Thomas Hueber
Thomas Hueber has 2 papers in our library, in 2022–2026, most of them on Language models & pretraining, Speech & spoken language, English; often with Angelo Ortiz Tandazo, Emmanuel Dupoux, Laurent Besacier.
OpenAlex · ORCID · h-index 22 · 150 works · 2,333 citations OpenAlex, 2026-10-14
📄 2 works in our library · 🔗 Cited 7 times in our library · 2 more in our library without a page yet · ⭐ Paper Stars ranking: #9969
Affiliations
Fields, topics and concepts
📚 Shelves 7The field of science this work belongs to (OpenAlex fields).Arts and Humanities · 2 worksComputer Science · 2 worksPsychology · 2 worksArtificial Intelligence · 2 worksExperimental and Cognitive Psychology · 2 worksLanguage and Linguistics · 2 worksSignal Processing · 2 works
🧭 Topics 3Research subjects and languages the work is about.English · 1 workLanguage models & pretraining · 1 workSpeech & spoken language · 1 work
Works by year
2020s
Papers
- BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language model (2022 · 9 citations)
Personal pronouns are usually unstressed, so a stressed pronoun («HE loves her») signals contrastive focus that needs discourse knowledge to predict. - MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units Discovery (2026 · 1 citation)
Self-supervised speech models such as HuBERT need very large amounts of clean audio. The units they discover are also shorter and more numerous than real phonemes, and they stay sensitive to speaker and phonetic context. This limits their use for low-resource and unwritten languages.
All works
- BERT, can HE predict contrastive focus? Predicting and controlling prominence in neural TTS using a language modelBrooke Stephenson, Laurent Besacier, Laurent Girin, et al.English · 9 citations
- Investigating the dynamics of hand and lips in French Cued Speech using attention mechanisms and CTC-based decoding ↗arXiv:2306.08290 · Interspeech, ISCA, Aug 2023, Dublin, Ireland · no summary yetSanjana Sankar et al.2023 · 3 citations
- MauBERT: Universal Phonetic Inductive Biases for Few-Shot Acoustic Units DiscoveryAnnual Meeting of the Association for Computational Linguistics (ACL)Angelo Ortiz Tandazo, Manel Khentout, Youssef Benchekroun, et al.2026 · 1 citation
- Vizart3D : Retour Articulatoire Visuel pour l'Aide à la Prononciation (Vizart3D: Visual Articulatory Feedack for Computer-Assisted Pronunciation Training) [in French] ↗Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 5: Software Demonstrations · no summary yetThomas Hueber et al.2012
Co-authors here
Venues
- Annual Meeting of the Association for Computational Linguistics (ACL): ACL 2026
- Interspeech: Interspeech 2022
- Proceedings of the Joint Conference JEP-TALN-RECITAL 2012, volume 5: Software Demonstrations
Cited by
Updated
This page in Markdown → https://md.research.elamur.ai/free/en/authors/thomas-hueber/