MOS-FAD: Improving Fake Audio Detection Via Automatic Mean Opinion Score Prediction

IEEE Automatic Mean Opinion Score (MOS) prediction is employed to evaluate the quality of synthetic speech. This study extends the application of predicted MOS to the task of Fake Audio Detection (FAD) as we expect that MOS can be used to assess how close synthesized speech is to the natural human v...

Full description

Bibliographic Details

Published in:	Proceedings of the ... IEEE International Conference on Acoustics, Speech and Signal Processing (1998) pp. 876 - 880
Main Authors:	Zhou, Wangjin, Yang, Zhengdong, Chu, Chenhui, Li, Sheng, Dabre, Raj, Zhao, Yi, Tatsuya, Kawahara
Format:	Conference Proceeding
Language:	English
Published:	IEEE 14.04.2024
Subjects:	fake audio detection (FAD) Logic gates model fusion MOS prediction Predictive models self-supervised learned (SSL) model Signal processing Speech synthesis Task analysis Training Training data
ISSN:	2379-190X
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!