# Score and Lyrics-Free Singing Voice Generation

arXiv: https://arxiv.org/abs/1912.11747 · HTML: https://mlsanity.com/paper/1912.11747/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Dec 2019.

## Built on by (most cited first, 4 of 4)

- [The Ethical Implications of Generative Audio Models: A Systematic Literature Review](https://mlsanity.com/paper/2307.05527/) (2023)
- [KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms](https://mlsanity.com/paper/2110.04005/) (2021)
- [SingAug: Data Augmentation for Singing Voice Synthesis with Cycle-consistent Training Strategy](https://mlsanity.com/paper/2203.17001/) (2022)
- [Mamba2 Meets Silence: Robust Vocal Source Separation for Sparse Regions](https://mlsanity.com/paper/2508.14556/) (2025)

## Abstract (arXiv)

Generative models for singing voice have been mostly concerned with the task of ``singing voice synthesis,'' i.e., to produce singing voice waveforms given musical scores and text lyrics. In this work, we explore a novel yet challenging alternative: singing voice generation without pre-assigned scores and lyrics, in both training and inference time. In particular, we outline three such generation schemes, and propose a pipeline to tackle these new tasks. Moreover, we implement such models using generative adversarial networks and evaluate them both objectively and subjectively.