# SingOMD: Singing Oriented Multi-resolution Discrete Representation Construction from Speech Models

arXiv: https://arxiv.org/abs/2406.08905 · HTML: https://mlsanity.com/paper/2406.08905/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2024.

## Built on by (most cited first, 2 of 2)

- [SingMOS-Pro: An Comprehensive Benchmark for Singing Quality Assessment](https://mlsanity.com/paper/2510.01812/) (2025)
- [TokenMapper: A Step Toward Interoperable Speech Token Translation](https://mlsanity.com/paper/2609.12563/) (2026)

## Abstract (arXiv)

Discrete representation has shown advantages in speech generation tasks, wherein discrete tokens are derived by discretizing hidden features from self-supervised learning (SSL) pre-trained models. However, the direct application of speech SSL models to singing generation encounters domain gaps between speech and singing. Furthermore, singing generation necessitates a more refined representation than typical speech. To address these challenges, we introduce SingOMD, a novel method to extract singing-oriented multi-resolution discrete representations from speech SSL models. Specifically, we first adapt the features from speech SSL through a resynthesis task and incorporate multi-resolution modules based on resampling to better serve singing generation. These adapted multi-resolution features are then discretized via clustering. Extensive experiments demonstrate the robustness, efficiency, and effectiveness of these representations in singing vocoders and singing voice synthesis.