Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram

Code

• github.com/coqui-ai/TTS
  pytorch★ 44,894
• github.com/PaddlePaddle/PaddleSpeech
  paddle★ 12,564
• github.com/TensorSpeech/TensorflowTTS
  tf★ 3,995
• github.com/facebookresearch/denoiser
  pytorch★ 1,882
• github.com/bigpon/vcc20_baseline_cyclevae
  pytorch★ 131
• github.com/bigpon/QPPWG
  pytorch★ 46
• github.com/yanggeng1995/GAN-TTS
  pytorch★ 0
• github.com/Moon-sung-woo/ParallelWaveGan_korean
  pytorch★ 0
• github.com/yanggeng1995/FB-MelGAN
  pytorch★ 0
• github.com/mukeshv0/ParallelWaveGAN
  pytorch★ 0

Abstract

We propose Parallel WaveGAN, a distillation-free, fast, and small-footprint waveform generation method using a generative adversarial network. In the proposed method, a non-autoregressive WaveNet is trained by jointly optimizing multi-resolution spectrogram and adversarial loss functions, which can effectively capture the time-frequency distribution of the realistic speech waveform. As our method does not require density distillation used in the conventional teacher-student framework, the entire model can be easily trained. Furthermore, our model is able to generate high-fidelity speech even with its compact architecture. In particular, the proposed Parallel WaveGAN has only 1.44 M parameters and can generate 24 kHz speech waveform 28.68 times faster than real-time on a single GPU environment. Perceptual listening test results verify that our proposed method achieves 4.16 mean opinion score within a Transformer-based text-to-speech framework, which is comparative to the best distillation-based Parallel WaveNet system.

Tasks

Reproductions