Synthetic Singers: A Review of Deep-Learning-based Singing Voice Synthesis Approaches

TL;DR

This survey comprehensively reviews deep-learning-based singing voice synthesis systems, categorizing architectures, analyzing core technologies, and discussing datasets and evaluation methods to guide future research and development.

Contribution

It provides the first systematic categorization and analysis of SVS architectures, technologies, datasets, and evaluation benchmarks in a comprehensive survey.

Findings

Cascaded and end-to-end architectures are the main paradigms.

Core technologies include singing modeling and control techniques.

Reviewed datasets, annotation tools, and evaluation benchmarks.

Abstract

Recent advances in singing voice synthesis (SVS) have attracted substantial attention from both academia and industry. With the advent of large language models and novel generative paradigms, producing controllable, high-fidelity singing voices has become an attainable goal. Yet the field still lacks a comprehensive survey that systematically analyzes deep-learning-based singing voice synthesis systems and their enabling technologies. To address the aforementioned issue, this survey first categorizes existing systems by task type and then organizes current architectures into two major paradigms: cascaded and end-to-end approaches. Moreover, we provide an in-depth analysis of core technologies, covering singing modeling and control techniques. Finally, we review relevant datasets, annotation tools, and evaluation benchmarks that support training and assessment. In appendix, we introduce training strategies and further discussion of SVS. This survey provides an up-to-date review of the literature on SVS models, which would be a useful reference for both researchers and engineers. Related materials are available at https://github.com/David-Pigeon/SyntheticSingers.