Transformer-based Acoustic Modeling for Hybrid Speech Recognition

Le Duc
Le Duc
Liu Chunxi
Liu Chunxi
Xiao Alex
Xiao Alex
Mahadeokar Jay
Mahadeokar Jay
Huang Hongzhao
Huang Hongzhao
Tjandra Andros
Tjandra Andros
Zhang Xiaohui
Zhang Xiaohui
Zhang Frank
Zhang Frank
Fuegen Christian
Fuegen Christian

ICASSP, pp. 6874-6878, 2019.

Cited by: 36|Bibtex|Views118|DOI:https://doi.org/10.1109/ICASSP40776.2020.9054345
EI
Other Links: arxiv.org|academic.microsoft.com|dblp.uni-trier.de

Abstract:

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also present a preliminary study of using limited right context in transformer mo...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments