← authors · overview

• Recent Developments on ESPnet Toolkit Boosted by Conformer
  2020 · 40 citations
• Continuous Speech Separation Using Speaker Inventory for Long Multi-talker Recording
  2020 · 6 citations
• The 2020 ESPnet update: new features, broadened applications, performance improvements, and future plans
  2020 · 6 citations
• Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions
  2021 · 5 citations
• Rethinking the Separation Layers in Speech Separation Networks
  2020 · 3 citations
• Efficient Multilingual ASR Finetuning via LoRA Language Experts
  2025 · 2 citations
• Interspeech 2025 URGENT Speech Enhancement Challenge
  2025 · 2 citations
• Adapting Multi-Lingual ASR Models for Handling Multiple Talkers
  2023 · 1 citations
• P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge
  2025
• URGENT-PK: Perceptually-Aligned Ranking Model Designed for Speech Enhancement Competition
  2025
• Dual-Path Modeling for Long Recording Speech Separation in Meetings
  2021
• Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge
  2022
• SpeechComposer: Unifying Multiple Speech Tasks with Prompt Composition
  2024