Scholar
Thomas Rolland
Google Scholar ID: -TeQwvAAAAAJ
INESC-ID
ASR
PEFT
Speech Processing
TTS
Machine learming
Follow
Homepage
↗
Google Scholar
↗
Citations & Impact
All-time
Citations
152
H-index
7
i10-index
5
Publications
15
Co-authors
0
Contact
Email
trolland@protonmail.ch
CV
Open ↗
GitHub
Open ↗
LinkedIn
Open ↗
Publications
4 items
Exploring the potential and limitations of Model Merging for Multi-Domain Adaptation in ASR
2026
Cited
0
CAMÕES: A Comprehensive Automatic Speech Recognition Benchmark for European Portuguese
2025
Cited
0
Children's Voice Privacy: First Steps And Emerging Challenges
2025
Cited
0
Tackling Cognitive Impairment Detection from Speech: A submission to the PROCESS Challenge
2024
Cited
0
Resume (English only)
Research Experience
Postdoctoral Researcher at INESC-ID (Lisbon), working on parameter-efficient Transformers and speech technologies.
Developed state-of-the-art ASR systems for European Portuguese and created CAMÕES, a comprehensive ASR evaluation benchmark.
Led the 'ASR Arena' project to identify top-performing ASR models.
Conducted the 'Children's speech data in the wild' project to collect diverse real-world children's speech for testing.
Researched the Looped-Transformer, a parameter-efficient Transformer variant using loop mechanisms.
Co-authors
0 total
Co-authors: 0 (list not available)
×
Welcome back
Sign in to Agora
Welcome back! Please sign in to continue.
Email address
Password
Forgot password?
Continue
Do not have an account?
Sign up