Showing eess.ASShow all
2 papers · 1 filter
eess.AS2026
REDnet: Recursive Encoder and Decoder for Speech Separation under Unknown Number of Speakers and Variable Number of Microphones
Fulin Wu, Zhong-Qiu Wang
We propose (RED) for building a single deep neural network (DNN) model that can separate multi-speaker mixtures containing unknown numbers…
eess.AS2026
ARTT: Augmented Reverberant-Target Training for Unsupervised Monaural Speech Dereverberation
Siqi Song, Fulin Wu, Zhong-Qiu Wang
Due to the absence of clean reference signals and spatial cues, monaural unsupervised speech dereverberation is a challenging ill-posed inverse problem. To realize it, we propose a…