University of Southern CaliforniaUSC
USC ICT TwitterUSC ICT FacebookUSC ICT YouTube

New Phoneme Scheduling Tool for Automated Lip Syncing to Audio | Announcements | Forum


Please consider registering

sp_LogInOut Log In sp_Registration Register

Register | Lost password?
Advanced Search

— Forum Scope —

— Match —

— Forum Options —

Minimum search word length is 3 characters - maximum search word length is 84 characters

sp_Feed Topic RSS sp_TopicIcon
New Phoneme Scheduling Tool for Automated Lip Syncing to Audio
May 25, 2013
3:37 pm
Forum Posts: 983
Member Since:
December 1, 2011
sp_UserOfflineSmall Offline
We've added a phoneme scheduling tool by leveraging from scripts from the CSLU toolkit.
This allows you to record a .wav file, write a transcription of the speech, then automatically generate the phonemes that SmartBody needs to automatically lip sync to that audio. 
The capability to lip sync to an audio file has always been in SmartBody, but it has been difficult to locate a tool that is compatible with and can be distributed alongside SmartBody. Note that you will need to download those scripts from the CSLU toolkit and adhere to their license as well.
The code is located in the smartbody/tools/CSLUPhonemeScheduler directory, and details are in the SmartBody Manual in the section on 'Configuring Speech'. 
Ari Shapiro