# The Multi-speaker Multi-style Voice Cloning Challenge 2021

arXiv: https://arxiv.org/abs/2104.01818 · HTML: https://mlsanity.com/paper/2104.01818/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Apr 2021.

## Built on by (most cited first, 7 of 7)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [Voice Filter: Few-shot text-to-speech speaker adaptation using voice conversion as a post-processing module](https://mlsanity.com/paper/2202.08164/) (2022)
- [Analyzing and Improving Speaker Similarity Assessment for Speech Synthesis](https://mlsanity.com/paper/2507.02176/) (2025)
- [Self-supervised learning for robust voice cloning](https://mlsanity.com/paper/2204.03421/) (2022)
- [The AS-NU System for the M2VoC Challenge](https://mlsanity.com/paper/2104.03009/) (2021)
- [Towards Cross-speaker Reading Style Transfer on Audiobook Dataset](https://mlsanity.com/paper/2208.05359/) (2022)
- [Empirical Study Incorporating Linguistic Knowledge on Filled Pauses for Personalized Spontaneous Speech Synthesis](https://mlsanity.com/paper/2210.07559/) (2022)

## Abstract (arXiv)

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.