Thomas Pellegrini

105 papers A* 1A 25B 4C 3Misc 3Journal 33Unranked 34

Year	Rank	Type	Title / Venue / Authors
2025	J	`jnl`	Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning. CoRR Ludovic Tuncay, Etienne Labbé, Emmanouil Benetos, Thomas Pellegrini
2025	Misc	`conf`	Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging. ICASSP Ludovic Tuncay, Etienne Labbé, Thomas Pellegrini
2025	J	`jnl`	Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging. CoRR Ludovic Tuncay, Etienne Labbé, Thomas Pellegrini
2025	J	`jnl`	Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning. CoRR Lucas Block Medin, Thomas Pellegrini, Lucile Gelin
2024	—	`conf`	Adaptation de modèles auto-supervisés pour la reconnaissance de phonèmes dans la parole d'enfant. TALN (JEP) Lucas Block Medin, Lucile Gelin, Thomas Pellegrini
2024	J	`jnl`	CNN-based Compressor Mass Flow Estimator in Industrial Aircraft Vapor Cycle System. CoRR Justin Reverdi, Sixin Zhang, Saïd Aoues, Fabrice Gamboa, Serge Gratton, Thomas Pellegrini
2024	J	`jnl`	CoNeTTE: An Efficient Audio Captioning System Leveraging Multiple Datasets With Task Embedding. IEEE ACM Trans. Audio Speech Lang. Process. Etienne Labbé, Thomas Pellegrini, Julien Pinquier
2024	J	`jnl`	Enhancing Synthetic Training Data for Speech Commands: From ASR-Based Filtering to Domain Adaptation in SSL Latent Space. CoRR Sebastião Quintas, Isabelle Ferrané, Thomas Pellegrini
2024	—	`conf`	IRIT-MFU Multi-modal systems for emotion classification for Odyssey 2024 challenge. Odyssey Adrien Lafore, Clément Pagés, Leila Moudjari, Sebastião Quintas, Hervé Bredin, Thomas Pellegrini, Farah Benamara, Isabelle Ferrané, Jérôme Bertrand, Marie-Françoise Bertrand, Véronique Moriceau, Jérôme Farinas
2024	—	`conf`	Premier système IRIT-MyFamillyUp pour la compétition sur la reconnaissance des émotions Odyssey 2024. TALN (JEP) Adrien Lafore, Clément Pagés, Leila Moudjari, Sebastião Quintas, Isabelle Ferrané, Hervé Bredin, Thomas Pellegrini, Farah Benamara, Jérôme Bertrand, Marie-Françoise Bertrand, Véronique Moriceau, Jérôme Farinas
2024	A	`conf`	Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning. INTERSPEECH Lucas Block Medin, Thomas Pellegrini, Lucile Gelin
2024	A	`conf`	Specializing Self-Supervised Speech Representations for Speaker Segmentation. INTERSPEECH Séverin Baroudi, Thomas Pellegrini, Hervé Bredin
2023	A	`conf`	Adapting a ConvNeXt Model to Audio Classification on AudioSet. INTERSPEECH Thomas Pellegrini, Ismail Khalfaoui Hassani, Etienne Labbé, Timothée Masquelier
2023	J	`jnl`	Adapting a ConvNeXt model to audio classification on AudioSet. CoRR Thomas Pellegrini, Ismail Khalfaoui Hassani, Etienne Labbé, Timothée Masquelier
2023	J	`jnl`	Audio classification with Dilated Convolution with Learnable Spacings. CoRR Ismail Khalfaoui Hassani, Timothée Masquelier, Thomas Pellegrini
2023	J	`jnl`	Audio-video fusion strategies for active speaker detection in meetings. Multim. Tools Appl. Lionel Pibre, Francisco Madrigal, Cyrille Equoy, Frédéric Lerasle, Thomas Pellegrini, Julien Pinquier, Isabelle Ferrané
2023	J	`jnl`	CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding. CoRR Etienne Labbé, Thomas Pellegrini, Julien Pinquier
2023	—	`conf`	Comparing phoneme recognition systems on the detection and diagnosis of reading mistakes for young children's oral reading evaluation. SLaTE Lucile Gelin, Morgane Daniel, Thomas Pellegrini, Julien Pinquier
2023	J	`jnl`	Dilated Convolution with Learnable Spacings: beyond bilinear interpolation. CoRR Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothée Masquelier
2023	A*	`conf`	Dilated convolution with learnable spacings. ICLR Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothée Masquelier
2023	J	`jnl`	Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval? CoRR Etienne Labbé, Thomas Pellegrini, Julien Pinquier
2023	J	`jnl`	Multilingual Audio Captioning using machine translated data. CoRR Matéo Cousin, Etienne Labbé, Thomas Pellegrini
2023	—	`conf`	Multitask Learning in Audio Captioning: A Sentence Embedding Regression Loss Acts as a Regularizer. EUSIPCO Etienne Labbé, Julien Pinquier, Thomas Pellegrini
2023	J	`jnl`	Multitask learning in Audio Captioning: a sentence embedding regression loss acts as a regularizer. CoRR Etienne Labbé, Julien Pinquier, Thomas Pellegrini
2022	J	`jnl`	Audio-video fusion strategies for active speaker detection in meetings. CoRR Lionel Pibre, Francisco Madrigal, Cyrille Equoy, Frédéric Lerasle, Thomas Pellegrini, Julien Pinquier, Isabelle Ferrané
2022	J	`jnl`	Comparison of semi-supervised deep learning algorithms for audio classification. EURASIP J. Audio Speech Music. Process. Léo Cances, Etienne Labbé, Thomas Pellegrini
2022	—	`conf`	Is my Automatic Audio Captioning System so Bad? SPIDEr-max: A Metric to Consider Several Caption Candidates. DCASE Etienne Labbé, Thomas Pellegrini, Julien Pinquier
2022	J	`jnl`	Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates. CoRR Etienne Labbé, Thomas Pellegrini, Julien Pinquier
2022	—	`conf`	Language-Based Audio Retrieval with Textual Embeddings of Tag Names. DCASE Thomas Pellegrini
2022	J	`jnl`	PCEDNet: A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds. ACM Trans. Graph. Chems-Eddine Himeur, Thibault Lejemble, Thomas Pellegrini, Mathias Paulin, Loic Barthe, Nicolas Mellado
2022	—	`ed.`	Proceedings of the 7th Workshop on Detection and Classification of Acoustic Scenes and Events 2022, DCASE 2022, Nancy, France, November 3-4, 2022 DCASE Mathieu Lagrange, Annamaria Mesaros, Thomas Pellegrini, Gaël Richard, Romain Serizel, Dan Stowell
2021	C	`conf`	Automatic macro segmentation into interaction sequence: a silence-based approach for meeting structuring. CBMI Lionel Pibre, Sélim Mechrouh, Thomas Pellegrini, Julien Pinquier, Isabelle Ferrané
2021	Misc	`conf`	Comparison of Deep Co-Training and Mean-Teacher Approaches for Semi-Supervised Audio Tagging. ICASSP Léo Cances, Thomas Pellegrini
2021	A	`conf`	Deep-Learning-Based Central African Primate Species Classification with MixUp and SpecAugment. Interspeech Thomas Pellegrini
2021	J	`jnl`	Dilated convolution with learnable spacings. CoRR Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothée Masquelier
2021	J	`jnl`	End-to-end acoustic modelling for phone recognition of young readers. CoRR Lucile Gelin, Morgane Daniel, Julien Pinquier, Thomas Pellegrini
2021	J	`jnl`	End-to-end acoustic modelling for phone recognition of young readers. Speech Commun. Lucile Gelin, Morgane Daniel, Julien Pinquier, Thomas Pellegrini
2021	Misc	`conf`	Fast Threshold Optimization for Multi-Label Audio Tagging Using Surrogate Gradient Learning. ICASSP Thomas Pellegrini, Timothée Masquelier
2021	J	`jnl`	Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning. CoRR Thomas Pellegrini, Timothée Masquelier
2021	J	`jnl`	Improving Deep-learning-based Semi-supervised Audio Tagging with Mixup. CoRR Léo Cances, Etienne Labbé, Thomas Pellegrini
2021	—	`conf`	Low-Activity Supervised Convolutional Spiking Neural Networks Applied to Speech Commands Recognition. SLT Thomas Pellegrini, Romain Zimmer, Timothée Masquelier
2021	A	`conf`	Simulating Reading Mistakes for Child Speech Transformer-Based Phone Recognition. Interspeech Lucile Gelin, Thomas Pellegrini, Julien Pinquier, Morgane Daniel
2021	—	`conf`	Weakly supervised discourse segmentation for multiparty oral conversations. EMNLP (1) Lila Gravellier, Julie Hunter, Philippe Muller, Thomas Pellegrini, Isabelle Ferrané
2020	—	`conf`	Deep learning with weakly-annotated data: a sound event detection use case (and hate speech detection here and there) (abstract). TWSDetection Thomas Pellegrini
2020	—	`conf`	Informations segmentales pour la caractérisation phonétique du locuteur : variabilité inter- et intra-locuteurs (An automatic classification task involving 44 speakers was performed using convolutional neural networks (CNN) on broadband spectrograms extracted from 2-second sequences of a spontaneous speech corpus (NCCFr)). JEP-TALN-RECITAL (1) Cédric Gendrot, Emmanuel Ferragne, Thomas Pellegrini
2020	J	`jnl`	Low-activity supervised convolutional spiking neural networks applied to speech commands recognition. CoRR Thomas Pellegrini, Romain Zimmer, Timothée Masquelier
2020	J	`jnl`	PCEDNet : A Neural Network for Fast and Efficient Edge Detection in 3D Point Clouds. CoRR Chems-Eddine Himeur, Thibault Lejemble, Thomas Pellegrini, Mathias Paulin, Loic Barthe, Nicolas Mellado
2020	—	`conf`	Reconnaissance de phones fondée sur du Transfer Learning pour des enfants apprenants lecteurs en environnement de classe (Transfer Learning based phone recognition on children learning to read, with speech recorded in a classroom environment). JEP-TALN-RECITAL (1) Lucile Gelin, Morgane Daniel, Thomas Pellegrini, Julien Pinquier
2019	—	`conf`	A Convolutional Neural Network for 250-MHz Quantitative Acoustic-microscopy Resolution Enhancement. EMBC Jonathan Mamou, Thomas Pellegrini, Denis Kouamé, Adrian Basarab
2019	A	`conf`	Char+CV-CTC: Combining Graphemes and Consonant/Vowel Units for CTC-Based ASR Using Multitask Learning. INTERSPEECH Abdelwahab Heba, Thomas Pellegrini, Jean-Pierre Lorré, Régine André-Obrecht
2019	B	`conf`	Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection. IJCNN Thomas Pellegrini, Léo Cances
2019	J	`jnl`	Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection. CoRR Thomas Pellegrini, Léo Cances
2019	—	`conf`	Evaluation of Post-Processing Algorithms for Polyphonic Sound Event Detection. WASPAA Léo Cances, Patrice Guyot, Thomas Pellegrini
2019	J	`jnl`	Evaluation of post-processing algorithms for polyphonic sound event detection. CoRR Léo Cances, Patrice Guyot, Thomas Pellegrini
2019	J	`jnl`	Technical report: supervised training of convolutional spiking neural networks with PyTorch. CoRR Romain Zimmer, Thomas Pellegrini, Srisht Fateh Singh, Timothée Masquelier
2019	A	`conf`	The Airbus Air Traffic Control Speech Recognition 2018 Challenge: Towards ATC Automatic Transcription and Call Sign Detection. INTERSPEECH Thomas Pellegrini, Jérôme Farinas, Estelle Delpech, François Lancelot
2018	J	`jnl`	Densely Connected CNNs for Bird Audio Detection. CoRR Thomas Pellegrini
2018	A	`conf`	Group emotion recognition strategies for entertainment robots. IROS Sarah Cosentino, Estelle I. S. Randria, Jia-Yeu Lin, Thomas Pellegrini, Salvatore Sessa, Atsuo Takanishi
2018	—	`conf`	Sound event detection from weak annotations: weighted-GRU versus multi-instance-learning. DCASE Léo Cances, Thomas Pellegrini, Patrice Guyot
2018	J	`jnl`	The Airbus Air Traffic Control speech recognition 2018 challenge: towards ATC automatic transcription and call sign detection. CoRR Thomas Pellegrini, Jérôme Farinas, Estelle Delpech, François Lancelot
2017	—	`conf`	Densely connected CNNs for bird audio detection. EUSIPCO Thomas Pellegrini
2017	—	`conf`	Lexical Emphasis Detection in Spoken French Using F-BANKs and Neural Networks. SLSP Abdelwahab Heba, Thomas Pellegrini, Tom Jorquera, Régine André-Obrecht, Jean-Pierre Lorré
2017	C	`conf`	Music Feature Maps with Convolutional Neural Networks for Music Genre Classification. CBMI Christine Sénac, Thomas Pellegrini, Florian Mouret, Julien Pinquier
2017	—	`conf`	Unsupervised Speech Unit Discovery Using K-means and Neural Networks. SLSP Céline Manenti, Thomas Pellegrini, Julien Pinquier
2016	A	`conf`	CNN-Based Phone Segmentation Experiments in a Less-Represented Language. INTERSPEECH Céline Manenti, Thomas Pellegrini, Julien Pinquier
2016	C	`conf`	Filterbank coefficients selection for segmentation in singer turns. CBMI Marwa Thlithi, Julien Pinquier, Thomas Pellegrini, Régine André-Obrecht
2016	A	`conf`	Inferring Phonemic Classes from CNN Activation Maps Using Clustering Techniques. INTERSPEECH Thomas Pellegrini, Sandrine Mouysset
2016	—	`conf`	Influence de la quantité de données sur une tâche de segmentation de phones fondée sur les réseaux de neurones (Phone-level speech segmentation with neural networks : influence of the amount of data ). JEP-TALN-RECITAL (1) Céline Manenti, Thomas Pellegrini, Julien Pinquier
2016	A	`conf`	Pronunciation Assessment of Japanese Learners of French with GOP Scores and Phonetic Information. INTERSPEECH Vincent Laborde, Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Halima Sahraoui, Jérôme Farinas
2016	—	`conf`	Réseau de neurones convolutif pour l'évaluation automatique de la prononciation (CNN-based automatic pronunciation assessment of Japanese speakers learning French ). JEP-TALN-RECITAL (1) Thomas Pellegrini, Lionel Fontan, Halima Sahraoui
2016	A	`conf`	Sinusoidal Modelling for Ecoacoustics. INTERSPEECH Patrice Guyot, Alice Eldridge, Ying Chen Eyre-Walker, Alison Johnston, Thomas Pellegrini, Mika Peck
2015	J	`jnl`	Automatic Assessment of Speech Capability Loss in Disordered Speech. ACM Trans. Access. Comput. Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Jérôme Farinas, Charlotte Alazard-Guiu, Marina Robert, Peggy Gatignol
2015	A	`conf`	Comparing SVM, softmax, and shallow neural networks for eating condition classification. INTERSPEECH Thomas Pellegrini
2015	—	`conf`	Predicting disordered speech comprehensibility from Goodness of Pronunciation scores. SLPAT@Interspeech Lionel Fontan, Thomas Pellegrini, Julia Olcoz, Alberto Abad
2015	—	`conf`	Pyc2Sound: a Python tool to convert images into sound. Audio Mostly Conference Vincent Bragard, Thomas Pellegrini, Julien Pinquier
2015	—	`conf`	Time-continuous Estimation of Emotion in Music with Recurrent Neural Networks. MediaEval Thomas Pellegrini, Valentin Barrière
2014	—	`conf`	Automatically Recognising European Portuguese Children's Speech - Pronunciation Patterns Revealed by an Analysis of ASR Errors. PROPOR Annika Hämäläinen, Hyongsil Cho, Sara Candeias, Thomas Pellegrini, Alberto Abad, Michael Tjalve, Isabel Trancoso, Miguel Sales Dias
2014	—	`conf`	Correlating ASR errors with developmental changes in speech production: a study of 3-10-year-old European Portuguese children's speech. WOCCI Annika Hämäläinen, Sara Candeias, Hyongsil Cho, Hugo Meinedo, Alberto Abad, Thomas Pellegrini, Michael Tjalve, Isabel Trancoso, Miguel Sales Dias
2014	B	`conf`	El-WOZ: a client-server wizard-of-oz interface. LREC Thomas Pellegrini, Vahid Hedayati, Ângela Costa
2014	—	`conf`	Improving Speech Recognition through Automatic Selection of Age Group - Specific Acoustic Models. PROPOR Annika Hämäläinen, Hugo Meinedo, Michael Tjalve, Thomas Pellegrini, Isabel Trancoso, Miguel Sales Dias
2014	A	`conf`	Segmentation in singer turns with the Bayesian information criterion. INTERSPEECH Marwa Thlithi, Thomas Pellegrini, Julien Pinquier, Régine André-Obrecht
2014	A	`conf`	Speaker age estimation for elderly speech recognition in European Portuguese. INTERSPEECH Thomas Pellegrini, Vahid Hedayati, Isabel Trancoso, Annika Hämäläinen, Miguel Sales Dias
2014	A	`conf`	The goodness of pronunciation algorithm applied to disordered speech. INTERSPEECH Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Jérôme Farinas, Marina Robert
2014	—	`conf`	Towards soundpainting gesture recognition. Audio Mostly Conference Thomas Pellegrini, Patrice Guyot, Baptiste Angles, Christophe Mollaret, Christophe Mangou
2013	A	`conf`	A corpus-based study of elderly and young speakers of European Portuguese: acoustic correlates and their impact on speech recognition performance. INTERSPEECH Thomas Pellegrini, Annika Hämäläinen, Philippe Boula de Mareüil, Michael Tjalve, Isabel Trancoso, Sara Candeias, Miguel Sales Dias, Daniela Braga
2013	J	`jnl`	ASR-based exercises for listening comprehension practice in European Portuguese. Comput. Speech Lang. Thomas Pellegrini, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede, Maxine Eskénazi
2012	—	`conf`	Impact of Age in ASR for the Elderly: Preliminary Experiments in European Portuguese. IberSPEECH Thomas Pellegrini, Isabel Trancoso, Annika Hämäläinen, António Calado, Miguel Sales Dias, Daniela Braga
2012	A	`conf`	Less errors with TTS? A dictation experiment with foreign language learners. INTERSPEECH Thomas Pellegrini, Ângela Costa, Isabel Trancoso
2012	—	`conf`	Overview of Computer-assisted Language Learning for European Portuguese at L CSEDU (2) Thomas Pellegrini, Wang Ling, André Silva, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
2011	A	`conf`	Automatic Generation of Listening Comprehension Learning Material in European Portuguese. INTERSPEECH Thomas Pellegrini, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
2011	—	`conf`	Browsing videos by automatically detected audio events. EUROCON Virginia Barbosa, Thomas Pellegrini, Miguel M. F. Bugalho, Isabel Trancoso
2011	—	`conf`	Listening comprehension games for portuguese: exploring the best features. SLaTE Rui Correia, Thomas Pellegrini, Maxine Eskénazi, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
2010	A	`conf`	Context dependent modelling approaches for hybrid speech recognizers. INTERSPEECH Alberto Abad, Thomas Pellegrini, Isabel Trancoso, João Paulo Neto
2010	A	`conf`	Improving ASR error detection with non-decoder based features. INTERSPEECH Thomas Pellegrini, Isabel Trancoso
2010	—	`conf`	Multimedia learning materials. SLT José Lopes, Isabel Trancoso, Rui Correia, Thomas Pellegrini, Hugo Meinedo, Nuno J. Mamede, Maxine Eskénazi
2009	A	`conf`	Audio contributions to semantic video search. ICME Isabel Trancoso, Thomas Pellegrini, José Portelo, Hugo Meinedo, Miguel M. F. Bugalho, Alberto Abad, João Paulo Neto
2009	J	`jnl`	Automatic Word Decompounding for ASR in a Morphologically Rich Language: Application to Amharic. IEEE Trans. Speech Audio Process. Thomas Pellegrini, Lori Lamel
2009	A	`conf`	Detecting audio events for semantic video search. INTERSPEECH Miguel M. F. Bugalho, José Portelo, Isabel Trancoso, Thomas Pellegrini, Alberto Abad
2009	—	`conf`	Error Detection in Broadcast News ASR Using Markov Chains. LTC Thomas Pellegrini, Isabel Trancoso
2008	—	`conf`	Are audio or textual training data more important for ASR in less-represented languages? SLTU Thomas Pellegrini, Lori Lamel
2008	B	`conf`	Developments of "Lëtzebuergesch" Resources for Automatic Speech Processing and Linguistic Studies. LREC Martine Adda-Decker, Thomas Pellegrini, Éric Bilinski, Gilles Adda
2008	—	`—`	Transcription automatique de langues peu dotées. (Automatic speech recognition for less-represented languages). Thomas Pellegrini
2007	A	`conf`	Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language. INTERSPEECH Thomas Pellegrini, Lori Lamel
2006	B	`conf`	Experimental detection of vowel pronunciation variants in Amharic. LREC Thomas Pellegrini, Lori Lamel
2006	A	`conf`	Investigating automatic decomposition for ASR in less represented languages. INTERSPEECH Thomas Pellegrini, Lori Lamel