Search - ANR - Agence nationale de la recherche Access content directly

Filter your results

15 Results
ANR project: Code decision (reference) : ANR-18-CE23-0005
Image document

Fast threshold optimization for multi-label audio tagging using Surrogate gradient learning

Thomas Pellegrini , Timothée Masquelier
IEEE International Conference on Acoustics, Speech and Signal Processing, Jun 2021, Toronto, Canada. pp. 651-655, ⟨10.1109/ICASSP39728.2021.9414091⟩
Conference papers hal-03153644v1
Image document

Low-activity supervised convolutional spiking neural networks applied to speech commands recognition

Thomas Pellegrini , Romain Zimmer , Timothée Masquelier
IEEE Spoken Language Technology Workshop 2021, Jan 2021, Shenzhen (virtual), France. pp. 97-103, ⟨10.1109/SLT48900.2021.9383587⟩
Conference papers hal-03007620v1
Image document

Multitask learning in Audio Captioning: a sentence embedding regression loss acts as a regularizer

Etienne Labbé , Julien Pinquier , Thomas Pellegrini
31st European Signal Processing Conference (EUSIPCO 2023), Sep 2023, Helsinki, Finland. à paraître, ⟨10.48550/arXiv.2305.01482⟩
Conference papers hal-04207519v1

Adapting a ConvNeXt model to audio classification on AudioSet

Thomas Pellegrini , Ismail Khalfaoui-Hassani , Etienne Labbé , Timothée Masquelier
24th INTERSPEECH Conference (INTERSPEECH 2023), Aug 2023, Dublin, Ireland. à paraître
Conference papers hal-04114822v1

End-to-end acoustic modelling for phone recognition of young readers

Lucile Gelin , Morgane Daniel , Julien Pinquier , Thomas Pellegrini
Speech Communication, 2021, 134, pp.71-84. ⟨10.1016/j.specom.2021.08.003⟩
Journal articles hal-03373156v1
Image document

Killing two birds with a stone: can an audio captioning system also be used for audio-test retrieval?

Etienne Labbé , Thomas Pellegrini , Julien Pinquier
8th workshop on Detection and Classification of Acoustic Scenes and Events (DCASE2023), Sep 2023, Tampere, Finland. à paraître
Conference papers hal-04180972v1
Image document

Deep-learning-based central African primate species classification with MixUp and SpecAugment

Thomas Pellegrini
Interspeech 2021, Aug 2021, Brno, Czech Republic
Conference papers hal-03298384v1
Image document

Weakly supervised discourse segmentation for multiparty oral conversations

Lila Gravellier , Julie Hunter , Philippe Muller , Thomas Pellegrini , Isabelle Ferrané
2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021), ACL: Association for Computational Linguistics, Nov 2021, Punta Cana, Dominican Republic. pp.1381-1392
Conference papers hal-03466161v1
Image document

Comparison of Deep Co-Training and Mean-Teacher approaches for semi-supervised audio tagging

Léo Cances , Thomas Pellegrini
IEEE 46th International Conference on Acoustics, Speech and Signal Processing (ICASSP 2021), IEEE Signal Processing Society’s, Jun 2021, Toronto, Canada
Conference papers hal-03170277v1
Image document

CoNeTTE: An efficient Audio Captioning system leveraging multiple datasets with Task Embedding

Etienne Labbé , Thomas Pellegrini , Julien Pinquier
Preprints, Working Papers, ... hal-04193791v1
Image document

Is my automatic audio captioning system so bad? spider-max: a metric to consider several caption candidates

Etienne Labbé , Thomas Pellegrini , Julien Pinquier
Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2022), Nov 2022, Nancy, France
Conference papers hal-03810396v2
Image document

Towards phonetic interpretability in deep learning applied to voice comparison

Emmanuel Ferragne , Cédric Gendrot , Thomas Pellegrini
ICPhS, Aug 2019, Melbourne, Australia. pp.ISBN 978-0-646-80069-1
Conference papers halshs-02412948v1
Image document

Deep learning and voice comparison: phonetically-motivated vs. automatically-learned features

Cédric Gendrot , Emmanuel Ferragne , Thomas Pellegrini
ICPhS, Aug 2019, Melbourne, Australia
Conference papers halshs-02412947v1
Image document

Sound event detection from weak annotations: weighted-GRU versus multi-instance-learning

Léo Cances , Thomas Pellegrini , Patrice Guyot
Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018) - IEEE AASP 2018, Nov 2018, Surrey, United Kingdom. pp.64--68
Conference papers hal-02983147v1

Comparison of Semi-supervised Deep Learning Algorithms for Audio Classification

Léo Cances , Etienne Labbé , Thomas Pellegrini
EURASIP Journal on Audio, Speech, and Music Processing, 2022, 2022 (1, article 23), pp.1-14. ⟨10.1186/s13636-022-00255-6⟩
Journal articles hal-03855042v1