Thomas Thebaud

60 papers A* 3A 9B 1C 6Misc 4Journal 27Unranked 9
YearRankTypeTitle / Venue / Authors
2026 J jnl
Can LLMs Help Localize Fake Words in Partially Fake Speech?
CoRR
Lin Zhang, Thomas Thebaud, Zexin Cai, Sanjeev Khudanpur, Daniel Povey, Leibny Paola García-Perera, Matthew Wiesner, Nicholas Andrews
2026 J jnl
DiT-Flow: Speech Enhancement Robust to Multiple Distortions based on Flow Matching in Latent Space and Diffusion Transformers.
CoRR
Tianyu Cao, Helin Wang, Ari Frummer, Yuval Sieradzki, Adi Arbel, Laureano Moro-Velázquez, Jesús Villalba, Oren Gal, Thomas Thebaud, Najim Dehak
2026 J jnl
Reconstruct! Don't Encode: Self-Supervised Representation Reconstruction Loss for High-Intelligibility and Low-Latency Streaming Neural Audio Codec.
CoRR
Junhyeok Lee, Xiluo He, Jihwan Lee, Helin Wang, Shrikanth Narayanan, Thomas Thebaud, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2026 J jnl
Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation.
CoRR
Thomas Thebaud, Yuzhe Wang, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2025 J jnl
Backdoor Attacks Against Speech Language Models.
CoRR
Alexandrine Fortier, Thomas Thebaud, Jesús Villalba, Najim Dehak, Patrick Cardinal
2025 J jnl
Cross-Corpus and Cross-domain Handwriting Assessment of NeuroDegenerative Diseases via Time-Series-to-Image Conversion.
CoRR
Gabriel Chávez, Laureano Moro-Velázquez, Ankur A. Butala, Najim Dehak, Thomas Thebaud
2025 Misc conf
Demographic Attributes Prediction from Speech Using WavLM Embeddings.
CISS
Yuchen Yang, Thomas Thebaud, Najim Dehak
2025 J jnl
Demographic Attributes Prediction from Speech Using WavLM Embeddings.
CoRR
Yuchen Yang, Thomas Thebaud, Najim Dehak
2025 Misc conf
Detecting Neurodegenerative Diseases using Frame-Level Handwriting Embeddings.
ICASSP
Sarah Laouedj, Yuzhe Wang, Jesús Villalba, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak
2025 J jnl
Detecting Neurodegenerative Diseases using Frame-Level Handwriting Embeddings.
CoRR
Sarah Laouedj, Yuzhe Wang, Jesús Villalba, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak
2025 C conf
Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM.
ASRU
Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner, Peter Viechnicki, Najim Dehak
2025 J jnl
Enhancing Dialogue Annotation with Speaker Characteristics Leveraging a Frozen LLM.
CoRR
Thomas Thebaud, Yen-Ju Lu, Matthew Wiesner, Peter Viechnicki, Najim Dehak
2025 A conf
FaiST: A Benchmark Dataset for Fairness in Speech Technology.
INTERSPEECH
Maliha Jahan, Yinglun Sun, Priyam Mazumdar, Zsuzsanna Fagyal, Thomas Thebaud, Jesús Villalba, Mark Hasegawa-Johnson, Najim Dehak, Laureano Moro-Velázquez
2025 J jnl
Joint Diarization and Separation Using SepFormer With Non-Autoregressive Attractors.
IEEE Signal Process. Lett.
Magdalena Rybicka, Konrad Kowalczyk, Thomas Thebaud, Najim Dehak, Jesús Villalba
2025 J jnl
MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances.
CoRR
Junhyeok Lee, Helin Wang, Yaohan Guan, Thomas Thebaud, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2025 C conf
Multi-Target Backdoor Attacks Against Speaker Recognition.
ASRU
Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, Jesús Antonio Villalba López, Najim Dehak, Patrick Cardinal
2025 J jnl
Multi-Target Backdoor Attacks Against Speaker Recognition.
CoRR
Alexandrine Fortier, Sonal Joshi, Thomas Thebaud, Jesús Antonio Villalba López, Najim Dehak, Patrick Cardinal
2025 A conf
Multimodal Emotion Diarization: Frame-Wise Integration of Text and Audio Representations.
INTERSPEECH
Ziv Tamir, Thomas Thebaud, Jesús Villalba, Najim Dehak, Oren Kurland
2025 A* conf
Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation.
EMNLP
Yen-Ju Lu, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak, Jesús Villalba
2025 J jnl
Paired by the Teacher: Turning Unpaired Data into High-Fidelity Pairs for Low-Resource Text Generation.
CoRR
Yen-Ju Lu, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak, Jesús Villalba
2025 J jnl
ReFESS-QI: Reference-Free Evaluation For Speech Separation With Joint Quality And Intelligibility Scoring.
CoRR
Ari Frummer, Helin Wang, Tianyu Cao, Adi Arbel, Yuval Sieradzki, Oren Gal, Jesús Villalba, Thomas Thebaud, Najim Dehak
2025 J jnl
Scaling Multi-Talker ASR with Speaker-Agnostic Activity Streams.
CoRR
Xiluo He, Alexander Polok, Jesús Villalba, Thomas Thebaud, Matthew Maciejewski
2025 J jnl
SoloSpeech: Enhancing Intelligibility and Quality in Target Speech Extraction through a Cascaded Generative Pipeline.
CoRR
Helin Wang, Jiarui Hai, Dongchao Yang, Chen Chen, Kai Li, Junyi Peng, Thomas Thebaud, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
2025 J jnl
Spoken DialogSum: An Emotion-Rich Conversational Dataset for Spoken Dialogue Summarization.
CoRR
Yen-Ju Lu, Kunxiao Gao, Mingrui Liang, Helin Wang, Thomas Thebaud, Laureano Moro-Velázquez, Najim Dehak, Jesús Villalba
2025 A conf
The Interspeech 2025 Challenge on Speech Emotion Recognition in Naturalistic Conditions.
INTERSPEECH
Abinay Reddy Naini, Lucas Goncalves, Ali N. Salman, Pravin Mote, Ismail Rasim Ulgen, Thomas Thebaud, Laureano Moro-Velázquez, Leibny Paola García, Najim Dehak, Berrak Sisman, Carlos Busso
2025 Misc conf
Unveiling Performance Bias in ASR Systems: A Study on Gender, Age, Accent, and More.
ICASSP
Maliha Jahan, Priyam Mazumdar, Thomas Thebaud, Mark Hasegawa-Johnson, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
2025 J jnl
Vox-Profile: A Speech Foundation Model Benchmark for Characterizing Diverse Speaker and Speech Traits.
CoRR
Tiantian Feng, Jihwan Lee, Anfeng Xu, Yoonjeong Lee, Thanathai Lertpetchpun, Xuan Shi, Helin Wang, Thomas Thebaud, Laureano Moro-Velázquez, Dani Byrd, Najim Dehak, Shrikanth Narayanan
2024 — conf
A Phonetic Analysis of Speaker Verification Systems through Phoneme selection and Integrated Gradients.
Odyssey
Thomas Thebaud, Gabriel Hernández, Sarah Flora Samson Juan, Marie Tahon
2024 A* conf
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing.
NeurIPS
Yen-Ju Lu, Jing Liu, Thomas Thebaud, Laureano Moro-Velázquez, Ariya Rastrow, Najim Dehak, Jesús Villalba
2024 J jnl
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing.
CoRR
Yen-Ju Lu, Jing Liu, Thomas Thebaud, Laureano Moro-Velázquez, Ariya Rastrow, Najim Dehak, Jesús Villalba
2024 — conf
Clean Label Attacks Against SLU Systems.
SLT
Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak, Sanjeev Khudanpur
2024 J jnl
Clean Label Attacks against SLU Systems.
CoRR
Henry Li Xinyuan, Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak, Sanjeev Khudanpur
2024 — conf
Discovering Invariant Patterns of Cognitive Decline Via an Automated Analysis of the Cookie Thief Picture Description Task.
Odyssey
Anna Favaro, Najim Dehak, Thomas Thebaud, Jesús Villalba, Esther S. Oh, Laureano Moro-Velázquez
2024 J jnl
End-to-End Neural Speaker Diarization With Non-Autoregressive Attractors.
IEEE ACM Trans. Audio Speech Lang. Process.
Magdalena Rybicka, Jesús Villalba, Thomas Thebaud, Najim Dehak, Konrad Kowalczyk
2024 J jnl
Explainable Metrics for the Assessment of Neurodegenerative Diseases through Handwriting Analysis.
CoRR
Thomas Thebaud, Anna Favaro, Casey Chen, Gabriel Chávez, Laureano Moro-Velázquez, Ankur A. Butala, Najim Dehak
2024 A conf
Exploring the Complementary Nature of Speech and Eye Movements for Profiling Neurological Disorders.
INTERSPEECH
Yuzhe Wang, Anna Favaro, Thomas Thebaud, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
2024 — conf
Finding Spoken Identifications: Using GPT-4 Annotation for an Efficient and Fast Dataset Creation Pipeline.
LREC/COLING
Maliha Jahan, Helin Wang, Thomas Thebaud, Yinglun Sun, Giang Ha Le, Zsuzsanna Fagyal, Odette Scharenborg, Mark Hasegawa-Johnson, Laureano Moro-Velázquez, Najim Dehak
2024 B conf
Multimodal Emotion Recognition Harnessing the Complementarity of Speech, Language, and Vision.
ICMI
Thomas Thebaud, Anna Favaro, Yaohan Guan, Yuchen Yang, Prabhav Singh, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
2024 A conf
Noise-robust Speech Separation with Fast Generative Correction.
INTERSPEECH
Helin Wang, Jesús Villalba, Laureano Moro-Velázquez, Jiarui Hai, Thomas Thebaud, Najim Dehak
2024 — conf
Odyssey 2024 - Speech Emotion Recognition Challenge: Dataset, Baseline Framework, and Results.
Odyssey
Lucas Goncalves, Ali N. Salman, Abinay Reddy Naini, Laureano Moro-Velázquez, Thomas Thebaud, Paola García, Najim Dehak, Berrak Sisman, Carlos Busso
2024 J jnl
Supervised and Unsupervised Alignments for Spoofing Behavioral Biometrics.
CoRR
Thomas Thebaud, Gaël Le Lan, Anthony Larcher
2024 — conf
Unraveling Adversarial Examples against Speaker Identification - Techniques for Attack Detection and Victim Model Classification.
Odyssey
Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak
2024 J jnl
Unraveling Adversarial Examples against Speaker Identification - Techniques for Attack Detection and Victim Model Classification.
CoRR
Sonal Joshi, Thomas Thebaud, Jesús Villalba, Najim Dehak
2023 C conf
Clustering Unsupervised Representations as Defense Against Poisoning Attacks on Speech Commands Classification System.
ASRU
Thomas Thebaud, Sonal Joshi, Henry Li, Martin Sustek, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
2023 A conf
Do Phonatory Features Display Robustness to Characterize Parkinsonian Speech Across Corpora?
INTERSPEECH
Anna Favaro, Tianyu Cao, Thomas Thebaud, Jesús Villalba, Ankur A. Butala, Najim Dehak, Laureano Moro-Velázquez
2023 A conf
DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model.
INTERSPEECH
Helin Wang, Thomas Thebaud, Jesús Villalba, Myra Sydnor, Becky Lammers, Najim Dehak, Laureano Moro-Velázquez
2023 J jnl
Interpretable speech features vs. DNN embeddings: What to use in the automatic assessment of Parkinson's disease in multi-lingual scenarios.
Comput. Biol. Medicine
Anna Favaro, Yi-Ting Tsai, Ankur A. Butala, Thomas Thebaud, Jesús Villalba, Najim Dehak, Laureano Moro-Velázquez
2023 — conf
JHU IWSLT 2023 Dialect Speech Translation System Description.
IWSLT@ACL
Amir Hussein, Cihan Xiao, Neha Verma, Thomas Thebaud, Matthew Wiesner, Sanjeev Khudanpur
2023 C conf
Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks.
ASRU
Martin Sustek, Sonal Joshi, Henry Li, Thomas Thebaud, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
2023 J jnl
Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning.
CoRR
Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
2023 C conf
Model-Based Fairness Metric for Speaker Verification.
ASRU
Maliha Jahan, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak, Jesús Villalba
2023 A conf
Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning.
INTERSPEECH
Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
2023 A conf
Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition.
INTERSPEECH
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak
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
2021 Misc conf
Handwritten Digits Reconstruction from Unlabelled Embeddings.
ICASSP
Thomas Thebaud, Gaël Le Lan, Anthony Larcher
2021 C conf
On the Invertibility of a Voice Privacy System Using Embedding Alignment.
ASRU
Pierre Champion, Thomas Thebaud, Gaël Le Lan, Anthony Larcher, Denis Jouvet
2021 J jnl
On the invertibility of a voice privacy system using embedding alignement.
CoRR
Pierre Champion, Thomas Thebaud, Gaël Le Lan, Anthony Larcher, Denis Jouvet
2021 — conf
Spoofing Speaker Verification With Voice Style Transfer And Reconstruction Loss.
WIFS
Thomas Thebaud, Gaël Le Lan, Anthony Larcher
2020 — conf
Unsupervised Labelling of Stolen Handwritten Digit Embeddings with Density Matching.
ACNS Workshops
Thomas Thebaud, Gaël Le Lan, Anthony Larcher
2019 A* conf
Virtual Objects Look Farther on the Sides: The Anisotropy of Distance Perception in Virtual Reality.
VR
Etienne Peillard, Thomas Thebaud, Jean-Marie Normand, Ferran Argelaguet, Guillaume Moreau, Anatole Lécuyer