← authors · overview

• Scaling Speech Technology to 1,000+ Languages
  2023 · 116 citations
• Seamless: Multilingual Expressive and Streaming Speech Translation
  2023 · 41 citations
• Self-training and Pre-training are Complementary for Speech Recognition
  2020 · 13 citations
• SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
  2023 · 13 citations
• Speech-to-Speech Translation For A Real-world Unwritten Language
  2022 · 5 citations
• Efficient Monotonic Multihead Attention
  2023 · 5 citations
• Efficient Speech Representation Learning with Low-Bit Quantization
  2023 · 4 citations
• Generative Spoken Dialogue Language Modeling
  2022 · 3 citations
• Continual Learning for On-Device Speech Recognition using Disentangled Conformers
  2022 · 1 citations
• Hybrid Transducer and Attention based Encoder-Decoder Modeling for Speech-to-Text Tasks
  2023 · 1 citations
• Deliberation Model for On-Device Spoken Language Understanding
  2022
• STOP: A dataset for Spoken Task Oriented Semantic Parsing
  2022
• SSR: Alignment-Aware Modality Connector for Speech Language Models
  2024