TY - GEN
T1 - Lifi
T2 - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021
AU - Mathur, Aradhya Neeraj
AU - Batra, Devansh
AU - Singla, Yaman Kumar
AU - Shah, Rajiv Ratn
AU - Chen, Changyou
AU - Zimmermann, Roger
N1 - Publisher Copyright: © 2021 IEEE
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - https://www.scopus.com/pages/publications/85115170633
U2 - 10.1109/ICASSP39728.2021.9413998
DO - 10.1109/ICASSP39728.2021.9413998
M3 - Conference contribution
T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
SP - 7593
EP - 7597
BT - 2021 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2021 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 6 June 2021 through 11 June 2021
ER -