← authors · overview

• Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition
  2020 · 46 citations
• U2++: Unified Two-pass Bidirectional End-to-end Model for Speech Recognition
  2021 · 21 citations
• End-To-End Speech Recognition Using A High Rank LSTM-CTC Based Model
  2019 · 16 citations
• WeNet: Production oriented Streaming and Non-streaming End-to-End Speech Recognition Toolkit
  2021 · 16 citations
• A Domain Adaptation Framework for Speech Recognition Systems with Only Synthetic data
  2025 · 2 citations
• Knowledge Distillation For Recurrent Neural Network Language Modeling With Trust Regularization
  2019 · 1 citations
• SCA: Streaming Cross-attention Alignment for Echo Cancellation
  2022 · 1 citations
• T-Mimi: A Transformer-based Mimi Decoder for Real-Time On-Phone TTS
  2026
• TODM: Train Once Deploy Many Efficient Supernet-Based RNN-T Compression For On-device ASR Models
  2023