← People

Yifan Ding

Source-listed: Software Engineer on behalf of the Gemini team · Google DeepMind

  • Multimodal AI
  • Speech and audio

Selected work

5
  1. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextAuthor · 2024
  2. Translatotron 3: Speech to Speech Translation with Monolingual DataContributor · 2024
  3. SimulTron: On-Device Simultaneous Speech to Speech TranslationContributor · 2025
  4. Miipher: A Robust Speech Restoration Model Integrating Self-Supervised Speech and Text RepresentationsContributor · 2023
  5. LibriTTS-R: Restoration of a Large-Scale Multi-Speaker TTS CorpusContributor · 2023