Skip to content
/ SyncVSR Public

[Interspeech 2024] SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization

www.isca-archive.org/interspeech_2024/ahn24_interspeech.pdf

License

MIT license
60 stars 3 forks Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

KAIST-AILab/SyncVSR

About

[Interspeech 2024] SyncVSR: Data-Efficient Visual Speech Recognition with End-to-End Crossmodal Audio Token Synchronization

www.isca-archive.org/interspeech_2024/ahn24_interspeech.pdf

Topics

lipreading vsr

Resources

Readme

License

MIT license
Activity
Custom properties

Stars

60 stars

Watchers

10 watching

Forks

3 forks
Report repository

Releases 1

weight & audio token update Latest
Oct 3, 2024

Packages

No packages published

Contributors 3

  •  
  •  
  •  

Languages