Thomas Thebaud

According to our database, Thomas Thebaud authored at least 14 papers between 2019 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

Unraveling Adversarial Examples against Speaker Identification - Techniques for Attack Detection and Victim Model Classification.

Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak

CoRR, 2024

2023

Interpretable speech features vs. DNN embeddings: What to use in the automatic assessment of Parkinson's disease in multi-lingual scenarios.

Anna Favaro, Yi-Ting Tsai, Ankur Butala, Thomas Thebaud, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez

Comput. Biol. Medicine, November, 2023

Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning.

Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak

CoRR, 2023

JHU IWSLT 2023 Dialect Speech Translation System Description.

Amir Hussein, Cihan Xiao, Neha Verma, Thomas Thebaud, Matthew Wiesner, Sanjeev Khudanpur

Proceedings of the 20th International Conference on Spoken Language Translation, 2023

Clustering Unsupervised Representations as Defense Against Poisoning Attacks on Speech Commands Classification System.

Thomas Thebaud, Sonal Joshi, Henry Li, Martin Sustek, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks.

Martin Sustek, Sonal Joshi, Henry Li, Thomas Thebaud, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

Model-Based Fairness Metric for Speaker Verification.

Maliha Jahan, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak, Jesús Villalba

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2023

2022

Attaques par reconstruction de données biométriques comportementales à l'aide d'alignements d'embeddings. (Spoofing attacks using behavioural biometric data reconstruction and statistical alignments).

Thomas Thebaud

PhD thesis, 2022

2021

On the invertibility of a voice privacy system using embedding alignement.

Pierre Champion, Thomas Thebaud, Gaël Le Lan, Anthony Larcher, Denis Jouvet

CoRR, 2021

Spoofing Speaker Verification With Voice Style Transfer And Reconstruction Loss.

Thomas Thebaud, Gaël Le Lan, Anthony Larcher

Proceedings of the IEEE International Workshop on Information Forensics and Security, 2021

Handwritten Digits Reconstruction from Unlabelled Embeddings.

Thomas Thebaud, Gaël Le Lan, Anthony Larcher

Proceedings of the IEEE International Conference on Acoustics, 2021

On the Invertibility of a Voice Privacy System Using Embedding Alignment.

Pierre Champion, Thomas Thebaud, Gaël Le Lan, Anthony Larcher, Denis Jouvet

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

2020

Unsupervised Labelling of Stolen Handwritten Digit Embeddings with Density Matching.

Thomas Thebaud, Gaël Le Lan, Anthony Larcher

Proceedings of the Applied Cryptography and Network Security Workshops, 2020

2019

Virtual Objects Look Farther on the Sides: The Anisotropy of Distance Perception in Virtual Reality.

Etienne Peillard, Thomas Thebaud, Jean-Marie Normand, Ferran Argelaguet, Guillaume Moreau, Anatole Lécuyer

Proceedings of the IEEE Conference on Virtual Reality and 3D User Interfaces, 2019