# DSPGAN: a GAN-based universal vocoder for high-fidelity TTS by time-frequency domain supervision from DSP

arXiv: https://arxiv.org/abs/2211.01087 · HTML: https://mlsanity.com/paper/2211.01087/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Nov 2022.

## Built on by (most cited first, 6 of 6)

- [The Singing Voice Conversion Challenge 2023](https://mlsanity.com/paper/2306.14422/) (2023)
- [DualVC: Dual-mode Voice Conversion using Intra-model Knowledge Distillation and Hybrid Predictive Coding](https://mlsanity.com/paper/2305.12425/) (2023)
- [The NPU-HWC System for the ISCSLP 2024 Inspirational and Convincing Audio Generation Challenge](https://mlsanity.com/paper/2410.23815/) (2024)
- [The ISCSLP 2024 Conversational Voice Clone (CoVoC) Challenge: Tasks, Results and Findings](https://mlsanity.com/paper/2411.00064/) (2024)
- [Training Universal Vocoders with Feature Smoothing-Based Augmentation Methods for High-Quality TTS Systems](https://mlsanity.com/paper/2409.02517/) (2024)
- [Controllable Singing Style Conversion with Boundary-Aware Information Bottleneck](https://mlsanity.com/paper/2604.05526/) (2026)

## Abstract (arXiv)

Recent development of neural vocoders based on the generative adversarial neural network (GAN) has shown obvious advantages of generating raw waveform conditioned on mel-spectrogram with fast inference speed and lightweight networks. Whereas, it is still challenging to train a universal neural vocoder that can synthesize high-fidelity speech from various scenarios with unseen speakers, languages, and speaking styles. In this paper, we propose DSPGAN, a GAN-based universal vocoder for high-fidelity speech synthesis by applying the time-frequency domain supervision from digital signal processing (DSP). To eliminate the mismatch problem caused by the ground-truth spectrograms in the training phase and the predicted spectrograms in the inference phase, we leverage the mel-spectrogram extracted from the waveform generated by a DSP module, rather than the predicted mel-spectrogram from the Text-to-Speech (TTS) acoustic model, as the time-frequency domain supervision to the GAN-based vocoder. We also utilize sine excitation as the time-domain supervision to improve the harmonic modeling and eliminate various artifacts of the GAN-based vocoder. Experiments show that DSPGAN significantly outperforms the compared approaches and it can generate high-fidelity speech for various TTS models trained using diverse data.