Reconstructing Images and Audio: Multi-modal autoencoders

Keywords

No Thumbnail Available

Issue Date

2020-07-01

Language

en

Document type

Journal Title

Journal ISSN

Volume Title

Publisher

Title

ISSN

Volume

Issue

Startpage

Endpage

DOI

Abstract

In this thesis, a multi-modal auto-encoder is built that reconstructs both images and audio. The goal is to build a multi-modal auto-encoder that is capable of learning a shared representation between images of digits and audio of the pronunciation of the digits. This model, while fairly accurate on digits, does not perform very well on the audio data.

Description

Citation

Faculty

Faculteit der Sociale Wetenschappen