The Multi-Speaker Multi-Style Voice Cloning Challenge 2021

By Qicong Xie, Xiaohai Tian, Guanghou Liu, Kun Song, Lei Xie, Zhiyong Wu, Hai Li, Song Shi, Haizhou Li, Feng Hong and 2 more. 2021

29 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Hung-yi Lee
6. Sheng Zhao
7. Junichi Yamagishi
8. Yi-Chiao Wu

In Signal Processing

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Hung-yi Lee
6. Yi-Chiao Wu
7. Hsin-Min Wang
8. Yu Tsao

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, background): “, 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].”
• Investigating on Incorporating Pretrained and Learnable Speaker Representations for Multi-Speaker Multi-Style Text-to-Speech (2021, background): “To push the frontier of TTS technology, ICASSP 2021 M2VoC challenge [3] aims at addressing the problem of few-shot multi-speaker multi-style voice cloning.”
• The AS-NU System for the M2VoC Challenge (2021, background): “The multi-speaker multi-style voice cloning (M2VoC) challenge [13] aims to better understand different voice cloning techniques by utilizing a freely-available common dataset to share views about problems and challenges faced by current techniques.”
• CUHK-EE voice cloning system for ICASSP 2021 M2VoC challenge (2021, methodology): “The ICASSP 2021 M2VoC challenge (Multi-Speaker Multi-Style Voice Cloning Challenge) is focused on investigating and evaluating state-of-the-art solutions to the problem of “voice cloning”.”