ConSep：一种通过幅度条件化实现的抗噪声与混响语音分离框架
ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning
AI总结：
本文提出幅度条件化时域框架 ConSep，融合 STFT 特征优势，在无回声、噪声和混响条件下优于 SepFormer 与 Bi-Sep，并通过组件可视化验证其机理。
摘要：
语音分离近来得益于时域方法中采用的细粒度视角而取得了显著进展。然而，多项研究表明，在遇到噪声或混响等更恶劣条件时，采用短时傅里叶变换（STFT）进行特征提取可能是有益的。因此，我们提出一种幅度条件化的时域框架 ConSep，以继承这些有益特性。实验表明，与两种著名方法 SepFormer 和 Bi-Sep 相比，ConSep 在无回声、含噪和混响环境中提升了性能。此外，我们对 ConSep 的组件进行可视化，以强化其优势，并与我们在初步研究中发现的实际情况保持一致。
英文摘要：
Speech separation has recently made significant progress thanks to the fine-grained vision used in time-domain methods. However, several studies have shown that adopting Short-Time Fourier Transform (STFT) for feature extraction could be beneficial when encountering harsher conditions, such as noise or reverberation. Therefore, we propose a magnitude-conditioned time-domain framework, ConSep, to inherit the beneficial characteristics. The experiment shows that ConSep promotes performance in anechoic, noisy, and reverberant settings compared to two celebrated methods, SepFormer and Bi-Sep. Furthermore, we visualize the components of ConSep to strengthen the advantages and cohere with the actualities we have found in preliminary studies.
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。
