SiFiSinger: A High-Fidelity End-to-End Singing Voice Synthesizer based on Source-filter Model
Not on the map. Why?
Abstract (arXiv)
This paper presents an advanced end-to-end singing voice synthesis (SVS) system based on the source-filter mechanism that directly translates lyrical and melodic cues into expressive and high-fidelity human-like singing. Similarly to VISinger 2, the proposed system also utilizes training paradigms evolved from VITS and incorporates elements like the fundamental pitch (F0) predictor and waveform generation decoder. To address the issue that the coupling of mel-spectrogram features with F0 information may introduce errors during F0 prediction, we consider two strategies. Firstly, we leverage mel-cepstrum (mcep) features to decouple the intertwined mel-spectrogram and F0 characteristics. Secondly, inspired by the neural source-filter models, we introduce source excitation signals as the representation of F0 in the SVS system, aiming to capture pitch nuances more accurately. Meanwhile, differentiable mcep and F0 losses are employed as the waveform decoder supervision to fortify the prediction accuracy of speech envelope and pitch in the generated speech. Experiments on the Opencpop dataset demonstrate efficacy of the proposed model in synthesis quality and intonation accuracy.
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 14 of its 25 references that are in the map. First posted on arXiv 16 Oct 2024.
Builds on
14 of 25 references.
References · 14
- 2020HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesiscited by 1,154
- 2021Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speechcited by 561
- 2021DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanismcited by 154
- 2018CREPE: A Convolutional Representation for Pitch Estimationcited by 110
- 2022Opencpop: A High-Quality Open Source Chinese Popular Song Corpus for Singing Voice Synthesiscited by 53
- 2019Neural source-filter waveform models for statistical parametric speech synthesiscited by 46
- 2021VISinger: Variational Inference with Adversarial Learning for End-to-End Singing Voice Synthesiscited by 38
- 2020DeepSinger: Singing Voice Synthesis with Data Mined From the Webcited by 32
- 2020ByteSing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-Decoder Acoustic Models and WaveRNN Vocoderscited by 21
- 2019Sequence-to-sequence Singing Synthesis Using the Feed-forward Transformercited by 17
- 2021Sinsy: A Deep Neural Network-Based Singing Voice Synthesis Systemcited by 14
- 2022VISinger 2: High-Fidelity End-to-End Singing Voice Synthesis Enhanced by Digital Signal Processing Synthesizercited by 14
2 more
Built on by
Citing papers per year: 2025: 3.
3 papers.