pith. sign in

arxiv: 1812.02455 · v1 · pith:VNN52NEJnew · submitted 2018-12-06 · 💻 cs.CL · cs.SD· eess.AS

The USTC-NEL Speech Translation system at IWSLT 2018

classification 💻 cs.CL cs.SDeess.AS
keywords systemspeechtranslationiwsltmachinerecognitionmodelstask
0
0 comments X p. Extension
pith:VNN52NEJ Add to your LaTeX paper What is a Pith Number?
\usepackage{pith}
\pithnumber{VNN52NEJ}

Prints a linked pith:VNN52NEJ badge after your title and writes the identifier into PDF metadata. Compiles on arXiv with no extra files. Learn more

read the original abstract

This paper describes the USTC-NEL system to the speech translation task of the IWSLT Evaluation 2018. The system is a conventional pipeline system which contains 3 modules: speech recognition, post-processing and machine translation. We train a group of hybrid-HMM models for our speech recognition, and for machine translation we train transformer based neural machine translation models with speech recognition output style text as input. Experiments conducted on the IWSLT 2018 task indicate that, compared to baseline system from KIT, our system achieved 14.9 BLEU improvement.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.