# Generative Adversarial Network based Speaker Adaptation for High Fidelity WaveNet Vocoder

arXiv: https://arxiv.org/abs/1812.02339 · HTML: https://mlsanity.com/paper/1812.02339/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Dec 2018.

## Built on by (most cited first, 1 of 1)

- [Unified Source-Filter GAN: Unified Source-filter Network Based On Factorization of Quasi-Periodic Parallel WaveGAN](https://mlsanity.com/paper/2104.04668/) (2021)

## Abstract (arXiv)

Although state-of-the-art parallel WaveNet has addressed the issue of real-time waveform generation, there remains problems. Firstly, due to the noisy input signal of the model, there is still a gap between the quality of generated and natural waveforms. Secondly, a parallel WaveNet is trained under a distillation framework, which makes it tedious to adapt a well trained model to a new speaker. To address these two problems, in this paper we propose an end-to-end adaptation method based on the generative adversarial network (GAN), which can reduce the computational cost for the training of new speaker adaptation. Our subjective experiments shows that the proposed training method can further reduce the quality gap between generated and natural waveforms.