Rodrigo Mira
Scholar

Rodrigo Mira

Google Scholar ID: 08YfKjcAAAAJ
Google DeepMind
Video-To-SpeechSelf-supervised learningAudio-visual SpeechSpeech enhancement
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
504
 
H-index
8
 
i10-index
8
 
Publications
15
 
Co-authors
13
list available
Contact
No contact links provided.
Publications
5 items
Pay Attention to CTC: Fast and Robust Pseudo-Labelling for Unified Speech Recognition
2026
Cited
0
Lookahead Anchoring: Preserving Character Identity in Audio-Driven Human Animation
2025
Cited
0
KeySync: A Robust Approach for Leakage-free Lip Synchronization in High Resolution
2025
Cited
0
Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction
IEEE International Conference on Acoustics, Speech, and Signal Processing · 2025
Cited
0
KeyFace: Expressive Audio-Driven Facial Animation for Long Sequences via KeyFrame Interpolation
2025
Cited
0
Resume (English only)
Co-authors
13 total
Maja Pantic
Maja Pantic
Natwest Group / Imperial College London
Stavros Petridis
Stavros Petridis
GenAI Research Director, NatWest Group / Research Fellow, Imperial College London
Alexandros Haliassos
Alexandros Haliassos
Meta
Konstantinos Vougioukas
Konstantinos Vougioukas
PhD Student Imperial College London
Björn Schuller
Björn Schuller
Professor, Technische Universität München (TUM) / Imperial College London & CSO, audEERING
Pingchuan Ma
Pingchuan Ma
Meta
Antoni Bigata Casademunt
Antoni Bigata Casademunt
Imperial College London
Nikita Drobyshev
Nikita Drobyshev
Skoltech institute of science and technology