Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2505.14142 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915523420225536 |
|---|---|
| author | Wijngaard, Gijs Formisano, Elia Esposito, Michele Dumontier, Michel |
| author_facet | Wijngaard, Gijs Formisano, Elia Esposito, Michele Dumontier, Michel |
| contents | 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 semantics inspired by human cognition. To support this, we introduce AudSem, a novel dataset specifically curated for semantic descriptor reasoning in audio-language models. AudSem addresses the persistent challenge of data contamination in zero-shot evaluations by providing a carefully filtered collection of audio samples paired with captions generated through a robust multi-stage pipeline. Our experiments demonstrate that AudSemThinker outperforms state-of-the-art models across multiple training settings, highlighting its strength in semantic audio reasoning. Both AudSemThinker and the AudSem dataset are released publicly. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_14142 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound Wijngaard, Gijs Formisano, Elia Esposito, Michele Dumontier, Michel Sound Audio and Speech Processing 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 semantics inspired by human cognition. To support this, we introduce AudSem, a novel dataset specifically curated for semantic descriptor reasoning in audio-language models. AudSem addresses the persistent challenge of data contamination in zero-shot evaluations by providing a carefully filtered collection of audio samples paired with captions generated through a robust multi-stage pipeline. Our experiments demonstrate that AudSemThinker outperforms state-of-the-art models across multiple training settings, highlighting its strength in semantic audio reasoning. Both AudSemThinker and the AudSem dataset are released publicly. |
| title | AudSemThinker: Enhancing Audio-Language Models through Reasoning over Semantics of Sound |
| topic | Sound Audio and Speech Processing |
| url | https://arxiv.org/abs/2505.14142 |