Self-Supervised Learning of Speech Representation via Redundancy Reduction
| dc.contributor.author | Brima, Yusuf | |
| dc.contributor.editor | Stolzenburg, Frieder | |
| dc.date.accessioned | 2023-09-20T04:20:44Z | |
| dc.date.available | 2023-09-20T04:20:44Z | |
| dc.date.issued | 2023 | |
| dc.description.abstract | Our proposed research aims to contribute to the field of SSL for speech processing by developing representations that effectively capture latent speaker statistics. A comprehensive evaluation in various downstream tasks will provide a thorough assessment of the representations’ suitability and performance. The outcomes of this research will advance our understanding and utilization of SSL in speech representation learning, ultimately enhancing speaker-related applications and their practical implications. | en |
| dc.identifier.doi | 10.18420/ki2023-dc-02 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/42402 | |
| dc.language.iso | en | |
| dc.pubPlace | Bonn | |
| dc.publisher | Gesellschaft für Informatik e.V. | |
| dc.relation.ispartof | DC@KI2023: Proceedings of Doctoral Consortium at KI 2023 | |
| dc.subject | Barlow Twins; Acoustic Analysis; Deep Learning; Disentangled Representations; Representation Learning; Redundancy Reduction; Speech Analysis | en |
| dc.title | Self-Supervised Learning of Speech Representation via Redundancy Reduction | en |
| dc.type | Text | |
| gi.citation.endPage | 19 | |
| gi.citation.startPage | 11 | |
| gi.conference.date | 45195 | |
| gi.conference.location | Berlin | |
| gi.conference.sessiontitle | Doctoral Consortium at KI 2023 | |
| gi.document.quality | digidoc |
Dateien
Originalbündel
1 - 1 von 1
Vorschaubild nicht verfügbar
- Name:
- A2-paper.pdf
- Größe:
- 610.58 KB
- Format:
- Adobe Portable Document Format