Picture for Genshun Wan

Genshun Wan

Deep CLAS: Deep Contextual Listen, Attend and Spell

Add code
Sep 26, 2024
Viaarxiv icon

The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge

Add code
Sep 03, 2024
Figure 1 for The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
Figure 2 for The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
Figure 3 for The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
Figure 4 for The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
Viaarxiv icon

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

Add code
Aug 28, 2023
Figure 1 for The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
Figure 2 for The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
Figure 3 for The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
Figure 4 for The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
Viaarxiv icon

Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation

Add code
Jun 27, 2023
Viaarxiv icon

Improved Speech Pre-Training with Supervision-Enhanced Acoustic Unit

Add code
Dec 07, 2022
Viaarxiv icon

Progressive Multi-Scale Self-Supervised Learning for Speech Recognition

Add code
Dec 07, 2022
Viaarxiv icon

Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information

Add code
Dec 07, 2022
Viaarxiv icon

Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation

Add code
Dec 06, 2022
Viaarxiv icon