ThaiSpoof: A Database for Spoof Detection in Thai Language

Many applications and security systems have widely applied automatic speaker verification (ASV). However, these systems are vulnerable to various direct and indirect access attacks, which weakens their authentication capability. The research in spoofed speech detection contributes to enhancing these...

Full description

Saved in:
Bibliographic Details
Published in2023 18th International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP) pp. 1 - 6
Main Authors Galajit, Kasorn, Kosolsriwiwat, Thunpisit, Unoki, Masashi, Mawalim, Candy Olivia, Aimmanee, Pakinee, Kongprawechnon, Waree, Pa, Win Pa, Chaiwongyen, Anuwat, Racharak, Teeradaj, Boonkla, Surasak, Yassin, Hayati, Karnjana, Jessada
Format Conference Proceeding
LanguageEnglish
Published IEEE 27.11.2023
Subjects
Authentication
automatic speaker verification
Cepstral analysis
Convolutional neural networks
Error analysis
Natural language processing
speech modification
speech synthesis
spoof detection
Thai database
Voice activity detection
Online AccessGet full text

Cover

More Information
Summary:Many applications and security systems have widely applied automatic speaker verification (ASV). However, these systems are vulnerable to various direct and indirect access attacks, which weakens their authentication capability. The research in spoofed speech detection contributes to enhancing these systems. Unfortunately, the study in spoofing detection is limited to only some languages due to the need for various datasets. This paper focuses on a Thai language dataset for spoof detection. The dataset consists of genuine speech signals and various types of spoofed speech signals. The spoofed speech dataset is generated using text-to-speech tools for the Thai language, synthesis tools, and tools for speech modification. To showcase the utilization of this dataset, we implement a simple spoof detection model based on a convolutional neural network (CNN) taking linear frequency cepstral coefficients (LFCC) as its input. We trained, validated, and tested the model on our dataset referred to as ThaiSpoof. The experimental result shows that the accuracy of model is 93%, and equal error rate (EER) is 6.78%. The result shows that our ThaiSpoof dataset has the potential to develop for helping in spoof detection studies.
ISSN:2831-4565
DOI:10.1109/iSAI-NLP60301.2023.10354956