Improve GAN-based Neural Vocoder using Pointwise Relativistic LeastSquare GAN

By Cong Wang, Yu Chen, Bin Wang, Yi Shi. 2021

GAN-based neural vocoders, such as Parallel WaveGAN and MelGAN have attracted great interest due to their lightweight and parallel structures, enabling them to generate high fidelity waveform in a real-time manner. In this paper, inspired by Relativistic GAN, we introduce a novel variant of the LSGAN framework under the context of waveform synthesis, named Pointwise Relativistic LSGAN (PRLSGAN). In this approach, we take the truism score distribution into consideration and combine the original MSE loss with the proposed pointwise relative discrepancy loss to increase the difficulty of the generator to fool the discriminator, leading to improved generation quality. Moreover, PRLSGAN is a general-purposed framework that can be combined with any GAN-based neural vocoder to enhance its generation quality. Experiments have shown a consistent performance boost based on Parallel WaveGAN and MelGAN, demonstrating the effectiveness and strong generalization ability of our proposed PRLSGAN neural vocoders.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Xu Tan
2. Tao Qin
3. Tie-Yan Liu
4. Frank K. Soong
5. Yi Ren
6. Olivier Chapelle
7. Yanqing Liu
8. Rongjie Huang

Citations in the corpus

• A Survey on Neural Speech Synthesis (2021, background): “A lot of vocoders leverage GAN to ensure the audio generation quality, including WaveGAN [66], GAN-TTS [23], MelGAN [174], Parallel WaveGAN [396], HiFi-GAN [170], and other GAN-based vocoders [395, 385, 306, 410, 366, 134].”