# Generating lyrics with variational autoencoder and multi-modal artist embeddings

arXiv: https://arxiv.org/abs/1812.08318 · HTML: https://mlsanity.com/paper/1812.08318/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Dec 2018.

## Built on by (most cited first, 3 of 3)

- [A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models](https://mlsanity.com/paper/2201.05337/) (2022)
- [LyricJam: A system for generating lyrics for live instrumental music](https://mlsanity.com/paper/2106.01960/) (2021)
- [Between Predictability and Randomness: Seeking Artistic Inspiration from AI Generative Models](https://mlsanity.com/paper/2506.12634/) (2025)

## Abstract (arXiv)

We present a system for generating song lyrics lines conditioned on the style of a specified artist. The system uses a variational autoencoder with artist embeddings. We propose the pre-training of artist embeddings with the representations learned by a CNN classifier, which is trained to predict artists based on MEL spectrograms of their song clips. This work is the first step towards combining audio and text modalities of songs for generating lyrics conditioned on the artist's style. Our preliminary results suggest that there is a benefit in initializing artists' embeddings with the representations learned by a spectrogram classifier.