On the Utility of Speech and Audio Foundation Models for Marmoset Call Analysis
| Type of publication: | Conference paper |
| Citation: | Sarkar_VIHAR_2024 |
| Publication status: | Accepted |
| Booktitle: | 4th International Workshop on Vocal Interactivity in-and-between Humans, Animals and Robots |
| Year: | 2024 |
| Abstract: | 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. |
| Keywords: | bandwidth, bioacoustics, call-type and caller classification, speech and audio |
| Projects |
Idiap EVOLANG |
| Authors | |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
