Voice command generation using Progressive Wavegans
This work addresses the challenge of generating realistic voice commands for applications in speech synthesis, but it is incremental as it builds upon an existing WaveGAN approach.
The paper tackled the problem of generating synthetic speech samples by proposing extensions to the WaveGAN paradigm, resulting in a moderate improvement in human likeness with a Cohen's d coefficient of 0.65 compared to the original method.
Generative Adversarial Networks (GANs) have become exceedingly popular in a wide range of data-driven research fields, due in part to their success in image generation. Their ability to generate new samples, often from only a small amount of input data, makes them an exciting research tool in areas with limited data resources. One less-explored application of GANs is the synthesis of speech and audio samples. Herein, we propose a set of extensions to the WaveGAN paradigm, a recently proposed approach for sound generation using GANs. The aim of these extensions - preprocessing, Audio-to-Audio generation, skip connections and progressive structures - is to improve the human likeness of synthetic speech samples. Scores from listening tests with 30 volunteers demonstrated a moderate improvement (Cohen's d coefficient of 0.65) in human likeness using the proposed extensions compared to the original WaveGAN approach.