← authors · overview

• A Streaming On-Device End-to-End Model Surpassing Server-Side Conventional Model Quality and Latency
  2020 · 202 citations
• Towards Fast and Accurate Streaming End-to-End ASR
  2020 · 113 citations
• Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  2023 · 112 citations
• Transformer Based Deliberation for Two-Pass Speech Recognition
  2021 · 24 citations
• Efficient Domain Adaptation for Speech Foundation Models
  2023 · 19 citations
• Massively Multilingual Shallow Fusion with Large Language Models
  2023 · 14 citations
• Input Length Matters: Improving RNN-T and MWER Training for Long-form Telephony Speech Recognition
  2021 · 10 citations
• A Language Agnostic Multilingual Streaming On-Device ASR System
  2022 · 10 citations
• Improving Deliberation by Text-Only and Semi-Supervised Training
  2022 · 7 citations
• UML: A Universal Monolingual Output Layer for Multilingual ASR
  2023 · 5 citations
• Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device
  2021 · 4 citations
• A Better and Faster End-to-End Model for Streaming ASR
  2020 · 2 citations
• Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR
  2022 · 1 citations
• JOIST: A Joint Speech and Text Streaming Model For ASR
  2022 · 1 citations
• Less Is More: Improved RNN-T Decoding Using Limited Label Context and Path Merging
  2020