← authors · overview

• From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition
  2019 · 73 citations
• Transformer-Transducer: End-to-End Speech Recognition with Self-Attention
  2019 · 66 citations
• Dissecting User-Perceived Latency of On-Device E2E Speech Recognition
  2021 · 26 citations
• Emformer: Efficient Memory Transformer Based Acoustic Model For Low Latency Streaming Speech Recognition
  2020 · 13 citations
• Weak-Attention Suppression For Transformer Based Speech Recognition
  2020 · 5 citations
• Semantic Distance: A New Metric for ASR Performance Analysis Towards Spoken Language Understanding
  2021 · 5 citations
• Contextualized Streaming End-to-End Speech Recognition with Trie-Based Deep Biasing and Shallow Fusion
  2021 · 3 citations
• G2G: TTS-Driven Pronunciation Learning for Graphemic Hybrid ASR
  2019 · 1 citations
• Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer
  2020 · 1 citations
• Improving RNN Transducer Based ASR with Auxiliary Tasks
  2020 · 1 citations
• Deep Shallow Fusion for RNN-T Personalization
  2020 · 1 citations
• Dynamic Encoder Transducer: A Flexible Solution For Trading Off Accuracy For Latency
  2021