1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Sequence-Level Consistency Training For Semi-Supervised End-To-End Automatic Speech Recognition

Sequence-Level Consistency Training For Semi-Supervised End-To-End Automatic Speech Recognition

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

This paper presents a novel semi-supervised end-to-end automatic speech recognition (ASR) method that employs consistency training with the use of unlabeled data. In consistency training, unlabeled data can be utilized for constraining a model such that i

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Sequence-Level Consistency Training For Semi-Supervised End-To-End Automatic Speech Recognition

00:13:37

0 views

This paper presents a novel semi-supervised end-to-end automatic speech recognition (ASR) method that employs consistency training with the use of unlabeled data. In consistency training, unlabeled data can be utilized for constraining a model such that i