Multitask Training with Text Data for End-to-End Speech Recognition

Peidong Wang
Peidong Wang
Cited by: 0|Bibtex|Views20
Other Links: arxiv.org

Abstract:

We propose a multitask training method for attention-based end-to-end speech recognition models to better incorporate language level information. We regularize the decoder in a sequence-to-sequence architecture by multitask training it on both the speech recognition task and a next-token prediction language modeling task. Trained on eit...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments