← authors · overview

• USTC-NELSLIP System Description for DIHARD-III Challenge
  2021 · 20 citations
• Improved Speech Pre-Training with Supervision-Enhanced Acoustic Unit
  2022 · 1 citations
• The Multimodal Information Based Speech Processing (MISP) 2023 Challenge: Audio-Visual Target Speaker Extraction
  2023 · 1 citations
• DCF-DS: Deep Cascade Fusion of Diarization and Separation for Speech Recognition under Realistic Single-Channel Conditions
  2024 · 1 citations
• The USTC-NERCSLIP Systems for the CHiME-9 MCoRec Challenge
  2026
• Self-Supervised Audio-Visual Speech Representations Learning By Multimodal Self-Distillation
  2022
• Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information
  2022
• Progressive Multi-Scale Self-Supervised Learning for Speech Recognition
  2022
• Reducing the gap between streaming and non-streaming Transducer-based ASR by adaptive two-stage knowledge distillation
  2023
• The USTC-NERCSLIP Systems for the CHiME-7 DASR Challenge
  2023
• A Variance-Preserving Interpolation Approach for Diffusion Models with Applications to Single Channel Speech Enhancement and Recognition
  2024
• The USTC-NERCSLIP Systems for the CHiME-8 NOTSOFAR-1 Challenge
  2024
• Incorporating Spatial Cues in Modular Speaker Diarization for Multi-channel Multi-party Meetings
  2024