← authors · overview

• Continuous speech separation: dataset and analysis
  2020 · 215 citations
• Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  2023 · 112 citations
• Developing RNN-T Models Surpassing High-Performance Hybrid Models with Customization Capability
  2020 · 97 citations
• Serialized Output Training for End-to-End Overlapped Speech Recognition
  2020 · 61 citations
• Internal Language Model Training for Domain-Adaptive End-to-End Speech Recognition
  2021 · 43 citations
• SLM: Bridge the thin gap between speech and text foundation models
  2023 · 28 citations
• Continuous Speech Separation with Ad Hoc Microphone Arrays
  2021 · 27 citations
• High-Accuracy and Low-Latency Speech Recognition with Two-Head Contextual Layer Trajectory LSTM Model
  2020 · 24 citations
• Minimum Word Error Rate Training with Language Model Fusion for End-to-End Speech Recognition
  2021 · 14 citations
• JEIT: Joint End-to-End Model and Internal Language Model Training for Speech Recognition