 Seeing Through the Conversation: Audio-Visual Speech Separation based on
Diffusion ModelIEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023 |
 A Sparsity-promoting Dictionary Model for Variational AutoencodersInterspeech (Interspeech), 2022 |
 A cappella: Audio-visual Singing Voice SeparationBritish Machine Vision Conference (BMVC), 2021 |
 Mixture of Inference Networks for VAE-based Audio-visual Speech
EnhancementIEEE Transactions on Signal Processing (IEEE Trans. Signal Process.), 2019 |
