Publications

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

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

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

Highly Expressive Peking Opera Synthesis with Durian System

Published in (late-breaking demo) Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019), 2019

A prototype Jingju synthesis method which can generate expressive Jingju synthesis given the phoneme and note-pitch duration.

Recommended citation: Yusong Wu, Shengchen Li, Chenzhu Yu, Heng Lu, Chao Weng, Dong Yu (2019). "Highly Expressive Peking Opera Synthesis with Durian System" (late-breaking/demo) Proceedings of the 20th International Society for Music Information Retrieval Conference (ISMIR 2019). https://lukewys.github.io/files/ISMIR2019_lbd-correct_name.pdf

Distinguishing Chinese Guqin and Western Baroque pieces based on statistical model analysis of melodies

Published in Proceedings of Computer Music Multidisciplinary Research 2019 (CMMR 2019), 2019

Measuring similarity of melodies to genre by building statistical models. Aim to evaluate melodies generated by automatic composition systems that could generate multiple genres.

Recommended citation: Yusong Wu, Shengchen Li (2019). "Distinguishing Chinese Guqin and Western Baroque pieces based on statistical model analysis of melodies" Proceedings of Computer Music Multidisciplinary Research 2019 (CMMR 2019). https://lukewys.github.io/files/CMMR2019_YusongWu_refined.pdf