# Learning Marmoset Vocal Patterns with a Masked Autoencoder for Robust Call Segmentation, Classification, and Caller Identification

arXiv: https://arxiv.org/abs/2410.23279 · HTML: https://mlsanity.com/paper/2410.23279/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 30 Oct 2024.

## Builds on (most cited first, 4 of 4)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Can Self-Supervised Neural Representations Pre-Trained on Human Speech distinguish Animal Callers?](https://mlsanity.com/paper/2305.14035/) (2023)

## Abstract (arXiv)

The marmoset, a highly vocal primate, is a key model for studying social-communicative behavior. Unlike human speech, marmoset vocalizations are less structured, highly variable, and recorded in noisy, low-resource conditions. Learning marmoset communication requires joint call segmentation, classification, and caller identification -- challenging domain tasks. Previous CNNs handle local patterns but struggle with long-range temporal structure. We applied Transformers using self-attention for global dependencies. However, Transformers show overfitting and instability on small, noisy annotated datasets. To address this, we pretrain Transformers with MAE -- a self-supervised method reconstructing masked segments from hundreds of hours of unannotated marmoset recordings. The pretraining improved stability and generalization. Results show MAE-pretrained Transformers outperform CNNs, demonstrating modern self-supervised architectures effectively model low-resource non-human vocal communication.