← People

Soroosh Mariooryad

Source-listed: Staff Research Scientist · Google DeepMind

  • Multimodal AI
  • Language models
  • Speech and audio

Selected work

5
  1. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextContributor · 2024
  2. Zero-Shot Mono-to-Binaural Speech SynthesisContributor · 2025
  3. Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMContributor · 2024
  4. Speaker GenerationContributor · 2022
  5. Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesisContributor · 2021