← authors · overview

• A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
  2020 · 202 citations
• Personalized Speech recognition on mobile devices
  2016 · 164 citations
• On the Compression of Recurrent Neural Networks with an Application to LVCSR acoustic modeling for Embedded Speech Recognition
  2016 · 85 citations
• Optimizing Speech Recognition For The Edge
  2019 · 58 citations
• Streaming End-to-end Speech Recognition For Mobile Devices
  2018 · 23 citations
• Two-Pass End-to-End Speech Recognition
  2019 · 13 citations
• Analyzing the Quality and Stability of a Streaming End-to-End On-Device Speech Recognizer
  2020 · 11 citations
• Multi-user VoiceFilter-Lite via Attentive Speaker Embedding
  2021 · 5 citations
• Closing the Gap between Single-User and Multi-User VoiceFilter-Lite
  2022 · 3 citations