用两阶段Mamba-2网络提升音乐分离效果
A Two-Stage Band-Split Mamba-2 Network For Music Separation
- 分频段两阶段处理，引入基于掩码的残差映射
- 在MUSDB18数据集上达到SDR 10.39，优于基线模型
- 适合音频分离、时序建模方向的研究者参考
音乐源分离（MSS）旨在将混合音乐分解为独立音轨，如人声、贝斯、鼓等。由于音乐信号复杂，该任务极具挑战性。尽管RNN和Transformer广泛用于建模音乐序列，但仍有局限。最近，Mamba-2在多种序列建模任务中表现出高效率，但在MSS中尚未被充分探索。本文提出一种两阶段分频段的Mamba-2网络，通过基于掩码的残差映射，有效弥补掩码缺失的细节，进一步提升分离性能。实验验证了双向Mamba-2及两阶段结构在MSS中的优越性。源代码已公开于https://github.com/baijinglin/TS-BSmamba2。
原文摘要 · Abstract (English)
Music source separation (MSS) aims to separate mixed music into its distinct tracks, such as vocals, bass, drums, and more. MSS is considered to be a challenging audio separation task due to the complexity of music signals. Although the RNN and Transformer architecture are not perfect, they are commonly used to model the music sequence for MSS. Recently, Mamba-2 has already demonstrated high efficiency in various sequential modeling tasks, but its superiority has not been investigated in MSS. This paper applies Mamba-2 with a two-stage strategy, which introduces residual mapping based on the mask method, effectively compensating for the details absent in the mask and further improving separation performance. Experiments confirm the superiority of bidirectional Mamba-2 and the effectiveness of the two-stage network in MSS. The source code is publicly accessible at https://github.com/baijinglin/TS-BSmamba2.
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。