Elia Formisano — accepted AI-conference papers

2025

AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound

Gijs Wijngaard, Elia Formisano, Michele Esposito, Michel Dumontier

NeurIPS 2025poster

Audio-language models have shown promising results in various sound understanding tasks, yet they remain limited in their ability to reason over the fine-grained semantics of sound. In this paper, we present AudSemThinker, a model whose reasoning is structured around a framework of auditory semantic…

Cited by 0 Source ↗code ↗Scholar ↗

2023

Semantically-Informed Deep Neural Networks For Sound Recognition

Michele Esposito, Giancarlo Valente, Yenisel Plasencia Calaña, Michel Dumontier, Bruno L. Giordano, Elia Formisano

ICASSP 2023accepted

Deep neural networks (DNNs) for sound recognition learn to categorize a barking sound as a "dog" and a meowing sound as a "cat" but do not exploit information inherent to the semantic relations between classes (e.g., both are animal vocalisations). Cognitive neuroscience research, however, suggests…

Cited by 0 Source ↗Scholar ↗