Lucas Ondel Yang
Publications
Publications
|
|
Voyage dans le temps : des archives télévision et radio pour observer l’évolution des voixCulture et recherche, 2025, 149, pp.104-107 |
|
|
Non-Parametric Bayesian Subspace Models for Acoustic Unit DiscoveryIEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, 30, pp.1902 - 1917. ⟨10.1109/TASLP.2022.3171975⟩ |
|
|
Speech technology for unwritten languagesIEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, 28, pp.964 - 975. ⟨10.1109/TASLP.2020.2973896⟩ |
Variational Inference for acoustic unit discoveryProcedia Computer Science, 2016 |
|
|
Estimation automatique de caractéristiques acoustiques pour l'étude diachronique du français oral dans les médiasAtelier DAHLIA: DigitAl Humanities and cuLtural herItAge: data and knowledge management and analysis, Claudia Marinica; Fabrice Guillet; Florent Laroche, Jan 2025, Strasbourg, France |
Describing voice in French media archives: age and gender effects on pitch and articulation characteristicsXX Convegno Nazionale AISV, LFSAG (Laboratorio di Fonetica Sperimentale "Arturo Genre") Dipartimento di Lingue e Letterature Straniere e Culture Moderne Università degli Studi di Torino, Feb 2024, Turin, Italy |
|
|
|
Articulatory Configurations across Genders and Periods in French Radio and TV archivesInterspeech 2024, Itshak Lapidot; Sharon Gannot, Sep 2024, Kos, Greece. pp.3085-3089, ⟨10.21437/interspeech.2024-1177⟩ |
|
|
Comparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language ModelsINTERSPEECH 2023, Aug 2023, Dublin, Ireland. pp.87-91, ⟨10.21437/interspeech.2023-1802⟩ |
|
|
GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMIIEEE International Conference on Acoustics, Speech, and Signal Processing, May 2022, Singapour, Singapore. pp.8417-8421, ⟨10.1109/ICASSP43922.2022.9746824⟩ |
|
|
A Hierarchical Subspace Model for Language-Attuned Acoustic Unit DiscoveryIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Jun 2021, Toronto, Canada. pp.3710-3714, ⟨10.1109/ICASSP39728.2021.9414899⟩ |
|
|
The Zero Resource Speech Challenge 2020: Discovering discrete subword and word unitsInterspeech 2020 - Conference of the International Speech Communication Association, Oct 2020, Shangai / Virtual, China |
Bayesian subspace hidden Markov model for acoustic unit discoveryINTERSPEECH, 2019, Graz, Austria |
|
Deriving spectro-temporal properties of hearing from speech dataIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Brighton, United Kingdom |
|
|
|
The Zero Resource Speech Challenge 2019: TTS without TInterspeech 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria |
Towards automatic methods to detect errors in transcriptions of speech recordingsIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Brighton, United Kingdom |
|
|
|
Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the “Speaking rosetta” JSALT 2017 workshop2018 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Apr 2018, Calgary, Alberta, Canada. pp.4979 - 4983, ⟨10.1109/ICASSP.2018.8461761⟩ |
|
|
Bayesian models for unit discovery on a very low resource language2018 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), Apr 2018, Calgary, Alberta, Canada. ⟨10.1109/ICASSP.2018.8461545⟩ |
Automatic speech recognition and topic identification for almost-zero-resource languagesINTERSPEECH, 2018, Hyderabad, India |
|
|
|
Unsupervised Word Segmentation from Speech with AttentionInterspeech 2018, Sep 2018, Hyderabad, India. pp.2678-2682, ⟨10.21437/Interspeech.2018-1308⟩ |
Analysis of BUT-PT Submission for NIST LRE 2017Odyssey, 2018, Les Sables d'Olonne, France |
|
Bayesian joint-sequence models for grapheme-to-phoneme conversionIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States |
|
Bayesian phonotactic language model for acoustic unit discoveryIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States |
|
Building an asr system for a low-resource language through the adaptation of a high-resource language asr system: preliminary resultsICNLSSP, 2017, Casablanca, Morocco |
|
Image2speech: Automatically generating audio descriptions of imagesICNLSSP, 2017, Casablanca, Morocco |
|
Topic identification of spoken documents using unsupervised acoustic unit discoveryIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States |
|
An empirical evaluation of zero-resource acoustic units discoveryIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States |
|
MASK+: Data-driven regions selection for acoustic fingerprintingIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, Brisbane, Australia |
AUTOMATIC LEARNING OF A PHONOLOGICAL SYSTEM: A CASE STUDY ON MBOSHIInternational Conference Language Technologies for All (LT4ALL), 2019, Paris, France |
|
|
Variation of Perceived Voice Pitch Across Time Periods, Gender, and Age in French Media ArchivesValentina De Iacovo; Bianca Maria De Paolis; Daniela Mereu. The voice in the media and new technologies, 12 (004), Officinaventuno, pp.47-71, 2024, Studi Associazione Italiana Scienze della Voce, 978-88-97657-73-6. ⟨10.17469/O2112AISV000004⟩ |
|
|
Présentation LLM / Transformers2025 |
|
|
La “recette’’ LLM et modèles de fondation2025 |
|
|
Fast and General Automatic Differentiation for Finite-State Methods2026 |
|
|
Training dynamic models using early exits for automatic speech recognition on resource-constrained devices2023 |
Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings2021 |
|
Revisiting Joint Decoding Based Multi-Talker Speech Recognition with DNN Acoustic Model2021 |
|
Bayesian Subspace HMM for the Zerospeech 2020 Challenge2021 |
BUT-PT System Description for NIST LRE 2017[Technical Report] National Institute of Standards and Technology [Gaithersburg] (Agency of the U.S. Department of Commerce). 2017 |
Discovering Acoustic Units from Speech: A Bayesian ApproachComputation and Language [cs.CL]. Brno University of Technology (MAIS), 2021. English. ⟨NNT : ⟩ |