PolyBench: A Benchmark for Compositional Reasoning in Polyphonic Audio
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917327193243648 |
|---|---|
| author | Chen, Yuanjian Xiao, Yang Yin, Han Liu, Xubo Huang, Jinjie Dang, Ting |
| author_facet | Chen, Yuanjian Xiao, Yang Yin, Han Liu, Xubo Huang, Jinjie Dang, Ting |
| contents | Large Audio Language Models (LALMs) are increasingly capable of reasoning over audio. However, existing benchmarks provide limited coverage of reasoning in polyphonic audio, where multiple sound events co-occur and induce compositional structure. In this work, we introduce PolyBench, a benchmark designed to evaluate compositional reasoning in polyphonic audio. PolyBench comprises five evaluation subsets covering counting, classification, detection, concurrency, and duration estimation, requiring reasoning over multiple concurrent events and their relations. Evaluation of state-of-the-art LALMs reveals consistent performance degradation in polyphonic audio, indicating a fundamental bottleneck in current LALMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_05128 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PolyBench: A Benchmark for Compositional Reasoning in Polyphonic Audio Chen, Yuanjian Xiao, Yang Yin, Han Liu, Xubo Huang, Jinjie Dang, Ting Audio and Speech Processing Sound Large Audio Language Models (LALMs) are increasingly capable of reasoning over audio. However, existing benchmarks provide limited coverage of reasoning in polyphonic audio, where multiple sound events co-occur and induce compositional structure. In this work, we introduce PolyBench, a benchmark designed to evaluate compositional reasoning in polyphonic audio. PolyBench comprises five evaluation subsets covering counting, classification, detection, concurrency, and duration estimation, requiring reasoning over multiple concurrent events and their relations. Evaluation of state-of-the-art LALMs reveals consistent performance degradation in polyphonic audio, indicating a fundamental bottleneck in current LALMs. |
| title | PolyBench: A Benchmark for Compositional Reasoning in Polyphonic Audio |
| topic | Audio and Speech Processing Sound |
| url | https://arxiv.org/abs/2603.05128 |