Voice command generation using Progressive Wavegans

TL;DR

This paper introduces extensions to WaveGAN, a GAN-based sound generation method, to enhance the human likeness of synthetic speech, demonstrating moderate improvements through listening tests.

Contribution

The paper proposes preprocessing, audio-to-audio generation, skip connections, and progressive structures to improve WaveGAN's speech synthesis quality.

Findings

Moderate improvement in human likeness (Cohen's d=0.65)

Listening tests with 30 volunteers support effectiveness

Extensions outperform original WaveGAN in speech quality

Abstract

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.