Semi-Supervised Learning with Data Augmentation for End-to-End ASR

Jesús Andrés-Ferrer
Jesús Andrés-Ferrer
Puming Zhan
Puming Zhan

INTERSPEECH, pp. 2802-2806, 2020.

Cited by: 0|Bibtex|Views31|DOI:https://doi.org/10.21437/Interspeech.2020-1337
EI
Other Links: arxiv.org|dblp.uni-trier.de|academic.microsoft.com

Abstract:

In this paper, we apply Semi-Supervised Learning (SSL) along with Data Augmentation (DA) for improving the accuracy of End-to-End ASR. We focus on the consistency regularization principle, which has been successfully applied to image classification tasks, and present sequence-to-sequence (seq2seq) versions of the FixMatch and Noisy Stud...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments