Scholar

Thomas Pellegrini

Google Scholar ID: 5FvYex4AAAAJ

Lecturer, University of Toulouse, IRIT

Automatic speech and audio processing

Homepage↗Google Scholar↗

Citations & Impact

All-time

Citations

1,702

H-index

24

i10-index

52

Publications

20

Co-authors

8

list available

Publications

3 items

BEST-RQ-2: Contextualize-Then-Predict, a Two-Step Approach for Self-Supervised Audio Representations

2026

Cited

0

Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging

IEEE International Conference on Acoustics, Speech, and Signal Processing · 2025

Cited

0

Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning

Interspeech · 2024

Cited

1

Co-authors

4 total

Isabel Trancoso

INESC-ID / IST / University of Lisbon

INESC-ID, Instituto Superior Técnico, University of Lisbon, Portugal

Timothée Masquelier

CNRS Research Director (DR2), Cerco (CNRS-UT3), TMBI (Univ. Toulouse)

Philippe Muller

Professor (Computer Science), University of Toulouse, IRIT, ANITI member, TMBI