Hsin-Pei Lee, Jhih-Sheng Fan, Wei-Yun Ma
North American Chapter of the Association for Computational Linguistics (NAACL) 2019
Paper: https://www.aclweb.org/anthology/N19-4015/
Demo Video: https://www.youtube.com/watch?v=Gstzqls2f4A
iComposer is an interactive web-based songwriting system designed to assist human creators by greatly simplifying music production. iComposer automatically creates melodies to accompany any given text. It also enables users to generate a set of lyrics given arbitrary melodies. iComposer is based on three sequence-to-sequence models, which are used to predict melody, rhythm, and lyrics, respectively. Songs generated by iComposer are compared with human-composed and randomly-generated ones in a subjective test, the experimental results of which demonstrate the capability of the proposed system to write pleasing melodies and meaningful lyrics at a level similar to that of humans.
The neural network proposed in this paper is a sequence-to-sequence model with a single layer and 100 nodes in both the encoder and decoder LSTM. All the code for this system was written in Python using Pytorch as a backend.