Sound-to-Imagination: An Exploratory Study on Cross-Modal Translation Using Diverse Audiovisual Data

Sound-to-Imagination: An Exploratory Study on Cross-Modal Translation Using Diverse Audiovisual Data

The motivation of our research is to explore the possibilities of automatic sound-to-image (S2I) translation for enabling a human receiver to visually infer occurrences of sound-related events. We expect the computer to ‘imagine’ scenes from captured sounds, generating original images that depict th...

Full description

Bibliographic Details
Main Authors: Leonardo A. Fanzeres, Climent Nadeu
Format: Article
Language:English
Published: MDPI AG 2023-09-01
Series:Applied Sciences
Subjects:
computational imagination
cross-modal learning
deep audiovisual learning
generative adversarial networks (GANs)
information bottleneck
sound-to-image translation
Online Access:https://www.mdpi.com/2076-3417/13/19/10833

Internet

https://www.mdpi.com/2076-3417/13/19/10833

Similar Items