Soroosh Mariooryad
Source-listed: Staff Research Scientist · Google DeepMind
- Multimodal AI
- Language models
- Speech and audio
Selected work
5- Gemini 1.5: Unlocking multimodal understanding across millions of tokens of contextContributor · 2024
- Zero-Shot Mono-to-Binaural Speech SynthesisContributor · 2025
- Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLMContributor · 2024
- Speaker GenerationContributor · 2022
- Wave-Tacotron: Spectrogram-free end-to-end text-to-speech synthesisContributor · 2021