arXiv：cs.AI· Zhe Sun, Liang An, Jiayu Yao, Ronglai Qian, Jianing Cai, Ziwei Huang, Qing Fan, Zhiyuan Yang, Yujun Cai, Hongli Cao, Yiwei Wang, Xiaoyan Wang·· 18 小时前
UA-Bench：面向水下声学信号识别的大型音频语言模型基准
UA-Bench: Benchmarking Large Audio-Language Models on Underwater Acoustic Recognition
AI 导读
研究者提出 UA-Bench，据称首个评估大型音频语言模型（LALMs）水下声学信号识别的大规模基准，包含 375,051 条音频记录，覆盖检测脉冲、通信波形与舰船辐射噪声三类信号，每条约带三级标签层级（13 个叶类）、多轮对话模板及信源信道元数据。
正文
Authors:Zhe Sun, Liang An, Jiayu Yao, Ronglai Qian, Jianing Cai, Ziwei Huang, Qing Fan, Zhiyuan Yang, Yujun Cai, Hongli Cao, Yiwei Wang, Xiaoyan Wang
Abstract:Large audio-language models (LALMs) are fast becoming a general interface to sound, yet how far their broad pretraining carries into specialized domains remains largely open. Vessel monitoring, maritime safety, and ocean sensing all depend on recognizing underwater signals, but to our knowledge LALMs have not been systematically evaluated on them. Annotated recordings are costly to collect, and a faithful synthetic alternative has to bring together many interacting factors: the structure of detection pulses, communication waveforms, and ship-radiated noise, and the sound-speed profile, geometry, and multipath propagation through which each reaches the receiver. We address this by proposing \textbf{UA-Bench}, to our knowledge the first large-scale benchmark for evaluating LALMs on underwater acoustic signal recognition. It comprises 375,051 audio records that couple parameterized sources with modeled propagation, so that every record can be traced to the conditions that produced it. The records span these three signal families, and each carries a three-level label hierarchy (13 leaf classes), a templated multi-turn dialogue, and source and channel metadata. We evaluate on a balanced 2,600-record subset with a gated coarse-to-fine protocol that locates each error at source routing, fine-grained classification, or output format, and add a paired silent-audio control to test whether the waveform is actually used. Nine open LALMs, evaluated without task-specific adaptation, reach only 2.0\%--13.1\% leaf accuracy, against a random reference of 7.7\%. The waveform helps source routing far more than leaf recognition (for one model, +29.5 versus +2.3 points over silence), and just four models gain reliably at the leaf level, by at most 4.7 points. UA-Bench thus gives a reference point for these models, and its released training partition supports follow-up adaptation work.
| Comments: | 31 pages including appendix, 12 figures |
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.16942 [cs.SD] |
| (or arXiv:2610.16942v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.16942 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Zhe Sun [view email]
[v1]
Mon, 12 Oct 2026 15:18:11 UTC (4,352 KB)
来源：arXiv：cs.AI · arxiv.org