2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information

2021 IEEE International Conference on Acoustics, Speech and Signal Processing

6-11 June 2021 • Toronto, Ontario, Canada

Extracting Knowledge from Information
Login Paper Search My Schedule Paper Index Help

My ICASSP 2021 Schedule

Note: Your custom schedule will not be saved unless you create a new account or login to an existing account.
  1. Create a login based on your email (takes less than one minute)
  2. Perform 'Paper Search'
  3. Select papers that you desire to save in your personalized schedule
  4. Click on 'My Schedule' to see the current list of selected papers
  5. Click on 'Printable Version' to create a separate window suitable for printing (the header and menu will appear, but will not actually print)

Paper Detail

Paper IDHLT-10.2
Paper Title LIFI: TOWARDS LINGUISTICALLY INFORMED FRAME INTERPOLATION
Authors Aradhya Mathur, IIIT Delhi, India; Devansh Batra, IIIT-D, India; Yaman Kumar Singla, IIIT-D; Adobe; State University of New York at Buffalo, India; Rajiv Ratn Shah, IIIT Delhi, India; Changyou Chen, State University of New York at Buffalo, United States; Roger Zimmermann, NUS, Singapore
SessionHLT-10: Multi-modality in Language
LocationGather.Town
Session Time:Wednesday, 09 June, 16:30 - 17:15
Presentation Time:Wednesday, 09 June, 16:30 - 17:15
Presentation Poster
Topic Human Language Technology: [HLT-MMPL] Multimodal Processing of Language
IEEE Xplore Open Preview  Click here to view in IEEE Xplore
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.