NU-GAN: High resolution neural upsampling with GAN
This addresses the need for high-quality audio upsampling in text-to-speech pipelines, enabling production use at standard sampling rates, though it is incremental as it builds on existing GAN techniques for audio generation.
The paper tackles the problem of audio upsampling from lower to higher sampling rates, such as 22 kHz to 44.1 kHz, which is crucial for integrating generative speech technology into high-resolution applications. The result shows that NU-GAN achieves resampling where the output is distinguishable from original audio only 7.4% higher than random chance for single-speaker data and 10.8% for multi-speaker data.
In this paper, we propose NU-GAN, a new method for resampling audio from lower to higher sampling rates (upsampling). Audio upsampling is an important problem since productionizing generative speech technology requires operating at high sampling rates. Such applications use audio at a resolution of 44.1 kHz or 48 kHz, whereas current speech synthesis methods are equipped to handle a maximum of 24 kHz resolution. NU-GAN takes a leap towards solving audio upsampling as a separate component in the text-to-speech (TTS) pipeline by leveraging techniques for audio generation using GANs. ABX preference tests indicate that our NU-GAN resampler is capable of resampling 22 kHz to 44.1 kHz audio that is distinguishable from original audio only 7.4% higher than random chance for single speaker dataset, and 10.8% higher than chance for multi-speaker dataset.