arXiv cs.AI· Jo\~ao Victor Quintanilha, Emma Virnelli, Shuo Zhang·· 13 小时前AI 评分18
双通道对比编码器 DCCE：分别编码抹香鲸尾音节奏与频谱
Dual-Channel Contrastive Encoding of Sperm Whale Coda
AI 导读
研究者提出双通道对比编码器（DCCE），用独立编码器分别编码抹香鲸尾音的节奏与频谱信息后再融合，在 1,383 条尾音上评估社会单元、尾音类型和个体识别三项任务。
正文 · 原文
Abstract:Sperm whales (Physeter macrocephalus) communicate through short click sequences called codas, whose structure includes the rhythmic pattern of inter-click intervals (ICI) and the spectral composition of the clicks. In this paper, we propose the Dual-Channel Contrastive Encoder (DCCE), which explicitly encodes rhythm and spectral information with separate encoders before fusing them. We evaluate DCCE on three coda-understanding tasks: social unit, coda type, and individual identification. We compare DCCE against strong baselines from literature under a common linear-probe protocol and analyze the role of each channel and training objective through ablations. On 1,383 codas, shared partitions and validation-only layer selection support three random splits and three recording-date-disjoint folds. DCCE with unit pairing and type supervision achieves mean random-split macro-F1 of 0.901/0.865/0.597 for unit/type/identity. Raw ICI remains strongest for type (0.987), and ICI plus temporal mel statistics is a strong identity reference (0.724). An auxiliary identity objective improves spectral-branch identity prediction but does not improve the mean fused-identity score in this configuration. Date-grouped evaluation and four year holdouts expose generalization limits. The results support task-dependent combinations of timing and spectral information, without establishing independent biological channels or general architectural superiority. Code, notebooks, and complete results are available at this https URL.
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.29101 [cs.SD] |
| (or arXiv:2610.29101v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2610.29101 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | Proceedings of the 11th Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2026) |
Submission history
From: Shuo Zhang [view email]
[v1]
Wed, 21 Oct 2026 02:46:56 UTC (131 KB)
来源：arXiv cs.AI · arxiv.org