HuangmeiSinger: A Dataset and A Branchformer-Diffusion Model for Huangmei Opera Synthesis
Yufeng Qiu, Guofu Zhang, Zhaopin Su, Yang Zhou, Xiaoyi Bian · 2025
Singing voice synthesis has been extensively used in metaverse, music creation and entertainment, and cultural preservation and inheritance. However, the synthesis of traditional operas, such as Huangmei opera, has been limited due to the lack of professionally annotated high-quality datasets and appropriate deep learning models. In this work, we develop a singing voice dataset and propose an acoustic model tailored for the unique singing style for Huangmei opera. More specifically, we first propose a data annotation method, effectively addressing the challenges posed by the numerous arias in this art form. Next, we construct our Huangmei opera singing voice dataset with the detailed musical score information, where each singing recording is captured at a high sampling rate of 44.1 kHz. Subsequently, we incorporate the Branchformer encoder and the pitch diffusion module to handle the complex and diverse melodies characteristic of Huangmei opera. Finally, extensive subjective and objective experiments demonstrate the effectiveness of the proposed dataset and model. Audio samples, the dataset, and the codes are available at https://walkinginthelight.github.io/HuangmeiSinger.github.io/opera/.