Picture for Shilong Wu

Shilong Wu

Neural Speaker Diarization Using Memory-Aware Multi-Speaker Embedding with Sequence-to-Sequence Architecture

Add code
Sep 17, 2023
Viaarxiv icon

The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction

Add code
Sep 15, 2023
Viaarxiv icon

The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge

Add code
Aug 28, 2023
Viaarxiv icon

Semi-supervised multi-channel speaker diarization with cross-channel attention

Add code
Jul 17, 2023
Viaarxiv icon