Parallel WaveGAN: A fast waveform generation model based on generative adversarial networks with multi-resolution spectrogram
This addresses the problem of slow and complex speech synthesis for applications requiring real-time performance, though it is incremental as it builds on existing GAN and WaveNet frameworks.
The paper tackles fast and high-fidelity speech waveform generation by proposing Parallel WaveGAN, a method that uses a non-autoregressive WaveNet with multi-resolution spectrogram and adversarial losses, achieving 28.68 times faster than real-time generation and a 4.16 mean opinion score.
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.