3 papers
cs.SD2025
AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound
Gijs Wijngaard, Elia Formisano, Michele Esposito +1
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…
cs.SD2025
Data-Balanced Curriculum Learning for Audio Question Answering
Gijs Wijngaard, Elia Formisano, Michele Esposito +1
Audio question answering (AQA) requires models to understand acoustic content and perform complex reasoning. Current models struggle with dataset imbalances and unstable training d…
cs.SD2025
Audio-Language Datasets of Scenes and Events: A Survey
Gijs Wijngaard, Elia Formisano, Michele Esposito +1
Audio-language models (ALMs) generate linguistic descriptions of sound-producing events and scenes. Advances in dataset creation and computational power have led to significant pro…