Scholar
Thomas Thebaud
Google Scholar ID: 5wgj-vYAAAAJ
Assistant Research Scientist, ECE Dept., Johns Hopkins University, Baltimore
Adversarial and Backdoor attacks
Speech Emotion Recognition
Audio LLMs
Speaker Characterisation
Follow
Google Scholar
↗
Citations & Impact
All-time
Citations
305
H-index
8
i10-index
7
Publications
20
Co-authors
13
list available
Contact
No contact links provided.
Publications
27 items
Who Are They to Each Other? Multi-Agent Reasoning for Speaker Relationship Inference
2026
Cited
0
When Text Misleads: Inconsistent-Aware Reasoning for Audio-Grounded Dialogue
2026
Cited
0
SPEARBench: A Benchmark for Naturalness Evaluation in Streaming Speech-to-Speech Language Models
2026
Cited
0
ProPS: Prompted Profile Synthesis for Natural Language-Conditioned Speaker Embedding Distributions
2026
Cited
0
TurnNat: Automatic Evaluation of Turn-Taking Naturalness in Dyadic Spoken Dialogue
2026
Cited
0
Reference-Based Prosody and Rhythm Evaluation for Spoken Dialogue Systems
2026
Cited
0
TRACE: Temporal Relationship-Aware Conversational Entrainment Detection in Dyadic Speech
2026
Cited
0
Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System
2026
Cited
0
Load more
Resume (English only)
Co-authors
13 total
Najim Dehak
Associate Professor at ECE department, Johns Hopkins University.
Co-author 2
Jesús Villalba
Johns Hopkins University
Co-author 4
Ankur Butala MD
Johns Hopkins University School of Medicine
Co-author 6
Anthony Larcher
Professor Le Mans Université
Gaël Le Lan
Meta Reality Labs