Thomas Pellegrini

ORCID

Publication Activity (10 Years)

Years Active: 2006-2024
Publications (10 Years): 61

Top Venues

University of Paris-Sud, Orsay, France (PHD)

Education History

University of Paris-Sud, Orsay, France

PHD

Publications

Justin Reverdi, Sixin Zhang, Saïd Aoues, Fabrice Gamboa, Serge Gratton, Thomas Pellegrini
CNN-based Compressor Mass Flow Estimator in Industrial Aircraft Vapor Cycle System. CoRR (2024)
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
IRIT-MFU Multi-modal systems for emotion classification for Odyssey 2024 challenge. Odyssey (2024)
Etienne Labbé, Thomas Pellegrini, Julien Pinquier
CoNeTTE: An Efficient Audio Captioning System Leveraging Multiple Datasets With Task Embedding. IEEE ACM Trans. Audio Speech Lang. Process. 32 (2024)
Lionel Pibre, Francisco Madrigal, Cyrille Equoy, Frédéric Lerasle, Thomas Pellegrini, Julien Pinquier, Isabelle Ferrané
Audio-video fusion strategies for active speaker detection in meetings. Multim. Tools Appl. 82 (9) (2023)
Matéo Cousin, Etienne Labbé, Thomas Pellegrini
Multilingual Audio Captioning using machine translated data. CoRR (2023)
Thomas Pellegrini, Ismail Khalfaoui Hassani, Etienne Labbé, Timothée Masquelier
Adapting a ConvNeXt model to audio classification on AudioSet. CoRR (2023)
Ismail Khalfaoui Hassani, Timothée Masquelier, Thomas Pellegrini
Audio classification with Dilated Convolution with Learnable Spacings. CoRR (2023)
Lucile Gelin, Morgane Daniel, Thomas Pellegrini, Julien Pinquier
Comparing phoneme recognition systems on the detection and diagnosis of reading mistakes for young children's oral reading evaluation. SLaTE (2023)
Etienne Labbé, Thomas Pellegrini, Julien Pinquier
Killing two birds with one stone: Can an audio captioning system also be used for audio-text retrieval? CoRR (2023)
Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothée Masquelier
Dilated Convolution with Learnable Spacings: beyond bilinear interpolation. CoRR (2023)
Thomas Pellegrini, Ismail Khalfaoui Hassani, Etienne Labbé, Timothée Masquelier
Adapting a ConvNeXt Model to Audio Classification on AudioSet. INTERSPEECH (2023)
Etienne Labbé, Julien Pinquier, Thomas Pellegrini
Multitask Learning in Audio Captioning: A Sentence Embedding Regression Loss Acts as a Regularizer. EUSIPCO (2023)
Etienne Labbé, Thomas Pellegrini, Julien Pinquier
CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding. CoRR (2023)
Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothée Masquelier
Dilated convolution with learnable spacings. ICLR (2023)
Etienne Labbé, Julien Pinquier, Thomas Pellegrini
Multitask learning in Audio Captioning: a sentence embedding regression loss acts as a regularizer. CoRR (2023)
Thomas Pellegrini
Language-Based Audio Retrieval with Textual Embeddings of Tag Names. DCASE (2022)
Léo Cances, Etienne Labbé, Thomas Pellegrini
Comparison of semi-supervised deep learning algorithms for audio classification. EURASIP J. Audio Speech Music. Process. 2022 (1) (2022)
Etienne Labbé, Thomas Pellegrini, Julien Pinquier
Is my Automatic Audio Captioning System so Bad? SPIDEr-max: A Metric to Consider Several Caption Candidates. DCASE (2022)
Etienne Labbé, Thomas Pellegrini, Julien Pinquier
Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates. CoRR (2022)
Lionel Pibre, Francisco Madrigal, Cyrille Equoy, Frédéric Lerasle, Thomas Pellegrini, Julien Pinquier, Isabelle Ferrané
Audio-video fusion strategies for active speaker detection in meetings. CoRR (2022)
Chems-Eddine Himeur, Thibault Lejemble, Thomas Pellegrini, Mathias Paulin, Loic Barthe, Nicolas Mellado
PCEDNet: A Lightweight Neural Network for Fast and Interactive Edge Detection in 3D Point Clouds. ACM Trans. Graph. 41 (1) (2022)
Thomas Pellegrini, Romain Zimmer, Timothée Masquelier
Low-Activity Supervised Convolutional Spiking Neural Networks Applied to Speech Commands Recognition. SLT (2021)
Lucile Gelin, Morgane Daniel, Julien Pinquier, Thomas Pellegrini
End-to-end acoustic modelling for phone recognition of young readers. Speech Commun. 134 (2021)
Léo Cances, Etienne Labbé, Thomas Pellegrini
Improving Deep-learning-based Semi-supervised Audio Tagging with Mixup. CoRR (2021)
Thomas Pellegrini, Timothée Masquelier
Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning. CoRR (2021)
Léo Cances, Thomas Pellegrini
Comparison of Deep Co-Training and Mean-Teacher Approaches for Semi-Supervised Audio Tagging. ICASSP (2021)
Lionel Pibre, Sélim Mechrouh, Thomas Pellegrini, Julien Pinquier, Isabelle Ferrané
Automatic macro segmentation into interaction sequence: a silence-based approach for meeting structuring. CBMI (2021)
Lucile Gelin, Morgane Daniel, Julien Pinquier, Thomas Pellegrini
End-to-end acoustic modelling for phone recognition of young readers. CoRR (2021)
Thomas Pellegrini
Deep-Learning-Based Central African Primate Species Classification with MixUp and SpecAugment. Interspeech (2021)
Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothée Masquelier
Dilated convolution with learnable spacings. CoRR (2021)
Lucile Gelin, Thomas Pellegrini, Julien Pinquier, Morgane Daniel
Simulating Reading Mistakes for Child Speech Transformer-Based Phone Recognition. Interspeech (2021)
Lila Gravellier, Julie Hunter, Philippe Muller, Thomas Pellegrini, Isabelle Ferrané
Weakly supervised discourse segmentation for multiparty oral conversations. EMNLP (1) (2021)
Thomas Pellegrini, Timothée Masquelier
Fast Threshold Optimization for Multi-Label Audio Tagging Using Surrogate Gradient Learning. ICASSP (2021)
Cédric Gendrot, Emmanuel Ferragne, Thomas Pellegrini
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) (2020)
Lucile Gelin, Morgane Daniel, Thomas Pellegrini, Julien Pinquier
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) (2020)
Thomas Pellegrini
Deep learning with weakly-annotated data: a sound event detection use case (and hate speech detection here and there) (abstract). TWSDetection (2020)
Thomas Pellegrini, Romain Zimmer, Timothée Masquelier
Low-activity supervised convolutional spiking neural networks applied to speech commands recognition. CoRR (2020)
Chems-Eddine Himeur, Thibault Lejemble, Thomas Pellegrini, Mathias Paulin, Loic Barthe, Nicolas Mellado
PCEDNet : A Neural Network for Fast and Efficient Edge Detection in 3D Point Clouds. CoRR (2020)
Léo Cances, Patrice Guyot, Thomas Pellegrini
Evaluation of Post-Processing Algorithms for Polyphonic Sound Event Detection. WASPAA (2019)
Thomas Pellegrini, Léo Cances
Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection. CoRR (2019)
Abdelwahab Heba, Thomas Pellegrini, Jean-Pierre Lorré, Régine André-Obrecht
Char+CV-CTC: Combining Graphemes and Consonant/Vowel Units for CTC-Based ASR Using Multitask Learning. INTERSPEECH (2019)
Romain Zimmer, Thomas Pellegrini, Srisht Fateh Singh, Timothée Masquelier
Technical report: supervised training of convolutional spiking neural networks with PyTorch. CoRR (2019)
Thomas Pellegrini, Jérôme Farinas, Estelle Delpech, François Lancelot
The Airbus Air Traffic Control Speech Recognition 2018 Challenge: Towards ATC Automatic Transcription and Call Sign Detection. INTERSPEECH (2019)
Jonathan Mamou, Thomas Pellegrini, Denis Kouamé, Adrian Basarab
A Convolutional Neural Network for 250-MHz Quantitative Acoustic-microscopy Resolution Enhancement. EMBC (2019)
Thomas Pellegrini, Léo Cances
Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection. IJCNN (2019)
Léo Cances, Patrice Guyot, Thomas Pellegrini
Evaluation of post-processing algorithms for polyphonic sound event detection. CoRR (2019)
Sarah Cosentino, Estelle I. S. Randria, Jia-Yeu Lin, Thomas Pellegrini, Salvatore Sessa, Atsuo Takanishi
Group emotion recognition strategies for entertainment robots. IROS (2018)
Thomas Pellegrini, Jérôme Farinas, Estelle Delpech, François Lancelot
The Airbus Air Traffic Control speech recognition 2018 challenge: towards ATC automatic transcription and call sign detection. CoRR (2018)
Léo Cances, Thomas Pellegrini, Patrice Guyot
Sound event detection from weak annotations: weighted-GRU versus multi-instance-learning. DCASE (2018)
Thomas Pellegrini
Densely Connected CNNs for Bird Audio Detection. CoRR (2018)
Christine Sénac, Thomas Pellegrini, Florian Mouret, Julien Pinquier
Music Feature Maps with Convolutional Neural Networks for Music Genre Classification. CBMI (2017)
Thomas Pellegrini
Densely connected CNNs for bird audio detection. EUSIPCO (2017)
Céline Manenti, Thomas Pellegrini, Julien Pinquier
Unsupervised Speech Unit Discovery Using K-means and Neural Networks. SLSP (2017)
Abdelwahab Heba, Thomas Pellegrini, Tom Jorquera, Régine André-Obrecht, Jean-Pierre Lorré
Lexical Emphasis Detection in Spoken French Using F-BANKs and Neural Networks. SLSP (2017)
Thomas Pellegrini, Sandrine Mouysset
Inferring Phonemic Classes from CNN Activation Maps Using Clustering Techniques. INTERSPEECH (2016)
Marwa Thlithi, Julien Pinquier, Thomas Pellegrini, Régine André-Obrecht
Filterbank coefficients selection for segmentation in singer turns. CBMI (2016)
Vincent Laborde, Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Halima Sahraoui, Jérôme Farinas
Pronunciation Assessment of Japanese Learners of French with GOP Scores and Phonetic Information. INTERSPEECH (2016)
Céline Manenti, Thomas Pellegrini, Julien Pinquier
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) (2016)
Thomas Pellegrini, Lionel Fontan, Halima Sahraoui
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) (2016)
Patrice Guyot, Alice Eldridge, Ying Chen Eyre-Walker, Alison Johnston, Thomas Pellegrini, Mika Peck
Sinusoidal Modelling for Ecoacoustics. INTERSPEECH (2016)
Céline Manenti, Thomas Pellegrini, Julien Pinquier
CNN-Based Phone Segmentation Experiments in a Less-Represented Language. INTERSPEECH (2016)
Vincent Bragard, Thomas Pellegrini, Julien Pinquier
Pyc2Sound: a Python tool to convert images into sound. Audio Mostly Conference (2015)
Lionel Fontan, Thomas Pellegrini, Julia Olcoz, Alberto Abad
Predicting disordered speech comprehensibility from Goodness of Pronunciation scores. SLPAT@Interspeech (2015)
Thomas Pellegrini, Valentin Barrière
Time-continuous Estimation of Emotion in Music with Recurrent Neural Networks. MediaEval (2015)
Thomas Pellegrini
Comparing SVM, softmax, and shallow neural networks for eating condition classification. INTERSPEECH (2015)
Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Jérôme Farinas, Charlotte Alazard-Guiu, Marina Robert, Peggy Gatignol
Automatic Assessment of Speech Capability Loss in Disordered Speech. ACM Trans. Access. Comput. 6 (3) (2015)
Annika Hämäläinen, Hugo Meinedo, Michael Tjalve, Thomas Pellegrini, Isabel Trancoso, Miguel Sales Dias
Improving Speech Recognition through Automatic Selection of Age Group - Specific Acoustic Models. PROPOR (2014)
Thomas Pellegrini, Patrice Guyot, Baptiste Angles, Christophe Mollaret, Christophe Mangou
Towards soundpainting gesture recognition. Audio Mostly Conference (2014)
Annika Hämäläinen, Sara Candeias, Hyongsil Cho, Hugo Meinedo, Alberto Abad, Thomas Pellegrini, Michael Tjalve, Isabel Trancoso, Miguel Sales Dias
Correlating ASR errors with developmental changes in speech production: a study of 3-10-year-old European Portuguese children's speech. WOCCI (2014)
Thomas Pellegrini, Vahid Hedayati, Ângela Costa
El-WOZ: a client-server wizard-of-oz interface. LREC (2014)
Annika Hämäläinen, Hyongsil Cho, Sara Candeias, Thomas Pellegrini, Alberto Abad, Michael Tjalve, Isabel Trancoso, Miguel Sales Dias
Automatically Recognising European Portuguese Children's Speech - Pronunciation Patterns Revealed by an Analysis of ASR Errors. PROPOR (2014)
Thomas Pellegrini, Vahid Hedayati, Isabel Trancoso, Annika Hämäläinen, Miguel Sales Dias
Speaker age estimation for elderly speech recognition in European Portuguese. INTERSPEECH (2014)
Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Jérôme Farinas, Marina Robert
The goodness of pronunciation algorithm applied to disordered speech. INTERSPEECH (2014)
Marwa Thlithi, Thomas Pellegrini, Julien Pinquier, Régine André-Obrecht
Segmentation in singer turns with the Bayesian information criterion. INTERSPEECH (2014)
Thomas Pellegrini, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede, Maxine Eskénazi
ASR-based exercises for listening comprehension practice in European Portuguese. Comput. Speech Lang. 27 (5) (2013)
Thomas Pellegrini, Annika Hämäläinen, Philippe Boula de Mareüil, Michael Tjalve, Isabel Trancoso, Sara Candeias, Miguel Sales Dias, Daniela Braga
A corpus-based study of elderly and young speakers of European Portuguese: acoustic correlates and their impact on speech recognition performance. INTERSPEECH (2013)
Thomas Pellegrini, Isabel Trancoso, Annika Hämäläinen, António Calado, Miguel Sales Dias, Daniela Braga
Impact of Age in ASR for the Elderly: Preliminary Experiments in European Portuguese. IberSPEECH (2012)
Thomas Pellegrini, Ângela Costa, Isabel Trancoso
Less errors with TTS? A dictation experiment with foreign language learners. INTERSPEECH (2012)
Thomas Pellegrini, Wang Ling, André Silva, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
f. CSEDU (2) (2012)
Rui Correia, Thomas Pellegrini, Maxine Eskénazi, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
Listening comprehension games for portuguese: exploring the best features. SLaTE (2011)
Virginia Barbosa, Thomas Pellegrini, Miguel Bugalho, Isabel Trancoso
Browsing videos by automatically detected audio events. EUROCON (2011)
Thomas Pellegrini, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
Automatic Generation of Listening Comprehension Learning Material in European Portuguese. INTERSPEECH (2011)
José Lopes, Isabel Trancoso, Rui Correia, Thomas Pellegrini, Hugo Meinedo, Nuno J. Mamede, Maxine Eskénazi
Multimedia learning materials. SLT (2010)
Thomas Pellegrini, Isabel Trancoso
Improving ASR error detection with non-decoder based features. INTERSPEECH (2010)
Alberto Abad, Thomas Pellegrini, Isabel Trancoso, João Paulo Neto
Context dependent modelling approaches for hybrid speech recognizers. INTERSPEECH (2010)
Isabel Trancoso, Thomas Pellegrini, José Portelo, Hugo Meinedo, Miguel Bugalho, Alberto Abad, João Paulo Neto
Audio contributions to semantic video search. ICME (2009)
Thomas Pellegrini, Isabel Trancoso
Error Detection in Broadcast News ASR Using Markov Chains. LTC (2009)
Thomas Pellegrini, Lori Lamel
Automatic Word Decompounding for ASR in a Morphologically Rich Language: Application to Amharic. IEEE Trans. Speech Audio Process. 17 (5) (2009)
Miguel Bugalho, José Portelo, Isabel Trancoso, Thomas Pellegrini, Alberto Abad
Detecting audio events for semantic video search. INTERSPEECH (2009)
Thomas Pellegrini, Lori Lamel
Are audio or textual training data more important for ASR in less-represented languages? SLTU (2008)
Martine Adda-Decker, Thomas Pellegrini, Éric Bilinski, Gilles Adda
Developments of "Lëtzebuergesch" Resources for Automatic Speech Processing and Linguistic Studies. LREC (2008)
Thomas Pellegrini, Lori Lamel
Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language. INTERSPEECH (2007)
Thomas Pellegrini, Lori Lamel
Experimental detection of vowel pronunciation variants in Amharic. LREC (2006)
Thomas Pellegrini, Lori Lamel
Investigating automatic decomposition for ASR in less represented languages. INTERSPEECH (2006)

Thomas Pellegrini.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Thomas Pellegrini