Deep prior audio compression

Simple item page
but.event.date23.04.2024cs
but.event.titleSTUDENT EEICT 2024cs
dc.contributor.authorŠvento, Michal
dc.contributor.authorBalušík, Peter
dc.date.accessioned2024-07-09T07:38:39Z
dc.date.available2024-07-09T07:38:39Z
dc.date.issued2024cs
dc.description.abstractAudio 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.en
dc.formattextcs
dc.format.extent226-230cs
dc.format.mimetypeapplication/pdfen
dc.identifier.citationProceedings I of the 30st Conference STUDENT EEICT 2024: General papers. s. 226-230. ISBN 978-80-214-6231-1cs
dc.identifier.isbn978-80-214-6231-1
dc.identifier.issn2788-1334
dc.identifier.urihttps://hdl.handle.net/11012/249240
dc.language.isoencs
dc.publisherVysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologiícs
dc.relation.ispartofProceedings I of the 30st Conference STUDENT EEICT 2024: General papersen
dc.relation.urihttps://www.eeict.cz/eeict_download/archiv/sborniky/EEICT_2024_sbornik_1.pdfcs
dc.rights© Vysoké učení technické v Brně, Fakulta elektrotechniky a komunikačních technologiícs
dc.rights.accessopenAccessen
dc.subjectaudio processingen
dc.subjectdeep learningen
dc.subjectdeep audio prioren
dc.subjectcompressionen
dc.titleDeep prior audio compressionen
dc.type.driverconferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
eprints.affiliatedInstitution.departmentFakulta elektrotechniky a komunikačních technologiícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
226-eeict-2024.pdf
Size:
881.13 KB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Student EEICT 2024: General Papers