Saved in:
Bibliographic Details
Main Authors: Oiso, Hideyuki, Matsunaga, Yuto, Kakizaki, Kazuya, Miyagawa, Taiki
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.09869
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909347535126528
author Oiso, Hideyuki
Matsunaga, Yuto
Kakizaki, Kazuya
Miyagawa, Taiki
author_facet Oiso, Hideyuki
Matsunaga, Yuto
Kakizaki, Kazuya
Miyagawa, Taiki
contents We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD method using prompt tuning in a plug-in style. It bridges domain gaps by integrating it seamlessly with state-of-the-art transformer models and/or with other fine-tuning methods, boosting their performance on target data (challenge (i)). In addition, our method can fit small target datasets because it does not require a large number of extra parameters (challenge (ii)). This feature also contributes to computational efficiency, countering the high computational costs typically associated with large-scale pre-trained models in ADD (challenge (iii)). We conclude that prompt tuning for ADD under domain gaps presents a promising avenue for enhancing accuracy with minimal target data and negligible extra computational burden.
format Preprint
id arxiv_https___arxiv_org_abs_2410_09869
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset
Oiso, Hideyuki
Matsunaga, Yuto
Kakizaki, Kazuya
Miyagawa, Taiki
Sound
Artificial Intelligence
Cryptography and Security
Machine Learning
Audio and Speech Processing
We study test-time domain adaptation for audio deepfake detection (ADD), addressing three challenges: (i) source-target domain gaps, (ii) limited target dataset size, and (iii) high computational costs. We propose an ADD method using prompt tuning in a plug-in style. It bridges domain gaps by integrating it seamlessly with state-of-the-art transformer models and/or with other fine-tuning methods, boosting their performance on target data (challenge (i)). In addition, our method can fit small target datasets because it does not require a large number of extra parameters (challenge (ii)). This feature also contributes to computational efficiency, countering the high computational costs typically associated with large-scale pre-trained models in ADD (challenge (iii)). We conclude that prompt tuning for ADD under domain gaps presents a promising avenue for enhancing accuracy with minimal target data and negligible extra computational burden.
title Prompt Tuning for Audio Deepfake Detection: Computationally Efficient Test-time Domain Adaptation with Limited Target Dataset
topic Sound
Artificial Intelligence
Cryptography and Security
Machine Learning
Audio and Speech Processing
url https://arxiv.org/abs/2410.09869