CUNI Neural ASR with Phoneme-Level Intermediate Step for Non-Native SLT at IWSLT 2020
The result's identifiers
Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F20%3A10424489" target="_blank" >RIV/00216208:11320/20:10424489 - isvavai.cz</a>
Result on the web
<a href="https://www.aclweb.org/anthology/2020.iwslt-1.24" target="_blank" >https://www.aclweb.org/anthology/2020.iwslt-1.24</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.18653/v1/2020.iwslt-1.24" target="_blank" >10.18653/v1/2020.iwslt-1.24</a>
Alternative languages
Result language
angličtina
Original language name
CUNI Neural ASR with Phoneme-Level Intermediate Step for Non-Native SLT at IWSLT 2020
Original language description
In this paper, we present our submission to the Non-Native Speech Translation Task for IWSLT 2020. Our main contribution is a proposed speech recognition pipeline that consists of an acoustic model and a phoneme-to grapheme model. As an intermediate representation, we utilize phonemes. We demonstrate that the proposed pipeline surpasses commercially used automatic speech recognition (ASR) and submit it into the ASR track. We complement this ASR with off-the-shelf MT systems to take part also in the speech translation track.
Czech name
—
Czech description
—
Classification
Type
D - Article in proceedings
CEP classification
—
OECD FORD branch
10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Result continuities
Project
<a href="/en/project/GX19-26934X" target="_blank" >GX19-26934X: Neural Representations in Multi-modal and Multi-lingual Modeling</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)
Others
Publication year
2020
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů
Data specific for result type
Article name in the collection
Proceedings of the 17th International Conference on Spoken Language Translation
ISBN
978-1-952148-07-1
ISSN
—
e-ISSN
—
Number of pages
9
Pages from-to
191-199
Publisher name
Association for Computational Linguistics
Place of publication
Online
Event location
Online
Event date
Jul 9, 2020
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—