Neural Melody Composition from Lyrics
arXiv:1809.04318
Abstract
In this paper, we study a novel task that learns to compose music from natural language. Given the lyrics as input, we propose a melody composition model that generates lyrics-conditional melody as well as the exact alignment between the generated melody and the given lyrics simultaneously. More specifically, we develop the melody composition model based on the sequence-to-sequence framework. It consists of two neural encoders to encode the current lyrics and the context melody respectively, and a hierarchical decoder to jointly produce musical notes and the corresponding alignment. Experimental results on lyrics-melody pairs of 18,451 pop songs demonstrate the effectiveness of our proposed methods. In addition, we apply a singing voice synthesizer software to synthesize the "singing" of the lyrics and melodies for human evaluation. Results indicate that our generated melodies are more melodious and tuneful compared with the baseline method.
References in corpus (6)
- Neural Machine Translation by Jointly Learning to Align and Translate
- Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
- C-RNN-GAN: Continuous recurrent neural networks with adversarial training
- A Hierarchical Latent Vector Model for Learning Long-Term Structure in Music
- MidiNet: A Convolutional Generative Adversarial Network for Symbolic-domain Music Generation
- MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer