Skip to main content

PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many Mapping

Junhyeok Lee (MINDsLab Inc.); Seungu Han (MINDsLab Inc.,); Hyunjae Cho (MINDsLab Inc.); Wonbin Jung (MINDs Lab Inc.)

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00
04 Jun 2023

Previous generative adversarial network (GAN)-based neural vocoders are trained to reconstruct the exact ground truth waveform from the paired mel-spectrogram and do not consider the one-to-many relationship of speech synthesis. This conventional training causes overfitting for both the discriminators and the generator, leading to the periodicity artifacts in the generated audio signal. In this work, we present PhaseAug, the first differentiable augmentation for speech synthesis that rotates the phase of each frequency bin to simulate one-to-many mapping. With our proposed method, we outperform baselines without any architecture modification. Code and audio samples will be available at https://github.com/mindslab-ai/phaseaug.

More Like This

  • SPS
    Members: Free
    IEEE Members: $11.00
    Non-members: $15.00