GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks

The scarcity of high-quality and multi-task singing datasets significantly hinders the development of diverse controllable and personalized singing tasks, as existing singing datasets suffer from low quality, limited diversity of languages and singers, absence of multi-technique information and real...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Zhang, Yu, Pan, Changhao, Guo, Wenxiang, Li, Ruiqi, Zhu, Zhiyuan, Wang, Jialei, Xu, Wenhao, Lu, Jingyu, Hong, Zhiqing, Wang, Chuxin, Zhang, LiChao, He, Jinzheng, Jiang, Ziyue, Chen, Yuxin, Chen, Yang, Zhou, Jiecheng, Cheng, Xinyu, Zhou, Zhao
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 30.10.2024
Subjects
Annotations
Benchmarks
Controllability
Data processing
Datasets
Languages
Music
Musical scores
Musicians & conductors
Phonemes
Singers
Singing
Speech recognition
Voice control
Voice recognition
Online AccessGet full text

Cover

More Information
Summary:The scarcity of high-quality and multi-task singing datasets significantly hinders the development of diverse controllable and personalized singing tasks, as existing singing datasets suffer from low quality, limited diversity of languages and singers, absence of multi-technique information and realistic music scores, and poor task suitability. To tackle these problems, we present GTSinger, a large global, multi-technique, free-to-use, high-quality singing corpus with realistic music scores, designed for all singing tasks, along with its benchmarks. Particularly, (1) we collect 80.59 hours of high-quality singing voices, forming the largest recorded singing dataset; (2) 20 professional singers across nine widely spoken languages offer diverse timbres and styles; (3) we provide controlled comparison and phoneme-level annotations of six commonly used singing techniques, helping technique modeling and control; (4) GTSinger offers realistic music scores, assisting real-world musical composition; (5) singing voices are accompanied by manual phoneme-to-audio alignments, global style labels, and 16.16 hours of paired speech for various singing tasks. Moreover, to facilitate the use of GTSinger, we conduct four benchmark experiments: technique-controllable singing voice synthesis, technique recognition, style transfer, and speech-to-singing conversion. The corpus and demos can be found at http://gtsinger.github.io. We provide the dataset and the code for processing data and conducting benchmarks at https://huggingface.co/datasets/GTSinger/GTSinger and https://github.com/GTSinger/GTSinger.
ISSN:2331-8422