Skip to main navigation Skip to search Skip to main content

Lifi: Towards linguistically informed frame interpolation

  • Aradhya Neeraj Mathur
  • , Devansh Batra
  • , Yaman Kumar Singla
  • , Rajiv Ratn Shah
  • , Changyou Chen
  • , Roger Zimmermann

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Here we explore the problem of speech video interpolation. With close to 70% of web traffic, such content today forms the primary form of online communication and entertainment. Despite high performance on conventional metrics like MSE, PSNR, and SSIM, we find that the state-of-the-art frame interpolation models fail to produce faithful speech interpolation. For instance, we observe the lips stay static while the person is still speaking for most interpolated frames. With this motivation, using the information of words, sub-words, and visemes, we provide a new set of linguistically informed metrics targeted explicitly to the problem of speech video interpolation. We release several datasets to test video interpolation models of their speech understanding. We also design linguistically informed deep learning video interpolation algorithms to generate the missing frames.

Original languageEnglish
Title of host publication2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7593-7597
Number of pages5
ISBN (Electronic)9781728176055
DOIs
StatePublished - 2021
Event2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Virtual, Toronto, Canada
Duration: Jun 6 2021Jun 11 2021

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2021-June

Conference

Conference2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
Country/TerritoryCanada
CityVirtual, Toronto
Period06/6/2106/11/21

Fingerprint

Dive into the research topics of 'Lifi: Towards linguistically informed frame interpolation'. Together they form a unique fingerprint.

Cite this