Leveraging Out-of-Task Data for End-to-End Automatic Speech Translation

Pino Juan
Pino Juan
Puzon Liezl
Puzon Liezl
Gopinath Deepak
Gopinath Deepak
Cited by: 0|Views45

Abstract:

For automatic speech translation (AST), end-to-end approaches are outperformed by cascaded models that transcribe with automatic speech recognition (ASR), then translate with machine translation (MT). A major cause of the performance gap is that, while existing AST corpora are small, massive datasets exist for both the ASR and MT subsys...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments