# HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis

arXiv: https://arxiv.org/abs/2009.01776 · HTML: https://mlsanity.com/paper/2009.01776/

## Key facts

- Cited by 39 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Sep 2020.

## Built on by (most cited first, 30 of 39)

- [A Survey on Neural Speech Synthesis](https://mlsanity.com/paper/2106.15561/) (2021)
- [DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism](https://mlsanity.com/paper/2105.02446/) (2021)
- [Mega-TTS: Zero-Shot Text-to-Speech at Scale with Intrinsic Inductive Bias](https://mlsanity.com/paper/2306.03509/) (2023)
- [CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model](https://mlsanity.com/paper/2305.06908/) (2023)
- [Foundation Models for Music: A Survey](https://mlsanity.com/paper/2408.14340/) (2024)
- [The Singing Voice Conversion Challenge 2023](https://mlsanity.com/paper/2306.14422/) (2023)
- [DelightfulTTS: The Microsoft Speech Synthesis System for Blizzard Challenge 2021](https://mlsanity.com/paper/2110.12612/) (2021)
- [DiffRhythm 2: Efficient and High Fidelity Song Generation via Block Flow Matching](https://mlsanity.com/paper/2510.22950/) (2025)
- [Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System](https://mlsanity.com/paper/2108.02776/) (2021)
- [FSD: An Initial Chinese Dataset for Fake Song Detection](https://mlsanity.com/paper/2309.02232/) (2023)
- [Prompt-Singer: Controllable Singing-Voice-Synthesis with Natural Language Prompt](https://mlsanity.com/paper/2403.11780/) (2024)
- [SongCreator: Lyrics-based Universal Song Generation](https://mlsanity.com/paper/2409.06029/) (2024)
- [HiFTNet: A Fast High-Quality Neural Vocoder with Harmonic-plus-Noise Filter and Inverse Short Time Fourier Transform](https://mlsanity.com/paper/2309.09493/) (2023)
- [HiddenSinger: High-Quality Singing Voice Synthesis via Neural Audio Codec and Latent Diffusion Models](https://mlsanity.com/paper/2306.06814/) (2023)
- [WeSinger: Data-augmented Singing Voice Synthesis with Auxiliary Losses](https://mlsanity.com/paper/2203.10750/) (2022)
- [LeVo 2: Stable and Melodious Song Generation via Hierarchical Representation Modeling and Progressive Post-Training](https://mlsanity.com/paper/2606.30642/) (2026)
- [RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses](https://mlsanity.com/paper/2111.00962/) (2021)
- [Mandarin Singing Voice Synthesis with Denoising Diffusion Probabilistic Wasserstein GAN](https://mlsanity.com/paper/2209.10446/) (2022)
- [YingMusic-Singer: Zero-shot Singing Voice Synthesis and Editing with Annotation-free Melody Guidance](https://mlsanity.com/paper/2512.04779/) (2025)
- [Singing-Tacotron: Global duration control attention and dynamic filter for End-to-end singing voice synthesis](https://mlsanity.com/paper/2202.07907/) (2022)
- [Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information](https://mlsanity.com/paper/2308.16836/) (2023)
- [Versatile Framework for Song Generation with Prompt-based Control](https://mlsanity.com/paper/2504.19062/) (2025)
- [Conan: A Chunkwise Online Network for Zero-Shot Adaptive Voice Conversion](https://mlsanity.com/paper/2507.14534/) (2025)
- [Latent Space Explorations of Singing Voice Synthesis using DDSP](https://mlsanity.com/paper/2103.07197/) (2021)
- [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)
- [PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model](https://mlsanity.com/paper/2402.14692/) (2024)
- [MakeSinger: A Semi-Supervised Training Method for Data-Efficient Singing Voice Synthesis via Classifier-free Diffusion Guidance](https://mlsanity.com/paper/2406.05965/) (2024)
- [Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control](https://mlsanity.com/paper/2111.09146/) (2021)
- [Applications and Advances of Artificial Intelligence in Music Generation:A Review](https://mlsanity.com/paper/2409.03715/) (2024)

## Abstract (arXiv)

High-fidelity singing voices usually require higher sampling rate (e.g., 48kHz) to convey expression and emotion. However, higher sampling rate causes the wider frequency band and longer waveform sequences and throws challenges for singing voice synthesis (SVS) in both frequency and time domains. Conventional SVS systems that adopt small sampling rate cannot well address the above challenges. In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice. HiFiSinger consists of a FastSpeech based acoustic model and a Parallel WaveGAN based vocoder to ensure fast training and inference and also high voice quality. To tackle the difficulty of singing modeling caused by high sampling rate (wider frequency band and longer waveform), we introduce multi-scale adversarial training in both the acoustic model and vocoder to improve singing modeling. Specifically, 1) To handle the larger range of frequencies caused by higher sampling rate, we propose a novel sub-frequency GAN (SF-GAN) on mel-spectrogram generation, which splits the full 80-dimensional mel-frequency into multiple sub-bands and models each sub-band with a separate discriminator. 2) To model longer waveform sequences caused by higher sampling rate, we propose a multi-length GAN (ML-GAN) for waveform generation to model different lengths of waveform sequences with separate discriminators. 3) We also introduce several additional designs and findings in HiFiSinger that are crucial for high-fidelity voices, such as adding F0 (pitch) and V/UV (voiced/unvoiced flag) as acoustic features, choosing an appropriate window/hop size for mel-spectrogram, and increasing the receptive field in vocoder for long vowel modeling. Experiment results show that HiFiSinger synthesizes high-fidelity singing voices with much higher quality: 0.32/0.44 MOS gain over 48kHz/24kHz baseline and 0.83 MOS gain over previous SVS systems.