Abstract:
In recent years, neural vocoders have surpassed classical
speech generation approaches in naturalness and perceptual
quality of the synthesized speech. Computationally heavy
models like WaveNet and WaveGlow achieve best results,
while lightweight GAN models, e.g. MelGAN and Parallel
WaveGAN, remain inferior in terms of perceptual quality.
We therefore propose StyleMelGAN, a lightweight neural
vocoder allowing synthesis of high-fidelity speech with low
computational complexity. StyleMelGAN employs temporal adaptive normalization to style a low-dimensional noise
vector with the acoustic features of the target speech. For
efficient training, multiple random-window discriminators
adversarially evaluate the speech signal analyzed by a filter
bank, with regularization provided by a multi-scale spectral
reconstruction loss. The highly parallelizable speech generation is several times faster than real-time on CPUs and GPUs.
MUSHRA and P.800 listening tests show that StyleMelGAN
outperforms prior neural vocoders in copy-synthesis and
Text-to-Speech scenarios.
Preprint: arxiv (accepted to
ICASSP 2021)
