NU-Wave 2: A General Neural Audio Upsampling Model for Various Sampling Rates

TL;DR

NU-Wave 2 is a versatile neural audio upsampling model based on diffusion that can handle various input sampling rates with a single trained model, improving efficiency and performance.

Contribution

It introduces NU-Wave 2, a diffusion-based model that generalizes audio upsampling across multiple sampling rates using novel spectral features.

Findings

Produces high-resolution audio across different input rates

Requires fewer parameters than comparable models

Effective in resolving harmonics and bandwidth issues

Abstract

Conventionally, audio super-resolution models fixed the initial and the target sampling rates, which necessitate the model to be trained for each pair of sampling rates. We introduce NU-Wave 2, a diffusion model for neural audio upsampling that enables the generation of 48 kHz audio signals from inputs of various sampling rates with a single model. Based on the architecture of NU-Wave, NU-Wave 2 uses short-time Fourier convolution (STFC) to generate harmonics to resolve the main failure modes of NU-Wave, and incorporates bandwidth spectral feature transform (BSFT) to condition the bandwidths of inputs in the frequency domain. We experimentally demonstrate that NU-Wave 2 produces high-resolution audio regardless of the sampling rate of input while requiring fewer parameters than other models. The official code and the audio samples are available at https://mindslab-ai.github.io/nuwave2.