Acoustic Individual Identification of White-Faced Capuchin Monkeys Using Joint Multi-Species Embeddings

ACL ARR 2025 February Submission6063 Authors

Abstract: Acoustic individual identification of wild animals is an essential task for understanding animal vocalizations within their social contexts, and for facilitating conservation and wildlife monitoring efforts. However, most of the work in this space relies on human efforts, as the development of methods for automatic individual identification is hindered by the lack of data. In this paper, we explore cross-species pre-training to address the task of individual classification in White-Faced Capuchin monkeys. Using acoustic embeddings from birds and humans, we find that they can be effectively used to identify the calls from individual monkeys. Moreover, we find that joint multi-species representations can lead to further improvements over the use of one representation at a time. Our work demonstrates the potential of cross-species data transfer and multi-species representations, as strategies to address tasks on species with very limited data.

Paper Type: Short

Research Area: Special Theme (conference specific)

Research Area Keywords: automatic speech recognition, spoken language understanding, representation learning, generalization, transfer learning / domain adaptation, self-supervised learning, contrastive learning

Contribution Types: NLP engineering experiment, Approaches low compute settings-efficiency, Data analysis

Languages Studied: White-Faced Capuchin Communication System

Submission Number: 6063