Original title: Deep prior audio compression
Authors: Švento, Michal ; Balušík, Peter
Document type: Papers
Language: eng
Publisher: Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologií
Abstract: Audio compression is still an up-to-date topic because the demand for big data streams is rapidly increasing. Deep learning has brought up new algorithms that decrease bitrates with good perception quality. The novel approach in generative artificial intelligence is to produce new data from prior stored in network parameters, called a deep prior. The deep audio prior framework shows its success in various tasks such as inpainting, declipping, and bandwidth extension, but it has not been tested for compression. In this paper, we test this method with a prebuilt network for inpainting. Our idea of compression is based on reducing the number of time-frequency coefficients in the spectrogram while allowing the reconstruction of the original signal with high quality.
Keywords: audio processing; compression; deep audio prior; deep learning
Host item entry: Proceedings I of the 30st Conference STUDENT EEICT 2024: General papers, ISBN 978-80-214-6231-1, ISSN 2788-1334

Institution: Brno University of Technology (web)
Document availability information: Fulltext is available in the Brno University of Technology Digital Library.
Original record: https://hdl.handle.net/11012/249240

Permalink: http://www.nusl.cz/ntk/nusl-622557


The record appears in these collections:
Universities and colleges > Public universities > Brno University of Technology
Conference materials > Papers