Saved in:
Bibliographic Details
Main Authors: Sun, Jingchen, Han, Shaobo, Kohno, Wataru, Chen, Changyou
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2501.09877
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910787854925824
author Sun, Jingchen
Han, Shaobo
Kohno, Wataru
Chen, Changyou
author_facet Sun, Jingchen
Han, Shaobo
Kohno, Wataru
Chen, Changyou
contents Contrastive Language-Audio Pretraining (CLAP) models have demonstrated unprecedented performance in various acoustic signal recognition tasks. Fiber-optic-based acoustic recognition is one of the most important downstream tasks and plays a significant role in environmental sensing. Adapting CLAP for fiber-optic acoustic recognition has become an active research area. As a non-conventional acoustic sensor, fiber-optic acoustic recognition presents a challenging, domain-specific, low-shot deployment environment with significant domain shifts due to unique frequency response and noise characteristics. To address these challenges, we propose a support-based adaptation method, CLAP-S, which linearly interpolates a CLAP Adapter with the Support Set, leveraging both implicit knowledge through fine-tuning and explicit knowledge retrieved from memory for cross-domain generalization. Experimental results show that our method delivers competitive performance on both laboratory-recorded fiber-optic ESC-50 datasets and a real-world fiber-optic gunshot-firework dataset. Our research also provides valuable insights for other downstream acoustic recognition tasks. The code and gunshot-firework dataset are available at https://github.com/Jingchensun/clap-s.
format Preprint
id arxiv_https___arxiv_org_abs_2501_09877
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CLAP-S: Support Set Based Adaptation for Downstream Fiber-optic Acoustic Recognition
Sun, Jingchen
Han, Shaobo
Kohno, Wataru
Chen, Changyou
Audio and Speech Processing
Machine Learning
Contrastive Language-Audio Pretraining (CLAP) models have demonstrated unprecedented performance in various acoustic signal recognition tasks. Fiber-optic-based acoustic recognition is one of the most important downstream tasks and plays a significant role in environmental sensing. Adapting CLAP for fiber-optic acoustic recognition has become an active research area. As a non-conventional acoustic sensor, fiber-optic acoustic recognition presents a challenging, domain-specific, low-shot deployment environment with significant domain shifts due to unique frequency response and noise characteristics. To address these challenges, we propose a support-based adaptation method, CLAP-S, which linearly interpolates a CLAP Adapter with the Support Set, leveraging both implicit knowledge through fine-tuning and explicit knowledge retrieved from memory for cross-domain generalization. Experimental results show that our method delivers competitive performance on both laboratory-recorded fiber-optic ESC-50 datasets and a real-world fiber-optic gunshot-firework dataset. Our research also provides valuable insights for other downstream acoustic recognition tasks. The code and gunshot-firework dataset are available at https://github.com/Jingchensun/clap-s.
title CLAP-S: Support Set Based Adaptation for Downstream Fiber-optic Acoustic Recognition
topic Audio and Speech Processing
Machine Learning
url https://arxiv.org/abs/2501.09877