Dual channel encoding improves understanding of sperm whale communication
Dual-Channel Contrastive Encoding of Sperm Whale Coda
SoundArtificial IntelligenceMachine Learning
Summary
Sperm whales talk using short sequences of clicks called codas that have unique rhythms and sound features. The authors designed a new AI method that separately studies these rhythms and sound patterns then combines them to understand whale social groups, types of messages, and individual whales. They tested their method and found it works well for identifying group and message types but can struggle to recognize individual whales over years. Their results suggest combining timing and sound details helps depending on the task, but no single way is the best for all.
What this means in practice
- •For marine biologists: Use dual-channel encoding to better classify whale social groups and communication patterns from recorded click sequences.
- •For acoustic monitoring teams: Improve identification of whale call types and individuals in large audio datasets by combining rhythmic and spectral click information.
Authors
João Victor Quintanilha, Emma Virnelli, Shuo Zhang
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 https://dcce-research-site.vercel.app.