The HCCL-DKU system for fake audio generation task of the 2022 ICASSP ADD Challenge

TL;DR

This paper introduces a novel end-to-end PPG-based voice conversion system that significantly improves fake audio generation quality and spoofing success, achieving second place in the 2022 ICASSP ADD challenge.

Contribution

The paper presents a new fully end-to-end PPG-based voice conversion model that outperforms existing models in quality and spoofing effectiveness.

Findings

Outperforms Tacotron and Fastspeech models in quality

Achieves high spoofing success rate of 0.916

Secures second place in the ICASSP ADD challenge

Abstract

The voice conversion task is to modify the speaker identity of continuous speech while preserving the linguistic content. Generally, the naturalness and similarity are two main metrics for evaluating the conversion quality, which has been improved significantly in recent years. This paper presents the HCCL-DKU entry for the fake audio generation task of the 2022 ICASSP ADD challenge. We propose a novel ppg-based voice conversion model that adopts a fully end-to-end structure. Experimental results show that the proposed method outperforms other conversion models, including Tacotron-based and Fastspeech-based models, on conversion quality and spoofing performance against anti-spoofing systems. In addition, we investigate several post-processing methods for better spoofing power. Finally, we achieve second place with a deception success rate of 0.916 in the ADD challenge.