Michelle Tadmor Ramanovich
Google (United States)(US)
Publications by Year
Research Areas
Speech Recognition and Synthesis, Natural Language Processing Techniques, Topic Modeling, Speech and Audio Processing, Music and Audio Processing
Most-Cited Works
- → AudioPaLM: A Large Language Model That Can Speak and Listen(2023)41 cited
- → CVSS Corpus and Massively Multilingual Speech-to-Speech Translation(2022)23 cited
- → Translatotron 2: High-quality direct speech-to-speech translation with voice preservation(2021)21 cited
- Translatotron 2: Robust direct speech-to-speech translation.(2021)
- → More than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech(2022)13 cited
- → Translatotron 3: Speech to Speech Translation with Monolingual Data(2024)12 cited
- → SimulTron: On-Device Simultaneous Speech to Speech Translation(2025)2 cited
- On-Device and System-Wide Audio Live Captioning with Language Translation(2021)