Synthesising Expressiveness in Peking Opera via Duration Informed Attention Network
This work addresses data collection flexibility for Peking opera synthesis, but it is incremental as it builds on existing methods with a hybrid approach.
The paper tackles expressive Peking opera singing synthesis by using musical notes instead of pitch contours, enabling human annotation and automatic features for training, and achieves comparable expressiveness to pitch contour-based systems.
This paper presents a method that generates expressive singing voice of Peking opera. The synthesis of expressive opera singing usually requires pitch contours to be extracted as the training data, which relies on techniques and is not able to be manually labeled. With the Duration Informed Attention Network (DurIAN), this paper makes use of musical note instead of pitch contours for expressive opera singing synthesis. The proposed method enables human annotation being combined with automatic extracted features to be used as training data thus the proposed method gives extra flexibility in data collection for Peking opera singing synthesis. Comparing with the expressive singing voice of Peking opera synthesised by pitch contour based system, the proposed musical note based system produces comparable singing voice in Peking opera with expressiveness in various aspects.