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

Sheng Zhao, Qilong Yuan, Yibo Duan, Zhuoyue Chen
7/3/2023
cs.SDcs.CLeess.AS

No confident code implementation found for this paper. 5 possible matches can be shown below.

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%.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 5 weaker matches are hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

The FruitShell French synthesis system at the Blizzard 2023 Challenge

86% match2023

Improved Child Text-to-Speech Synthesis through Fastpitch-based Transfer Learning

85% match1 repo132023

DiffSSD: A Diffusion-Based Dataset For Speech Forensics

85% match2024

Speech-Forensics: Towards Comprehensive Synthetic Speech Dataset Establishment and Analysis

84% match2024

MimicLM: Zero-Shot Voice Imitation through Autoregressive Modeling of Pseudo-Parallel Speech Corpora

84% match2026

Syn-Att: Synthetic Speech Attribution via Semi-Supervised Unknown Multi-Class Ensemble of CNNs

84% match1 repo32023

Cite this paper

@article{zhao2023endtoend,
  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},
  year   = {2023},
  eprint = {2307.00729},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2307.00729v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2307.00729.svg)](https://codeofpaper.com/paper/2307.00729)

Discussion