no code implementations • 23 Jan 2024 • Younglo Lee, Shukjae Choi, Byeong-Yeol Kim, Zhong-Qiu Wang, Shinji Watanabe
We propose a novel speech separation model designed to separate mixtures with an unknown number of speakers.
Ranked #1 on Speech Separation on WSJ0-5mix
no code implementations • 18 Apr 2023 • Zhong-Qiu Wang, Samuele Cornell, Shukjae Choi, Younglo Lee, Byeong-Yeol Kim, Shinji Watanabe
We propose FSB-LSTM, a novel long short-term memory (LSTM) based architecture that integrates full- and sub-band (FSB) modeling, for single- and multi-channel speech enhancement in the short-time Fourier transform (STFT) domain.