CV HAL - Lucas Ondel Yang

Voyage dans le temps : des archives télévision et radio pour observer l’évolution des voix

David Doukhan , Anissa-Claire Adgharouamane , Marlène Coulomb-Gully , Simon Devauchelle , Benjamin Elie et al.

Culture et recherche, 2025, 149, pp.104-107

Article dans une revue hal-05373155v1

Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery

Lucas Ondel , Bolaji Yusuf , Lukáš Burget , Murat Saraçlar

IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, 30, pp.1902 - 1917. ⟨10.1109/TASLP.2022.3171975⟩

Article dans une revue hal-03467205v1

Speech technology for unwritten languages

Odette Scharenborg , Laurent Besacier , Alan Black , Mark Hasegawa-Johnson , Florian Metze et al.

IEEE/ACM Transactions on Audio, Speech and Language Processing, 2020, 28, pp.964 - 975. ⟨10.1109/TASLP.2020.2973896⟩

Article dans une revue hal-02480675v1

Variational Inference for acoustic unit discovery

Lucas Ondel , Lukáš Burget , Jan Černocký

Procedia Computer Science, 2016

Article dans une revue hal-03478236v1

Estimation automatique de caractéristiques acoustiques pour l'étude diachronique du français oral dans les médias

Simon Devauchelle , David Doukhan , Lucas Ondel Yang , Benjamin Élie , Albert Rilliard

Atelier DAHLIA: DigitAl Humanities and cuLtural herItAge: data and knowledge management and analysis, Claudia Marinica; Fabrice Guillet; Florent Laroche, Jan 2025, Strasbourg, France

Communication dans un congrès hal-04938377v1

Articulatory Configurations across Genders and Periods in French Radio and TV archives

Benjamin Elie , David Doukhan , Rémi Uro , Lucas Ondel Yang , Albert Rilliard et al.

Interspeech 2024, Itshak Lapidot; Sharon Gannot, Sep 2024, Kos, Greece. pp.3085-3089, ⟨10.21437/interspeech.2024-1177⟩

Communication dans un congrès hal-04694868v1

Describing voice in French media archives: age and gender effects on pitch and articulation characteristics

Simon Devauchelle , Albert Rilliard , David Doukhan , Lucas Ondel Yang

XX 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

Communication dans un congrès hal-04874662v1

Comparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language Models

Léa-Marie Lam-Yee-Mui , Lucas Ondel Yang , Ondřej Klejch

interspeech 2023, Aug 2023, Dublin, Ireland. pp.87-91, ⟨10.21437/interspeech.2023-1802⟩

Communication dans un congrès hal-04227249v1

GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMI

Lucas Ondel , Léa-Marie Lam-Yee-Mui , Martin Kocour , Caio Corro , Lukás Burget

ICASSP 2022 - IEEE International Conference on Acoustics, Speech and Signal Processing, May 2022, Singapour, Singapore. pp.8417-8421, ⟨10.1109/ICASSP43922.2022.9746824⟩

Communication dans un congrès hal-03434552v1

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

Bolaji Yusuf , Lucas Ondel , Lukáš Burget , Jaň Černocký , Murat Saraclar

ICASSP 2021 - IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2021, Toronto, Canada. pp.3710-3714, ⟨10.1109/ICASSP39728.2021.9414899⟩

Communication dans un congrès hal-03477993v1

The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units

Ewan Dunbar , Julien Karadayi , Mathieu Bernard , Xuan-Nga Cao , Robin Algayres et al.

Interspeech 2020 - Conference of the International Speech Communication Association, Oct 2020, Shangai / Virtual, China

Communication dans un congrès hal-02962224v1

Deriving spectro-temporal properties of hearing from speech data

Lucas Ondel , Ruizhi Li , Gregory Sell , Hynek Hermansky

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Brighton, United Kingdom

Communication dans un congrès hal-03478158v1

Bayesian subspace hidden Markov model for acoustic unit discovery

Lucas Ondel , Vydana Hari Krishna , Lukáš Burget , Jan Černocký

INTERSPEECH, 2019, Graz, Austria

Communication dans un congrès hal-03478174v1

The Zero Resource Speech Challenge 2019: TTS without T

Ewan Dunbar , Robin Algayres , Julien Karadayi , Mathieu Bernard , Juan Benjumea et al.

Interspeech 2019 - 20th Annual Conference of the International Speech Communication Association, Sep 2019, Graz, Austria

Communication dans un congrès hal-02274112v1

Towards automatic methods to detect errors in transcriptions of speech recordings

Jinyi Yang , Lucas Ondel , Vimal Manohar , Hynek Hermansky

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2019, Brighton, United Kingdom

Communication dans un congrès hal-03478164v1

Analysis of BUT-PT Submission for NIST LRE 2017

Oldřich Plchot , Pavel Matejka , Ondrej Novotny , Sandro Cumani , Alicia Lozano-Diez et al.

Odyssey, 2018, Les Sables d'Olonne, France

Communication dans un congrès hal-03478191v1

Unsupervised Word Segmentation from Speech with Attention

Pierre Godard , Marcely Zanon Boito , Lucas Ondel , Alexandre Berard , François Yvon et al.

Interspeech 2018, Sep 2018, Hyderabad, India. pp.2678-2682, ⟨10.21437/Interspeech.2018-1308⟩

Communication dans un congrès hal-01818092v1

Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the “Speaking rosetta” JSALT 2017 workshop

Odette Scharenborg , Laurent Besacier , Alan Black , Mark Hasegawa-Johnson , Florian Metze et al.

ICASSP 2018 - IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2018, Calgary, Alberta, Canada. pp.4979 - 4983, ⟨10.1109/ICASSP.2018.8461761⟩

Communication dans un congrès hal-01709578v1

Bayesian models for unit discovery on a very low resource language

Lucas Ondel , Pierre Godard , Laurent Besacier , Elin Larsen , Mark Hasegawa-Johnson et al.

ICASSP 2018 - IEEE International Conference on Acoustics, Speech, and Signal Processing, Apr 2018, Calgary, Alberta, Canada. ⟨10.1109/ICASSP.2018.8461545⟩

Communication dans un congrès hal-01709589v1

Automatic speech recognition and topic identification for almost-zero-resource languages

Matthew Wiesner , Chunxi Liu , Lucas Ondel , Craig Harman , Vimal Manohar et al.

INTERSPEECH, 2018, Hyderabad, India

Communication dans un congrès hal-03478201v1

An empirical evaluation of zero-resource acoustic units discovery

Chunxi Liu , Jinyi Yang , Ming Sun , Santosh Kesiraju , Alena Rott et al.

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States

Communication dans un congrès hal-03478220v1

Bayesian joint-sequence models for grapheme-to-phoneme conversion

Mirko Hannemann , Jan Trmal , Lucas Ondel , Santosh Kesiraju , Lukáš Burget

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States

Communication dans un congrès hal-03478209v1

Bayesian phonotactic language model for acoustic unit discovery

Lucas Ondel , Lukáš Burget , Jan Černocký , Santosh Kesiraju

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States

Communication dans un congrès hal-03478211v1

Image2speech: Automatically generating audio descriptions of images

Mark Hasegawa-Johnson , Alan Black , Lucas Ondel , Odette Scharenborg , Francesco Ciannella

ICNLSSP, 2017, Casablanca, Morocco

Communication dans un congrès hal-03478222v1

Building an asr system for a low-resource language through the adaptation of a high-resource language asr system: preliminary results

Odette Scharenborg , Francesco Cianella , Alan W Black , Shruti Palaskar , Florian Metze et al.

ICNLSSP, 2017, Casablanca, Morocco

Communication dans un congrès hal-03478229v1

Topic identification of spoken documents using unsupervised acoustic unit discovery

Santosh Kesiraju , Lucas Ondel , Raghavendra Pappagari , Lukáš Burget , Najim Dehak et al.

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2017, Nouvelle Orleans, United States

Communication dans un congrès hal-03478213v1

MASK+: Data-driven regions selection for acoustic fingerprinting

Lucas Ondel , Xavier Anguera , Jordi Luque

IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2015, Brisbane, Australia

Communication dans un congrès hal-03478239v1

AUTOMATIC LEARNING OF A PHONOLOGICAL SYSTEM: A CASE STUDY ON MBOSHI

Lucas Ondel , Lukáš Burget

International Conference Language Technologies for All (LT4ALL), 2019, Paris, France

Poster de conférence hal-03478242v1

Variation of Perceived Voice Pitch Across Time Periods, Gender, and Age in French Media Archives

Simon Devauchelle , Albert Rilliard , David Doukhan , Lucas Ondel Yang

Valentina 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⟩

Chapitre d'ouvrage hal-05450567v1

Présentation LLM / Transformers

Alban Perli , Théo Gigant , Lucas Ondel Yang , Yann Fraigneau

2025

Autre publication scientifique hal-05191640v1

La “recette’’ LLM et modèles de fondation

Théo Gigant , Alban Perli , Yann Fraigneau , Lucas Ondel Yang

2025

Autre publication scientifique hal-05153758v1

Fast and General Automatic Differentiation for Finite-State Methods

Lucas Ondel Yang , Tina Raissi , Martin Kocour , Pablo Riera , Caio Corro

2026

Pré-publication, Document de travail hal-05500843v1

Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

George August Wright , Umberto Cappellazzo , Salah Zaiem , Desh Raj , Lucas Ondel Yang et al.

2023

Pré-publication, Document de travail hal-04216190v1

Bayesian Subspace HMM for the Zerospeech 2020 Challenge

Bolaji Yusuf , Lucas Ondel

2021

Pré-publication, Document de travail hal-03478155v1

Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings

Marcely Zanon , Bolaji Yusuf , Lucas Ondel , Aline Villavicencio , Laurent Besacier

2021

Pré-publication, Document de travail hal-03477951v1

Revisiting Joint Decoding Based Multi-Talker Speech Recognition with DNN Acoustic Model

Martin Kocour , Kateřina Žmolíková , Lucas Ondel , Ján Švec , Marc Delcroix et al.

2021

Pré-publication, Document de travail hal-03477923v1

BUT-PT System Description for NIST LRE 2017

Pavel Matejka , Oldřich Plchot , Ondrej Novotny , Sandro Cumani , Alicia Lozano-Diez et al.

[Technical Report] National Institute of Standards and Technology [Gaithersburg] (Agency of the U.S. Department of Commerce). 2017

Rapport (rapport technique) hal-03478228v1

Discovering Acoustic Units from Speech: A Bayesian Approach

Lucas Ondel

Computation and Language [cs.CL]. Brno University of Technology (MAIS), 2021. English. ⟨NNT : ⟩

Thèse tel-03478075v1

Lucas Ondel Yang

Publications

Publications

Voyage dans le temps : des archives télévision et radio pour observer l’évolution des voix

Non-Parametric Bayesian Subspace Models for Acoustic Unit Discovery

Speech technology for unwritten languages

Variational Inference for acoustic unit discovery

Estimation automatique de caractéristiques acoustiques pour l'étude diachronique du français oral dans les médias

Articulatory Configurations across Genders and Periods in French Radio and TV archives

Describing voice in French media archives: age and gender effects on pitch and articulation characteristics

Comparing Self-Supervised Pre-Training and Semi-Supervised Training for Speech Recognition in Languages with Weak Language Models

GPU-Accelerated Forward-Backward Algorithm with Application to Lattice-Free MMI

A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery

The Zero Resource Speech Challenge 2020: Discovering discrete subword and word units

Deriving spectro-temporal properties of hearing from speech data

Bayesian subspace hidden Markov model for acoustic unit discovery

The Zero Resource Speech Challenge 2019: TTS without T

Towards automatic methods to detect errors in transcriptions of speech recordings

Analysis of BUT-PT Submission for NIST LRE 2017

Unsupervised Word Segmentation from Speech with Attention

Linguistic unit discovery from multi-modal inputs in unwritten languages: Summary of the “Speaking rosetta” JSALT 2017 workshop

Bayesian models for unit discovery on a very low resource language

Automatic speech recognition and topic identification for almost-zero-resource languages

An empirical evaluation of zero-resource acoustic units discovery

Bayesian joint-sequence models for grapheme-to-phoneme conversion

Bayesian phonotactic language model for acoustic unit discovery

Image2speech: Automatically generating audio descriptions of images

Building an asr system for a low-resource language through the adaptation of a high-resource language asr system: preliminary results

Topic identification of spoken documents using unsupervised acoustic unit discovery

MASK+: Data-driven regions selection for acoustic fingerprinting

AUTOMATIC LEARNING OF A PHONOLOGICAL SYSTEM: A CASE STUDY ON MBOSHI

Variation of Perceived Voice Pitch Across Time Periods, Gender, and Age in French Media Archives

Présentation LLM / Transformers

La “recette’’ LLM et modèles de fondation

Fast and General Automatic Differentiation for Finite-State Methods

Training dynamic models using early exits for automatic speech recognition on resource-constrained devices

Bayesian Subspace HMM for the Zerospeech 2020 Challenge

Unsupervised Word Segmentation from Discrete Speech Units in Low-Resource Settings

Revisiting Joint Decoding Based Multi-Talker Speech Recognition with DNN Acoustic Model

BUT-PT System Description for NIST LRE 2017

Discovering Acoustic Units from Speech: A Bayesian Approach