We introduce UNMIXX, a novel framework for multiple singing voices separation (MSVS). While related to speech separation, MSVS faces unique challenges: data scarcity and the highly correlated nature of singing voices mixture. To address these issues, we propose UNMIXX with three key components: (1) musically informed mixing strategy to construct highly correlated, music-like mixtures, (2) cross-source attention that drives representations of two singers apart via reverse attention, and (3) magnitude penalty loss penalizing erroneously assigned interfering energy. UNMIXX not only addresses data scarcity by simulating realistic training data, but also excels at separating highly correlated mixtures through cross-source interactions at both the architectural and loss levels. Our extensive experiments demonstrate that UNMIXX greatly enhances performance, with SDRi gains exceeding 2.2 dB over prior work.

翻译：本文提出UNMIXX，一种用于多人歌声分离的新型框架。尽管与语音分离相关，但多人歌声分离面临独特挑战：数据稀缺性以及歌声混合的高度相关性。为解决这些问题，我们提出UNMIXX，其包含三个关键组件：(1) 基于音乐知识的混合策略，用于构建高度相关、音乐化的混合信号；(2) 跨源注意力机制，通过反向注意力驱动两位歌手的表征分离；(3) 幅度惩罚损失，对错误分配的干扰能量进行惩罚。UNMIXX不仅通过模拟真实训练数据解决了数据稀缺问题，更通过在架构和损失层面的跨源交互机制，擅长分离高度相关的混合信号。我们的大量实验表明，UNMIXX显著提升了分离性能，其SDRi增益较先前工作超过2.2 dB。