2 papers
cs.SD2024
SZU-AFS Antispoofing System for the ASVspoof 5 Challenge
Yuxiong Xu, Jiafeng Zhong, Sengui Zheng +2
This paper presents the SZU-AFS anti-spoofing system, designed for Track 1 of the ASVspoof 5 Challenge under open conditions. The system is built with four stages: selecting a base…
cs.SD2023
Comparative Analysis of Transfer Learning in Deep Learning Text-to-Speech Models on a Few-Shot, Low-Resource, Customized Dataset
Ze Liu
Text-to-Speech (TTS) synthesis using deep learning relies on voice quality. Modern TTS models are advanced, but they need large amount of data. Given the growing computational comp…