Difference between revisions of "Speech2Face: Learning the Face Behind a Voice"

From statwiki
Jump to: navigation, search
(Model Architecture)
Line 13: Line 13:
  
 
'''Speech2Face model and training pipeline'''
 
'''Speech2Face model and training pipeline'''
 +
 
[[File:ModelFramework.jpg]]
 
[[File:ModelFramework.jpg]]
  
  
 
'''Voice Encoder Architechture'''  
 
'''Voice Encoder Architechture'''  
 +
 
[[File:VoiceEncoderArch.JPG]]
 
[[File:VoiceEncoderArch.JPG]]
 
 
 
  
 
== Results ==
 
== Results ==

Revision as of 12:30, 24 November 2020

Presented by

Ian Cheung, Russell Parco, Scholar Sun, Jacky Yao, Daniel Zhang

Introduction

Previous Work

Motivation

Model Architecture

Speech2Face model and training pipeline

ModelFramework.jpg


Voice Encoder Architechture

VoiceEncoderArch.JPG

Results

Conclusion

Discussion

Critiques

References