Thomas Thebaud

Publication Activity (10 Years)

Years Active: 2019-2024
Publications (10 Years): 22

Top Topics

Speaker Verification

Handwritten Digits

Automated Analysis

Top Venues

Publications

Maliha Jahan, Helin Wang, Thomas Thebaud, Yinglun Sun, Giang Ha Le, Zsuzsanna Fagyal, Odette Scharenborg, Mark Hasegawa-Johnson, Laureano Moro-Velázquez, Najim Dehak
Finding Spoken Identifications: Using GPT-4 Annotation for an Efficient and Fast Dataset Creation Pipeline. LREC/COLING (2024)
Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak
Unraveling Adversarial Examples against Speaker Identification - Techniques for Attack Detection and Victim Model Classification. CoRR (2024)
Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak
Unraveling Adversarial Examples against Speaker Identification - Techniques for Attack Detection and Victim Model Classification. Odyssey (2024)
Anna Favaro, Najim Dehak, Thomas Thebaud, Jesús Villalba, Esther S. Oh, Laureano Moro-Velázquez
Discovering Invariant Patterns of Cognitive Decline Via an Automated Analysis of the Cookie Thief Picture Description Task. Odyssey (2024)
Thomas Thebaud, Gabriel Hernández, Sarah Flora Samson Juan, Marie Tahon
A Phonetic Analysis of Speaker Verification Systems through Phoneme selection and Integrated Gradients. Odyssey (2024)
Lucas Goncalves, Ali N. Salman, Abinay Reddy Naini, Laureano Moro-Velázquez, Thomas Thebaud, Paola García, Najim Dehak, Berrak Sisman, Carlos Busso
Odyssey 2024 - Speech Emotion Recognition Challenge: Dataset, Baseline Framework, and Results. Odyssey (2024)
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition. INTERSPEECH (2023)
Martin Sustek, Sonal Joshi, Henry Li, Thomas Thebaud, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks. ASRU (2023)
Anna Favaro, Tianyu Cao, Thomas Thebaud, Jesús Villalba, Ankur Butala, Najim Dehak, Laureano Moro-Velázquez
Do Phonatory Features Display Robustness to Characterize Parkinsonian Speech Across Corpora? INTERSPEECH (2023)
Maliha Jahan, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak, Jesús Villalba
Model-Based Fairness Metric for Speaker Verification. ASRU (2023)
Helin Wang, Thomas Thebaud, Jesús Villalba, Myra Sydnor, Becky Lammers, Najim Dehak, Laureano Moro-Velázquez
DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model. INTERSPEECH (2023)
Thomas Thebaud, Sonal Joshi, Henry Li, Martin Sustek, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
Clustering Unsupervised Representations as Defense Against Poisoning Attacks on Speech Commands Classification System. ASRU (2023)
Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning. CoRR (2023)
Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning. INTERSPEECH (2023)
Amir Hussein, Cihan Xiao, Neha Verma, Thomas Thebaud, Matthew Wiesner, Sanjeev Khudanpur
JHU IWSLT 2023 Dialect Speech Translation System Description. IWSLT@ACL (2023)
Anna Favaro, Yi-Ting Tsai, Ankur Butala, Thomas Thebaud, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
Interpretable speech features vs. DNN embeddings: What to use in the automatic assessment of Parkinson's disease in multi-lingual scenarios. Comput. Biol. Medicine 166 (2023)
Thomas Thebaud, Gaël Le Lan, Anthony Larcher
Spoofing Speaker Verification With Voice Style Transfer And Reconstruction Loss. WIFS (2021)
Pierre Champion, Thomas Thebaud, Gaël Le Lan, Anthony Larcher, Denis Jouvet
On the invertibility of a voice privacy system using embedding alignement. CoRR (2021)
Pierre Champion, Thomas Thebaud, Gaël Le Lan, Anthony Larcher, Denis Jouvet
On the Invertibility of a Voice Privacy System Using Embedding Alignment. ASRU (2021)
Thomas Thebaud, Gaël Le Lan, Anthony Larcher
Handwritten Digits Reconstruction from Unlabelled Embeddings. ICASSP (2021)
Thomas Thebaud, Gaël Le Lan, Anthony Larcher
Unsupervised Labelling of Stolen Handwritten Digit Embeddings with Density Matching. ACNS Workshops (2020)
Etienne Peillard, Thomas Thebaud, Jean-Marie Normand, Ferran Argelaguet, Guillaume Moreau, Anatole Lécuyer
Virtual Objects Look Farther on the Sides: The Anisotropy of Distance Perception in Virtual Reality. VR (2019)