Multimodal

Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement
Recent studies have increasingly acknowledged the advantages of incorporating visual data into speech enhancement (SE) systems. We …
Shafique Ahmed, Chia-Wei Chen, Wenze Ren, Li, Chin-Jou, Ernie Chu, Jun-Cheng Chen, Amir Hussain, Hsin-Min Wang, Yu Tsao, Jen-Cheng Hou
PDF DOI
Deep Complex U-Net with Conformer for Audio-Visual Speech Enhancement
EGO4D Audio-Visual Speaker Diarization Challenge 2023
Utilized self-supervised embeddings and people tracking algorithms to identify who and where the speakers are in egocentric videos.
PDF
EGO4D Audio-Visual Speaker Diarization Challenge 2023
1st COG-MHEAR AVSE Challenge
A DCCRN-based Audio-visual Speech Enhancement Approach. Ranked 3rd place.
PDF
1st COG-MHEAR AVSE Challenge