← authors · overview

• Large-Scale Multilingual Speech Recognition with a Streaming End-to-End Model
  2019 · 158 citations
• Google USM: Scaling Automatic Speech Recognition Beyond 100 Languages
  2023 · 112 citations
• MAESTRO: Matched Speech Text Representations through Modality Matching
  2022 · 71 citations
• mSLAM: Massively multilingual joint pre-training for speech and text
  2022 · 59 citations
• SLAM: A Unified Encoder for Speech and Language Modeling via Speech-Text Joint Pre-Training
  2021 · 50 citations
• AudioPaLM: A Large Language Model That Can Speak and Listen
  2023 · 41 citations
• Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation
  2022 · 15 citations
• FLEURS: Few-shot Learning Evaluation of Universal Representations of Speech
  2022 · 15 citations
• Mu$^2$SLAM: Multitask, Multilingual Speech and Language Models
  2022 · 5 citations
• Understanding Shared Speech-Text Representations