AudioSR: Versatile Audio Super-resolution at Scale
It addresses the problem of limited versatility in audio super-resolution for digital applications, offering a plug-and-play solution for multiple audio types, though it is incremental in method.
The paper tackles audio super-resolution by introducing AudioSR, a diffusion-based model that upsamples audio from 2kHz-16kHz to 24kHz bandwidth at 48kHz sampling rate, achieving strong results on benchmarks and enhancing quality in various audio generative models.
Audio super-resolution is a fundamental task that predicts high-frequency components for low-resolution audio, enhancing audio quality in digital applications. Previous methods have limitations such as the limited scope of audio types (e.g., music, speech) and specific bandwidth settings they can handle (e.g., 4kHz to 8kHz). In this paper, we introduce a diffusion-based generative model, AudioSR, that is capable of performing robust audio super-resolution on versatile audio types, including sound effects, music, and speech. Specifically, AudioSR can upsample any input audio signal within the bandwidth range of 2kHz to 16kHz to a high-resolution audio signal at 24kHz bandwidth with a sampling rate of 48kHz. Extensive objective evaluation on various audio super-resolution benchmarks demonstrates the strong result achieved by the proposed model. In addition, our subjective evaluation shows that AudioSR can acts as a plug-and-play module to enhance the generation quality of a wide range of audio generative models, including AudioLDM, Fastspeech2, and MusicGen. Our code and demo are available at https://audioldm.github.io/audiosr.