The Multi-speaker Multi-style Voice Cloning Challenge 2021

Abstract

The Multi-speaker Multi-style Voice Cloning Challenge (M2VoC) aims to provide a common sizable dataset as well as a fair testbed for the benchmarking of the popular voice cloning task. Specifically, we formulate the challenge to adapt an average TTS model to the stylistic target voice with limited data from target speaker, evaluated by speaker identity and style similarity. The challenge consists of two tracks, namely few-shot track and one-shot track, where the participants are required to clone multiple target voices with 100 and 5 samples respectively. There are also two sub-tracks in each track. For sub-track a, to fairly compare different strategies, the participants are allowed to use only the training data provided by the organizer strictly. For sub-track b, the participants are allowed to use any data publicly available. In this paper, we present a detailed explanation on the tasks and data used in the challenge, followed by a summary of submitted systems and evaluation results.

A Survey on Neural Speech Synthesis

“…It is known as different terms in academia and industry, such as voice adaptation [43], voice cloning [9], custom voice [39], etc. Adaptive TTS has been a hot research topic, e,g., a lot of works in statistic parametric speech synthesis have studied voice adaptation [77,386,443,65,122], and the recent voice cloning challenge also attracts a lot of participants [388,118,331,45]. In adaptive TTS scenario, a source TTS model (usually trained on a multi-speaker speech dataset) is usually adapted with few adaptation data for each target voice.…”