。为此,我们提出了DTT-BSR,一种结合旋转位置嵌入(RoPE)变换器的生成对抗网络(GAN),用于长期时间建模,以及双路径带分割递归神经网络(RNN)用于多分辨率频谱处理。我们的模型在ICASSP 2026 MSR挑战赛中取得了客观排行榜第三名和主观排行榜第四名,证明了其出色的生成保真度和与紧凑参数规模(7.1M)的语义对齐。
英文摘要:
Music source restoration (MSR) aims to recover unprocessed stems from mixed and mastered recordings. The challenge lies in both separating overlapping sources and reconstructing signals degraded by production effects such as compression and reverberation. We therefore propose DTT-BSR, a hybrid generative adversarial network (GAN) combining rotary positional embeddings (RoPE) transformer for long-term temporal modeling with dual-path band-split recurrent neural network (RNN) for multi-resolution spectral processing. Our model achieved 3rd place on the objective leaderboard and 4th place on the subjective leaderboard on the ICASSP 2026 MSR Challenge, demonstrating exceptional generation fidelity and semantic alignment with a compact size of 7.1M parameters.
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。