LIFI: Towards Linguistically Informed Frame Interpolation

In this work, we explore a new problem of frame interpolation for speech videos. Such content today forms the major form of online communication. We try to solve this problem by using several deep learning video generation algorithms to generate the missing frames. We also provide examples where com...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2020-12
Main Authors: Mathur, Aradhya Neeraj, Batra, Devansh, Kumar, Yaman, Shah, Rajiv Ratn, Zimmermann, Roger
Format: Article
Language:English
Subjects:
Algorithms
Computer vision
Interpolation
Machine learning
Speech
Video
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this work, we explore a new problem of frame interpolation for speech videos. Such content today forms the major form of online communication. We try to solve this problem by using several deep learning video generation algorithms to generate the missing frames. We also provide examples where computer vision models despite showing high performance on conventional non-linguistic metrics fail to accurately produce faithful interpolation of speech. With this motivation, we provide a new set of linguistically-informed metrics specifically targeted to the problem of speech videos interpolation. We also release several datasets to test computer vision video generation models of their speech understanding.
ISSN:2331-8422