Joint Masked CPC and CTC Training for ASR

Chaitanya Talnikar
Chaitanya Talnikar
Tatiana Likhomanenko
Tatiana Likhomanenko
Cited by: 1|Views10

Abstract:

Self-supervised learning (SSL) has shown promise in learning representations of audio that are useful for automatic speech recognition (ASR). But, training SSL models like wav2vec~2.0 requires a two-stage pipeline. In this paper we demonstrate a single-stage training of ASR models that can utilize both unlabeled and labeled data. During...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments