FlowTSE: 基于流匹配的目标说话人提取
FlowTSE: Target Speaker Extraction with Flow Matching
AI总结：
针对现有生成式目标说话人提取方法流程复杂、计算开销大的问题，本文提出基于条件流匹配的FlowTSE方法，搭配新型条件声码器优化相位估计，在标准基准上性能达到或超过强基线。
摘要：
目标说话人提取（TSE）旨在以说话人登记音频为参考，从混合语音中分离出特定说话人的语音。现有方法大多为判别式，近年生成式TSE方法取得了不错的效果，但该方向仍有待充分探索，且多数现有方法依赖复杂流程与预训练组件，带来了计算开销。本文提出FlowTSE，这是一种基于条件流匹配的简单高效的TSE方法。模型以梅尔频谱图形式接收登记音频样本与混合语音信号，目标是提取目标说话人的干净语音。此外，针对相位重建至关重要的任务，我们提出了一种以混合信号的复短时傅里叶变换（STFT）为条件的新型声码器，可优化相位估计。在标准TSE基准上的实验结果表明，FlowTSE的性能与强基线相当甚至更优。
英文摘要：
Target speaker extraction (TSE) aims to isolate a specific speaker's speech from a mixture using speaker enrollment as a reference. While most existing approaches are discriminative, recent generative methods for TSE achieve strong results. However, generative methods for TSE remain underexplored, with most existing approaches relying on complex pipelines and pretrained components, leading to computational overhead. In this work, we present FlowTSE, a simple yet effective TSE approach based on conditional flow matching. Our model receives an enrollment audio sample and a mixed speech signal, both represented as mel-spectrograms, with the objective of extracting the target speaker's clean speech. Furthermore, for tasks where phase reconstruction is crucial, we propose a novel vocoder conditioned on the complex STFT of the mixed signal, enabling improved phase estimation. Experimental results on standard TSE benchmarks show that FlowTSE matches or outperforms strong baselines.
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。
