Synthesising Expressiveness in Peking Opera via Duration Informed Attention Network

Published in Submitted to 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020), 2019

Recommended citation: Yusong Wu, Shengchen Li, Chengzhu Yu, Heng Lu, Chao Weng, Liqiang Zhang, Dong Yu (2020). "Synthesising Expressiveness in Peking Opera via Duration Informed Attention Network" Submitted to 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2020). https://lukewys.github.io/files/ICASSP_2020_YusongWu.pdf

A singing synthesis model which generates singing voice of Peking Opera from note and phoneme sequence where pitch, dynamics and timbre are jointly sampled.

Details and Audio Sample

Download paper here