SDLGASJul 23, 2024

On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis

arXiv:2407.16417v26 citationsh-index: 5
Originality Synthesis-oriented
AI Analysis

This work addresses the utility of foundation models for marmoset call analysis, which is incremental as it builds on existing methods for neuro-biological research.

This study tackled the problem of evaluating speech and audio foundation models for analyzing marmoset calls, finding that higher bandwidth models improved performance and pre-training on speech or general audio yielded comparable results, outperforming a spectral baseline.

Marmoset monkeys encode vital information in their calls and serve as a surrogate model for neuro-biologists to understand the evolutionary origins of human vocal communication. Traditionally analyzed with signal processing-based features, recent approaches have utilized self-supervised models pre-trained on human speech for feature extraction, capitalizing on their ability to learn a signal's intrinsic structure independently of its acoustic domain. However, the utility of such foundation models remains unclear for marmoset call analysis in terms of multi-class classification, bandwidth, and pre-training domain. This study assesses feature representations derived from speech and general audio domains, across pre-training bandwidths of 4, 8, and 16 kHz for marmoset call-type and caller classification tasks. Results show that models with higher bandwidth improve performance, and pre-training on speech or general audio yields comparable results, improving over a spectral baseline.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes