CrossNet：利用全局、跨频带、窄带及位置编码实现单通道与多通道说话人分离
CrossNet: Leveraging Global, Cross-Band, Narrow-Band, and Positional Encoding for Single- and Multi-Channel Speaker Separation
AI总结：
本研究提出用于说话人分离的CrossNet复频谱映射架构，融合多维度时频相关性与随机块位置编码，在多场景任务上达SOTA，训练更高效且适配多麦克风场景。
摘要：
我们提出CrossNet，这是一种用于混响及噪声环境下说话人分离与增强的复频谱映射方法。该架构包含编码器层、全局多头自注意力模块、跨频带模块、窄带模块以及输出层，可捕捉时频域内的全局、跨频带和窄带相关性。为解决长语音性能下降问题，我们引入了随机块位置编码。在多个数据集上的实验结果表明，CrossNet具备有效性与鲁棒性，在混响及噪声混响说话人分离等任务上达到了SOTA（当前最优）性能。此外，与近期基线模型相比，它的训练速度更快、过程更稳定，且高性能可拓展至多麦克风场景，展现出在各类声学场景下的通用性。
英文摘要：
We introduce CrossNet, a complex spectral mapping approach to speaker separation and enhancement in reverberant and noisy conditions. The proposed architecture comprises an encoder layer, a global multi-head self-attention module, a cross-band module, a narrow-band module, and an output layer. CrossNet captures global, cross-band, and narrow-band correlations in the time-frequency domain. To address performance degradation in long utterances, we introduce a random chunk positional encoding. Experimental results on multiple datasets demonstrate the effectiveness and robustness of CrossNet, achieving state-of-the-art performance in tasks including reverberant and noisy-reverberant speaker separation. Furthermore, CrossNet exhibits faster and more stable training in comparison to recent baselines. Additionally, CrossNet's high performance extends to multi-microphone conditions, demonstrating its versatility in various acoustic scenarios.
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。
