Articles 

Conference proceedings

  • AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound. Wijngaard G, Formisano E, Esposito M, Dumontier M. Accepted at NeurIPS2025. Preprint: arXiv:2505.14142
  • 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. Giordano and 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

  • Evaluating the impact of multiscale temporal processing on sound-to-event recurrent neural networks. Michele Esposito, Bruno, L. Giordano, Giancarlo Valente, Elia Formisano (Poster Presented at Cognitive Computational Neuroscience, August 6–9, 2024, Boston, Massachusetts)
  • Disentangling Intermediate Representations in Sound-to-Event DNNs using Invertible Flow Models. Tim Dick, Enrique Hortal Quesada, Alexia Briassouli, Elia Formisano (Poster Presented at Cognitive Computational Neuroscience, August 6–9, 2024, Boston, Massachusetts)
  • Optimal stimulus selection for dissociating acoustic and semantic processing of natural sounds. Maria Araújo Vitoria, Marie Plegat, Giorgio Marinato, Michele Esposito, Christian Herff, Bruno L. Giordano, Elia Formisano (Poster Presented at Cognitive Computational Neuroscience, August 6–9, 2024, Boston, Massachusetts)
  • Semantically informed deep neural networks for sound recognition. Michele Esposito, Giancarlo Valente, Yeni Plasencia-Calana, Bruno L. Giordano and 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

  • 2023-2024: Master Data Science for Decision Making. How do we recognize auditory events? Disentangling intermediate representations in the acoustic-to-semantic transformation. Tim Dick (supervision: Formisano, Briassouli, Quesada) (2024 Master program’s best thesis award)
  • 2021-2022: Research Master Cognitive Neuroscience: The Influence of Semantics on Neural Models of Sound Recognition. Martin Bremm, (supervision: Formisano, Dumontier)
  • 2020-2021: Research Master Cognitive Neuroscience:  Opening the Black Box: Interpreting a Neural Network for Semantic Sound Recognition Using Layer-wise Relevance Propagation. Anna Vorreuther  (supervision, Formisano, Valente)