Publication detail

Deep prior audio compression

ŠVENTO, M. BALUŠÍK, P.

Original Title

Deep prior audio compression

Type

article in a collection out of WoS and Scopus

Language

English

Original 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 pre-built 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; deep learning; deep audio prior; compression

Authors

ŠVENTO, M.; BALUŠÍK, P.

Released

23. 4. 2024

Publisher

Brno University of Technology, Faculty of Electrical Engineering and Communication

Location

Brno

ISBN

2788-1334

Periodical

Proceedings II of the Conference STUDENT EEICT

State

Czech Republic

Pages count

5

BibTex

@inproceedings{BUT188830,
  author="Michal {Švento} and Peter {Balušík}",
  title="Deep prior audio compression",
  booktitle="Proceedings I of the 30th Student EEICT 2024 (General Papers)",
  year="2024",
  series="1",
  journal="Proceedings II of the Conference STUDENT EEICT",
  pages="5",
  publisher="Brno University of Technology, Faculty of Electrical Engineering and Communication",
  address="Brno",
  issn="2788-1334"
}