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 atthis http URL. We provide the dataset and the code for processing data and conducting benchmarks atthis https URLandthis https URL.
View on arXiv@article{zhang2025_2409.13832,
title={ GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks },
author={ Yu Zhang and Changhao Pan and Wenxiang Guo and Ruiqi Li and Zhiyuan Zhu and Jialei Wang and Wenhao Xu and Jingyu Lu and Zhiqing Hong and Chuxin Wang and LiChao Zhang and Jinzheng He and Ziyue Jiang and Yuxin Chen and Chen Yang and Jiecheng Zhou and Xinyu Cheng and Zhou Zhao },
journal={arXiv preprint arXiv:2409.13832},
year={ 2025 }
}