# Melody-Conditioned Lyrics Generation with SeqGANs

arXiv: https://arxiv.org/abs/2010.14709 · HTML: https://mlsanity.com/paper/2010.14709/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Oct 2020.

## Built on by (most cited first, 14 of 14)

- [DeepRapper: Neural Rap Generation with Rhyme and Rhythm Modeling](https://mlsanity.com/paper/2107.01875/) (2021)
- [Automatic Song Translation for Tonal Languages](https://mlsanity.com/paper/2203.13420/) (2022)
- [The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling](https://mlsanity.com/paper/2209.14458/) (2022)
- [Unsupervised Melody-to-Lyric Generation](https://mlsanity.com/paper/2305.19228/) (2023)
- [Translate the Beauty in Songs: Jointly Learning to Align Melody and Translate Lyrics](https://mlsanity.com/paper/2303.15705/) (2023)
- [Creative Data Generation: A Review Focusing on Text and Poetry](https://mlsanity.com/paper/2305.08493/) (2023)
- [LyricJam Sonic: A Generative System for Real-Time Composition and Musical Improvisation](https://mlsanity.com/paper/2210.15638/) (2022)
- [Syllable-level lyrics generation from melody exploiting character-level language model](https://mlsanity.com/paper/2310.00863/) (2023)
- [In BLOOM: Creativity and Affinity in Artificial Lyrics and Art](https://mlsanity.com/paper/2301.05402/) (2023)
- [Joint Learning of Wording and Formatting for Singable Melody-to-Lyric Generation](https://mlsanity.com/paper/2307.02146/) (2023)
- [Agent-Driven Large Language Models for Mandarin Lyric Generation](https://mlsanity.com/paper/2410.01450/) (2024)
- [Song Form-aware Full-Song Text-to-Lyrics Generation with Multi-Level Granularity Syllable Count Control](https://mlsanity.com/paper/2411.13100/) (2024)
- [Unsupervised Melody-Guided Lyrics Generation](https://mlsanity.com/paper/2305.07760/) (2023)
- [Tuning Into Bias: A Computational Study of Gender Bias in Song Lyrics](https://mlsanity.com/paper/2409.15949/) (2024)

## Abstract (arXiv)

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.