Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sarkar, Eklavya, -Doss, Mathew Magimai.
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915109518966784
author Sarkar, Eklavya
-Doss, Mathew Magimai.
author_facet Sarkar, Eklavya
-Doss, Mathew Magimai.
contents Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high transferability for bioacoustic processing. This paper investigates (i) whether SSL models pre-trained directly on animal vocalizations offer a significant advantage over those pre-trained on speech, and (ii) whether fine-tuning speech-pretrained models on automatic speech recognition (ASR) tasks can enhance bioacoustic classification. We conduct a comparative analysis using three diverse bioacoustic datasets and two different bioacoustic tasks. Results indicate that pre-training on bioacoustic data provides only marginal improvements over speech-pretrained models, with comparable performance in most scenarios. Fine-tuning on ASR tasks yields mixed outcomes, suggesting that the general-purpose representations learned during SSL pre-training are already well-suited for bioacoustic tasks. These findings highlight the robustness of speech-pretrained SSL models for bioacoustics and imply that extensive fine-tuning may not be necessary for optimal performance.
format Preprint
id arxiv_https___arxiv_org_abs_2501_05987
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing
Sarkar, Eklavya
-Doss, Mathew Magimai.
Machine Learning
Audio and Speech Processing
Self-supervised learning (SSL) foundation models have emerged as powerful, domain-agnostic, general-purpose feature extractors applicable to a wide range of tasks. Such models pre-trained on human speech have demonstrated high transferability for bioacoustic processing. This paper investigates (i) whether SSL models pre-trained directly on animal vocalizations offer a significant advantage over those pre-trained on speech, and (ii) whether fine-tuning speech-pretrained models on automatic speech recognition (ASR) tasks can enhance bioacoustic classification. We conduct a comparative analysis using three diverse bioacoustic datasets and two different bioacoustic tasks. Results indicate that pre-training on bioacoustic data provides only marginal improvements over speech-pretrained models, with comparable performance in most scenarios. Fine-tuning on ASR tasks yields mixed outcomes, suggesting that the general-purpose representations learned during SSL pre-training are already well-suited for bioacoustic tasks. These findings highlight the robustness of speech-pretrained SSL models for bioacoustics and imply that extensive fine-tuning may not be necessary for optimal performance.
title Comparing Self-Supervised Learning Models Pre-Trained on Human Speech and Animal Vocalizations for Bioacoustics Processing
topic Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2501.05987