| 2025 | ICASSP | Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging. | Ludovic Tuncay, Etienne Labb, Thomas Pellegrini |
| 2024 | Interspeech | Specializing Self-Supervised Speech Representations for Speaker Segmentation. | Sverin Baroudi, Thomas Pellegrini, Herv Bredin |
| 2024 | Interspeech | Self-Supervised Models for Phoneme Recognition: Applications in Children's Speech for Reading Learning. | Lucas Block Medin, Thomas Pellegrini, Lucile Gelin |
| 2023 | ICLR | Dilated convolution with learnable spacings. | Ismail Khalfaoui Hassani, Thomas Pellegrini, Timothe Masquelier |
| 2023 | Interspeech | Adapting a ConvNeXt Model to Audio Classification on AudioSet. | Thomas Pellegrini, Ismail Khalfaoui Hassani, Etienne Labb, Timothe Masquelier |
| 2021 | CBMI | Automatic macro segmentation into interaction sequence: a silence-based approach for meeting structuring. | Lionel Pibre, Slim Mechrouh, Thomas Pellegrini, Julien Pinquier, Isabelle Ferran |
| 2021 | EMNLP | Weakly supervised discourse segmentation for multiparty oral conversations. | Lila Gravellier, Julie Hunter, Philippe Muller, Thomas Pellegrini, Isabelle Ferran |
| 2021 | ICASSP | Comparison of Deep Co-Training and Mean-Teacher Approaches for Semi-Supervised Audio Tagging. | Lo Cances, Thomas Pellegrini |
| 2021 | ICASSP | Fast Threshold Optimization for Multi-Label Audio Tagging Using Surrogate Gradient Learning. | Thomas Pellegrini, Timothe Masquelier |
| 2021 | Interspeech | Simulating Reading Mistakes for Child Speech Transformer-Based Phone Recognition. | Lucile Gelin, Thomas Pellegrini, Julien Pinquier, Morgane Daniel |
| 2021 | Interspeech | Deep-Learning-Based Central African Primate Species Classification with MixUp and SpecAugment. | Thomas Pellegrini |
| 2019 | IJCNN | Cosine-similarity penalty to discriminate sound classes in weakly-supervised sound event detection. | Thomas Pellegrini, Lo Cances |
| 2019 | Interspeech | Char+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 |
| 2019 | Interspeech | The Airbus Air Traffic Control Speech Recognition 2018 Challenge: Towards ATC Automatic Transcription and Call Sign Detection. | Thomas Pellegrini, Jrme Farinas, Estelle Delpech, Franois Lancelot |
| 2018 | IROS | Group emotion recognition strategies for entertainment robots. | Sarah Cosentino, Estelle I. S. Randria, Jia-Yeu Lin, Thomas Pellegrini, Salvatore Sessa, Atsuo Takanishi |
| 2017 | CBMI | Music Feature Maps with Convolutional Neural Networks for Music Genre Classification. | Christine Snac, Thomas Pellegrini, Florian Mouret, Julien Pinquier |
| 2016 | CBMI | Filterbank coefficients selection for segmentation in singer turns. | Marwa Thlithi, Julien Pinquier, Thomas Pellegrini, Rgine Andr-Obrecht |
| 2016 | Interspeech | Sinusoidal Modelling for Ecoacoustics. | Patrice Guyot, Alice Eldridge, Ying Chen Eyre-Walker, Alison Johnston, Thomas Pellegrini, Mika Peck |
| 2016 | Interspeech | Pronunciation Assessment of Japanese Learners of French with GOP Scores and Phonetic Information. | Vincent Laborde, Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Halima Sahraoui, Jrme Farinas |
| 2016 | Interspeech | CNN-Based Phone Segmentation Experiments in a Less-Represented Language. | Cline Manenti, Thomas Pellegrini, Julien Pinquier |
| 2016 | Interspeech | Inferring Phonemic Classes from CNN Activation Maps Using Clustering Techniques. | Thomas Pellegrini, Sandrine Mouysset |
| 2015 | Interspeech | Comparing SVM, softmax, and shallow neural networks for eating condition classification. | Thomas Pellegrini |
| 2014 | Interspeech | The goodness of pronunciation algorithm applied to disordered speech. | Thomas Pellegrini, Lionel Fontan, Julie Mauclair, Jrme Farinas, Marina Robert |
| 2014 | Interspeech | Speaker age estimation for elderly speech recognition in European Portuguese. | Thomas Pellegrini, Vahid Hedayati, Isabel Trancoso, Annika Hmlinen, Miguel Sales Dias |
| 2014 | Interspeech | Segmentation in singer turns with the Bayesian information criterion. | Marwa Thlithi, Thomas Pellegrini, Julien Pinquier, Rgine Andr-Obrecht |
| 2014 | LREC | El-WOZ: a client-server wizard-of-oz interface. | Thomas Pellegrini, Vahid Hedayati, ngela Costa |
| 2013 | Interspeech | A 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 |
| 2012 | CSEDU | Overview of Computer-assisted Language Learning for European Portuguese at L | Thomas Pellegrini, Wang Ling, Andr Silva, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede |
| 2012 | Interspeech | Less errors with TTS? A dictation experiment with foreign language learners. | Thomas Pellegrini, ngela Costa, Isabel Trancoso |
| 2011 | Interspeech | Automatic Generation of Listening Comprehension Learning Material in European Portuguese. | Thomas Pellegrini, Rui Correia, Isabel Trancoso, Jorge Baptista, Nuno J. Mamede |
| 2010 | Interspeech | Context dependent modelling approaches for hybrid speech recognizers. | Alberto Abad, Thomas Pellegrini, Isabel Trancoso, Joo Paulo Neto |
| 2010 | Interspeech | Improving ASR error detection with non-decoder based features. | Thomas Pellegrini, Isabel Trancoso |
| 2009 | Interspeech | Detecting audio events for semantic video search. | Miguel M. F. Bugalho, Jos Portelo, Isabel Trancoso, Thomas Pellegrini, Alberto Abad |
| 2008 | LREC | Developments of "Ltzebuergesch" Resources for Automatic Speech Processing and Linguistic Studies. | Martine Adda-Decker, Thomas Pellegrini, ric Bilinski, Gilles Adda |
| 2007 | Interspeech | Using phonetic features in unsupervised word decompounding for ASR with application to a less-represented language. | Thomas Pellegrini, Lori Lamel |
| 2006 | Interspeech | Investigating automatic decomposition for ASR in less represented languages. | Thomas Pellegrini, Lori Lamel |
| 2006 | LREC | Experimental detection of vowel pronunciation variants in Amharic. | Thomas Pellegrini, Lori Lamel |