# Unified Source-Filter GAN with Harmonic-plus-Noise Source Excitation Generation

arXiv: https://arxiv.org/abs/2205.06053 · HTML: https://mlsanity.com/paper/2205.06053/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 22 references that are in the map.
- First posted on arXiv 12 May 2022.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [On the Variance of the Adaptive Learning Rate and Beyond](https://mlsanity.com/paper/1908.03265/) (2019)
- [Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram](https://mlsanity.com/paper/1910.11480/) (2019)
- [Efficient Neural Audio Synthesis](https://mlsanity.com/paper/1802.08435/) (2018)
- [LPCNet: Improving Neural Speech Synthesis Through Linear Prediction](https://mlsanity.com/paper/1810.11846/) (2018)
- [Neural source-filter-based waveform model for statistical parametric speech synthesis](https://mlsanity.com/paper/1810.11946/) (2018)
- [GAN Vocoder: Multi-Resolution Discriminator Is All You Need](https://mlsanity.com/paper/2103.05236/) (2021)
- [Neural Harmonic-plus-Noise Waveform Model with Trainable Maximum Voice Frequency for Text-to-Speech Synthesis](https://mlsanity.com/paper/1908.10256/) (2019)
- [Quasi-Periodic Parallel WaveGAN: A Non-autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Network](https://mlsanity.com/paper/2007.12955/) (2020)
- [PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components](https://mlsanity.com/paper/2102.07786/) (2021)
- [Quasi-Periodic WaveNet: An Autoregressive Raw Waveform Generative Model with Pitch-dependent Dilated Convolution Neural Network](https://mlsanity.com/paper/2007.05663/) (2020)
- [Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN](https://mlsanity.com/paper/2104.04668/) (2021)

## Built on by (most cited first, 5 of 5)

- [The Singing Voice Conversion Challenge 2023](https://mlsanity.com/paper/2306.14422/) (2023)
- [Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder](https://mlsanity.com/paper/2210.15533/) (2022)
- [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)
- [Period VITS: Variational Inference with Explicit Pitch Modeling for End-to-end Emotional Speech Synthesis](https://mlsanity.com/paper/2210.15964/) (2022)
- [NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit](https://mlsanity.com/paper/2210.15987/) (2022)

## Abstract (arXiv)

This paper introduces a unified source-filter network with a harmonic-plus-noise source excitation generation mechanism. In our previous work, we proposed unified Source-Filter GAN (uSFGAN) for developing a high-fidelity neural vocoder with flexible voice controllability using a unified source-filter neural network architecture. However, the capability of uSFGAN to model the aperiodic source excitation signal is insufficient, and there is still a gap in sound quality between the natural and generated speech. To improve the source excitation modeling and generated sound quality, a new source excitation generation network separately generating periodic and aperiodic components is proposed. The advanced adversarial training procedure of HiFiGAN is also adopted to replace that of Parallel WaveGAN used in the original uSFGAN. Both objective and subjective evaluation results show that the modified uSFGAN significantly improves the sound quality of the basic uSFGAN while maintaining the voice controllability.