Large scale weakly and semi-supervised learning for low-resource video ASR

Singh Kritika
Singh Kritika
Manohar Vimal
Manohar Vimal
Xiao Alex
Xiao Alex
Edunov Sergey
Edunov Sergey
Liptchinsky Vitaliy
Liptchinsky Vitaliy
Fuegen Christian
Fuegen Christian
Saraf Yatharth
Saraf Yatharth
Cited by: 0|Bibtex|Views118|Links

Abstract:

Many semi- and weakly-supervised approaches have been investigated for overcoming the labeling cost of building high quality speech recognition systems. On the challenging task of transcribing social media videos in low-resource conditions, we conduct a large scale systematic comparison between two self-labeling methods on one hand, and...More

Code:

Data:

Your rating :
0

 

Tags
Comments