← authors · overview

• A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
  2020 · 202 citations
• On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition
  2016 · 85 citations
• Phoneme-Based Contextualization for Cross-Lingual Speech Recognition in End-to-End Models
  2019 · 7 citations
• Neural-FST Class Language Model for End-to-End Speech Recognition
  2022 · 3 citations
• Improved Neural Language Model Fusion for Streaming Recurrent Neural Network Transducer
  2020 · 1 citations
• NN-grams: Unifying neural network and n-gram language models for Speech Recognition
  2016
• Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition Models
  2023
• Partial Rewriting for Multi-Stage ASR
  2023