arXiv cs.CL· Faadil Mustun, Chiara Semenzin, Roberto Dessi, Pablo Robin Guerrero, Pierre Orhan, Alexis Emanuelli, Emanuele Rossi, Yair Lakretz, Gonzalo de Polavieja, German Sumbre·· 9 小时前AI 评分26
OpenWhistle:迄今最大规模宽吻海豚发声数据集与基准发布
OpenWhistle: A Large-Scale Longitudinal Dataset and Benchmark of Bottlenose Dolphin Vocalizations
AI 导读
OpenWhistle 发布约 18 万段海豚哨声(114 小时)、覆盖 5 只个体长达五年的公开数据集,并附 8,354 段专家标注哨声及哨声类型检测与分类的可复现评测协议。
正文 · 原文
Abstract:Recent advances in bioacoustics have been driven by large-scale corpora and standardized benchmarks, yet existing resources are overwhelmingly bird-centric and shallow per species, limiting their use for studying the structure of a single species' communication system. This gap is particularly acute for cetaceans: despite bottlenose dolphins (Tursiops truncatus) being a compelling case of complex vocal communication among non-human mammals, existing dolphin datasets are small, fragmented, and largely closed. We introduce OpenWhistle, the largest publicly available dataset of dolphin vocalizations. It comprises approximately 180,000 whistles (114 hours) recorded over five years from a stable pod of five individuals in a semi-natural environment, paired with a curated subset of 8,354 expert-annotated whistles and reproducible evaluation protocols for whistle-type detection and classification. We further release the full processing pipeline for whistle detection, segmentation, and categorization. To demonstrate its utility, we pretrain a Wav2Vec2.0 model adapted to dolphin acoustics on the OpenWhistle corpus and show that it learns effective representations, outperforming general-purpose bioacoustic models such as AVES and BioLingual on both tasks while leaving meaningful headroom for future work. By releasing the dataset, pipeline, and evaluation protocol, we provide the first open dolphin whistle dataset tailored for training self-supervised models, laying the groundwork for advancing dolphin communication research and developing models that capture fine-grained acoustic structure within species.
| Comments: | Spotlight at the NeurIPS 2026 Datasets & Evaluations Track |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2609.34839 [cs.CL] |
| (or arXiv:2609.34839v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2609.34839 arXiv-issued DOI via DataCite |
Submission history
From: Chiara Semenzin [view email]
[v1]
Mon, 28 Sep 2026 10:37:20 UTC (11,979 KB)
[v2]
Tue, 17 Nov 2026 11:06:43 UTC (11,716 KB)
来源:arXiv cs.CL · arxiv.org