The Voice Conversion Challenge 2018: Promoting Development of Parallel and Nonparallel Methods

TL;DR

The Voice Conversion Challenge 2018 provided a standardized framework for evaluating and comparing state-of-the-art voice conversion systems, including both parallel and non-parallel data approaches, through large-scale perceptual testing.

Contribution

This paper introduces the 2018 challenge framework, encompassing new tasks and evaluation methods, to advance the development of voice conversion technology.

Findings

23 teams participated with diverse systems

Large-scale perceptual evaluation conducted

Results highlight progress and remaining challenges in VC

Abstract

We present the Voice Conversion Challenge 2018, designed as a follow up to the 2016 edition with the aim of providing a common framework for evaluating and comparing different state-of-the-art voice conversion (VC) systems. The objective of the challenge was to perform speaker conversion (i.e. transform the vocal identity) of a source speaker to a target speaker while maintaining linguistic information. As an update to the previous challenge, we considered both parallel and non-parallel data to form the Hub and Spoke tasks, respectively. A total of 23 teams from around the world submitted their systems, 11 of them additionally participated in the optional Spoke task. A large-scale crowdsourced perceptual evaluation was then carried out to rate the submitted converted speech in terms of naturalness and similarity to the target speaker identity. In this paper, we present a brief summary of the state-of-the-art techniques for VC, followed by a detailed explanation of the challenge tasks and the results that were obtained.