English

An End-to-End Multi-Module Audio Deepfake Generation System for ADD Challenge 2023

Sound 2023-07-04 v1 Computation and Language Audio and Speech Processing

Abstract

The task of synthetic speech generation is to generate language content from a given text, then simulating fake human voice.The key factors that determine the effect of synthetic speech generation mainly include speed of generation, accuracy of word segmentation, naturalness of synthesized speech, etc. This paper builds an end-to-end multi-module synthetic speech generation model, including speaker encoder, synthesizer based on Tacotron2, and vocoder based on WaveRNN. In addition, we perform a lot of comparative experiments on different datasets and various model structures. Finally, we won the first place in the ADD 2023 challenge Track 1.1 with the weighted deception success rate (WDSR) of 44.97%.

Keywords

Cite

@article{arxiv.2307.00729,
  title  = {An End-to-End Multi-Module Audio Deepfake Generation System for ADD Challenge 2023},
  author = {Sheng Zhao and Qilong Yuan and Yibo Duan and Zhuoyue Chen},
  journal= {arXiv preprint arXiv:2307.00729},
  year   = {2023}
}
R2 v1 2026-06-28T11:20:19.574Z