Melody-Conditioned Lyrics Generation with SeqGANs
This work addresses automatic lyrics generation for music and AI applications, but it is incremental as it builds on existing SeqGAN methods with added conditions.
The authors tackled the problem of generating lyrics conditioned on melody and theme using Sequence Generative Adversarial Networks (SeqGAN), showing that these conditions improve meaningfulness without harming evaluation metrics.
Automatic lyrics generation has received attention from both music and AI communities for years. Early rule-based approaches have~---due to increases in computational power and evolution in data-driven models---~mostly been replaced with deep-learning-based systems. Many existing approaches, however, either rely heavily on prior knowledge in music and lyrics writing or oversimplify the task by largely discarding melodic information and its relationship with the text. We propose an end-to-end melody-conditioned lyrics generation system based on Sequence Generative Adversarial Networks (SeqGAN), which generates a line of lyrics given the corresponding melody as the input. Furthermore, we investigate the performance of the generator with an additional input condition: the theme or overarching topic of the lyrics to be generated. We show that the input conditions have no negative impact on the evaluation metrics while enabling the network to produce more meaningful results.