2021/09/30 by James King, Ramon Viñas Torné, King, James +8
Computer Science · Engineering · #Acoustic Wave Phenomena Research #Advanced Image Processing Techniques #Aerodynamics and Acoustics in Jet Flows #Audio and Speech Processing (eess.AS) #Digital Media Forensic Detection #FOS: Computer and information sciences #FOS: Electrical engineering #Image and Signal Denoising Methods #Sound (cs.SD) #Speech and Audio Processing #cs.SD #eess.AS #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2109.14994
arxiv created 2021/09/30 · openalex publication_date 2021/09/30 · arxiv updated 2021/10/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
There have been several successful deep learning models that perform audio super-resolution. Many of these approaches involve using preprocessed feature extraction which requires a lot of domain-specific signal processing knowledge to implement. Convolutional Neural Networks (CNNs) improved upon this framework by automatically learning filters. An example of a convolutional approach is AudioUNet, which takes inspiration from novel methods of upsampling images. Our paper compares the pre-upsampling AudioUNet to a new generative model that upsamples the signal before using deep learning to transform it into a more believable signal. Based on the EDSR network for image super-resolution, the newly proposed model outperforms UNet with a 20% increase in log spectral distance and a mean opinion score of 4.06 compared to 3.82 for the two times upsampling case. AudioEDSR also has 87% fewer parameters than AudioUNet. How incorporating AudioUNet into a Wasserstein GAN (with gradient penalty) (WGAN-GP) structure can affect training is also explored. Finally the effects artifacting has on the current state of the art is analysed and solutions to this problem are proposed. The methods used in this paper have broad applications to telephony, audio recognition and audio generation tasks.