Disentangling Intermediate Representations in Sound-to-Event DNNs using Invertible Flow Models. Tim Dick, Alexia Briassouli, Enrique Hortal Quesada and Elia Formisano (submitted)
Audio-Language Datasets of Scenes and Events: A Survey. Gijs Wijngaard, Elia Formisano, Michele Esposito, Michel Dumontier (2024) arXiv:2407.06947v1 https://arxiv.org/abs/2407.06947#
Bridging Auditory Perception and Natural Language Processing with Semantically informed Deep Neural Networks. Michele Esposito, Giancarlo Valente, Yenisel Plasencia-Calaña, Michel Dumontier, Bruno L. Giordano, and Elia Formisano (2024) bioRxiv 2024.04.29.591634. https://www.biorxiv.org/content/10.1101/2024.04.29.591634v1
ACES: Evaluating Automated Audio Captioning Models on the Semantics of Sounds. Gijs Wijngaard and Elia Formisano and Bruno L. Giordano and Michel Dumontier (2024) arXiv, 2403.18572. https://arxiv.org/abs/2403.18572
Intermediate acoustic-to-semantic representations link behavioural and neural responses to natural sounds. Bruno L. Giordano, Michele Esposito, Giancarlo Valente, Elia Formisano (2023) Nature Neuroscience, 26(4):664-672. https://www.nature.com/articles/s41593-023-01285-9
What do we mean with sound semantics, exactly? A survey of taxonomies and ontologies of everyday sounds. Giordano BL, de Miranda Azevedo R, Plasencia-Calaña Y, Formisano E*, Dumontier M* (2022) Front Psychol. 2022 Sep 29;13:964209. https://doi.org/10.3389/fpsyg.2022.964209
Conference proceedings
ACES: Evaluating automated audio captioning models on the semantics of sounds Wijngaard G, Formisano E, Giordano B, Dumontier M, ACES: Evaluating automated audio captioning models on the semantics of sounds. Accepted at 31st European Signal Processing Conference, (EUSIPCO 2023) https://ieeexplore.ieee.org/abstract/document/10289793
Semantically informed deep neural networks for sound recognition. Michele Esposito, Giancarlo Valente, Yeni Plasencia-Calana, Bruno L. Giordanoand Elia Formisano. Presented at IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023), Session: “Synergy between human and machine approaches to sound/scene recognition and processing” https://ieeexplore.ieee.org/document/10095606
Conference abstracts/posters/presentations
Semantically informed deep neural networks for sound recognition. Michele Esposito, Giancarlo Valente, Yeni Plasencia-Calana, Bruno L. Giordanoand Elia Formisano. (Poster presented at International Conference on Auditory Cortex 2022)
Intermediate acoustic-to-semantic representations link behavioural and neural responses to natural sounds. Bruno L. Giordano, Michele Esposito, Giancarlo Valente, Elia Formisano (Poster presented at ICAC 2022)
Master Theses
Research Master Cognitive Neuroscience: The Influence of Semantics on Neural Models of Sound Recognition. Martin Bremm, (supervision: Formisano, Dumontier)