@inproceedings{801d21e4a9924af3b94ad8b0b964c70a,
title = "ConSep: a Noise- and Reverberation-Robust Speech Separation Framework by Magnitude Conditioning",
abstract = "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 BiSep. Furthermore, we visualize the components of ConSep to strengthen the advantages and cohere with the actualities we have found in preliminary studies.",
keywords = "conditioning, cross-domain, magnitude, multi-resolution, reverberation, speech separation",
author = "Ho, {Kuan Hsun} and Hung, {Jeih Weih} and Berlin Chen",
note = "Publisher Copyright: {\textcopyright} 2023 IEEE. ; 24th International Conference on Digital Signal Processing, DSP 2023 ; Conference date: 11-06-2023 Through 13-06-2023",
year = "2023",
doi = "10.1109/DSP58604.2023.10167992",
language = "English",
series = "International Conference on Digital Signal Processing, DSP",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "2023 24th International Conference on Digital Signal Processing, DSP 2023",
}