← authors · overview

• Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  2023 · 112 citations
• An Investigation Into On-device Personalization of End-to-end Automatic Speech Recognition Models
  2019 · 22 citations
• Mobile Keyboard Input Decoding with Finite-State Transducers
  2017 · 21 citations
• On-Device Personalization of Automatic Speech Recognition Models for Disordered Speech
  2021 · 12 citations
• Incremental Layer-wise Self-Supervised Learning for Efficient Speech Domain Adaptation On Device
  2021 · 4 citations
• Partial Variable Training for Efficient On-Device Federated Learning
  2021 · 4 citations
• A Method to Reveal Speaker Identity in Distributed ASR Training, and How to Counter It
  2021 · 1 citations
• Exploring Heterogeneous Characteristics of Layers in ASR Models for More Efficient Training
  2021 · 1 citations
• Federated Pruning: Improving Neural Network Efficiency with Federated Learning
  2022 · 1 citations
• BigSSL: Exploring the Frontier of Large-Scale Semi-Supervised Learning for Automatic Speech Recognition
  2021
• Fast Contextual Adaptation with Neural Associative Memory for On-Device Personalized Speech Recognition
  2021
• Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
  2023
• Improving Speech Recognition for African American English With Audio Classification
  2023
• Extending Multilingual Speech Synthesis to 100+ Languages without Transcribed Data
  2024