Skip to content

Thomas Pellegrini

Publication record assembled from the DBLP archive of ranked conferences.

Papers indexed

37

Venues

9

Active years

2006–2025

Best venue rank

A*

Where they publish

Papers

37 indexed papers, newest first.

YearVenueTitleAuthors
2025ICASSPHierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging.Ludovic Tuncay, Etienne Labb, Thomas Pellegrini
2024InterspeechSpecializing Self-Supervised Speech Representations for Speaker Segmentation.Sverin Baroudi, Thomas Pellegrini, Herv Bredin
2024InterspeechSelf-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning.Lucas Block Medin, Thomas Pellegrini, Lucile Gelin
2023ICLRDilated convolution with learnable spacings.Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothe Masquelier
2023InterspeechAdapting a ConvNeXt Model to Audio Classification on AudioSet.Thomas Pellegrini, Ismail Khalfaoui Hassani, Etienne Labb, Timothe Masquelier
2021CBMIAutomatic macro segmentation into interaction sequence: a silence-based approach for meeting structuring.Lionel Pibre, Slim Mechrouh, Thomas Pellegrini, Julien Pinquier, Isabelle Ferran
2021EMNLPWeakly supervised discourse segmentation for multiparty oral conversations.Lila Gravellier, Julie Hunter, Philippe Muller, Thomas Pellegrini, Isabelle Ferran
2021ICASSPComparison of Deep Co-Training and Mean-Teacher Approaches for Semi-Supervised Audio Tagging.Lo Cances, Thomas Pellegrini
2021ICASSPFast Threshold Optimization for Multi-Label Audio Tagging Using Surrogate Gradient Learning.Thomas Pellegrini, Timothe Masquelier
2021InterspeechSimulating Reading Mistakes for Child Speech Transformer-Based Phone Recognition.Lucile Gelin, Thomas Pellegrini, Julien Pinquier, Morgane Daniel
2021InterspeechDeep-Learning-Based Central African Primate Species Classification with MixUp and SpecAugment.Thomas Pellegrini
2019IJCNNCosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection.Thomas Pellegrini, Lo Cances
2019InterspeechChar+CV-CTC: Combining Graphemes and Consonant/Vowel Units for CTC-Based ASR Using Multitask Learning.Abdelwahab Heba, Thomas Pellegrini, Jean-Pierre Lorr, Rgine Andr-Obrecht
2019InterspeechThe Airbus Air Traffic Control Speech Recognition 2018 Challenge: Towards ATC Automatic Transcription and Call Sign Detection.Thomas Pellegrini, Jrme Farinas, Estelle Delpech, Franois Lancelot
2018IROSGroup emotion recognition strategies for entertainment robots.Sarah Cosentino, Estelle I. S. Randria, Jia-Yeu Lin, Thomas Pellegrini, Salvatore Sessa, Atsuo Takanishi
2017CBMIMusic Feature Maps with Convolutional Neural Networks for Music Genre Classification.Christine Snac, Thomas Pellegrini, Florian Mouret, Julien Pinquier
2016CBMIFilterbank coefficients selection for segmentation in singer turns.Marwa Thlithi, Julien Pinquier, Thomas Pellegrini, Rgine Andr-Obrecht
2016InterspeechSinusoidal Modelling for Ecoacoustics.Patrice Guyot, Alice Eldridge, Ying Chen Eyre-Walker, Alison Johnston, Thomas Pellegrini, Mika Peck
2016InterspeechPronunciation Assessment of Japanese Learners of French with GOP Scores and Phonetic Information.Vincent Laborde, Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Halima Sahraoui, Jrme Farinas
2016InterspeechCNN-Based Phone Segmentation Experiments in a Less-Represented Language.Cline Manenti, Thomas Pellegrini, Julien Pinquier
2016InterspeechInferring Phonemic Classes from CNN Activation Maps Using Clustering Techniques.Thomas Pellegrini, Sandrine Mouysset
2015InterspeechComparing SVM, softmax, and shallow neural networks for eating condition classification.Thomas Pellegrini
2014InterspeechThe goodness of pronunciation algorithm applied to disordered speech.Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Jrme Farinas, Marina Robert
2014InterspeechSpeaker age estimation for elderly speech recognition in European Portuguese.Thomas Pellegrini, Vahid Hedayati, Isabel Trancoso, Annika Hmlinen, Miguel Sales Dias
2014InterspeechSegmentation in singer turns with the Bayesian information criterion.Marwa Thlithi, Thomas Pellegrini, Julien Pinquier, Rgine Andr-Obrecht
2014LRECEl-WOZ: a client-server wizard-of-oz interface.Thomas Pellegrini, Vahid Hedayati, ngela Costa
2013InterspeechA corpus-based study of elderly and young speakers of European Portuguese: acoustic correlates and their impact on speech recognition performance.Thomas Pellegrini, Annika Hmlinen, Philippe Boula de Mareil, Michael Tjalve, Isabel Trancoso, Sara Candeias, Miguel Sales Dias, Daniela Braga
2012CSEDUOverview of Computer-assisted Language Learning for European Portuguese at LThomas Pellegrini, Wang Ling, Andr Silva, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
2012InterspeechLess errors with TTS? A dictation experiment with foreign language learners.Thomas Pellegrini, ngela Costa, Isabel Trancoso
2011InterspeechAutomatic Generation of Listening Comprehension Learning Material in European Portuguese.Thomas Pellegrini, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede
2010InterspeechContext dependent modelling approaches for hybrid speech recognizers.Alberto Abad, Thomas Pellegrini, Isabel Trancoso, Joo Paulo Neto
2010InterspeechImproving ASR error detection with non-decoder based features.Thomas Pellegrini, Isabel Trancoso
2009InterspeechDetecting audio events for semantic video search.Miguel M. F. Bugalho, Jos Portelo, Isabel Trancoso, Thomas Pellegrini, Alberto Abad
2008LRECDevelopments of "Ltzebuergesch" Resources for Automatic Speech Processing and Linguistic Studies.Martine Adda-Decker, Thomas Pellegrini, ric Bilinski, Gilles Adda
2007InterspeechUsing phonetic features in unsupervised word decompounding for ASR with application to a less-represented language.Thomas Pellegrini, Lori Lamel
2006InterspeechInvestigating automatic decomposition for ASR in less represented languages.Thomas Pellegrini, Lori Lamel
2006LRECExperimental detection of vowel pronunciation variants in Amharic.Thomas Pellegrini, Lori Lamel