Conference paper Open Access
Potapczyk, Tomasz; Przybysz, Pawel; Chochowski, Marcin; Szumaczuk, Artur
<?xml version='1.0' encoding='utf-8'?> <resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd"> <identifier identifierType="DOI">10.5281/zenodo.3525498</identifier> <creators> <creator> <creatorName>Potapczyk, Tomasz</creatorName> <givenName>Tomasz</givenName> <familyName>Potapczyk</familyName> <affiliation>Samsung R&D Institute, Poland</affiliation> </creator> <creator> <creatorName>Przybysz, Pawel</creatorName> <givenName>Pawel</givenName> <familyName>Przybysz</familyName> <affiliation>Samsung R&D Institute, Poland</affiliation> </creator> <creator> <creatorName>Chochowski, Marcin</creatorName> <givenName>Marcin</givenName> <familyName>Chochowski</familyName> <affiliation>Samsung R&D Institute, Poland</affiliation> </creator> <creator> <creatorName>Szumaczuk, Artur</creatorName> <givenName>Artur</givenName> <familyName>Szumaczuk</familyName> <affiliation>Samsung R&D Institute, Poland</affiliation> </creator> </creators> <titles> <title>Samsung's System for the IWSLT 2019 End-to-End Speech Translation Task</title> </titles> <publisher>Zenodo</publisher> <publicationYear>2019</publicationYear> <dates> <date dateType="Issued">2019-11-02</date> </dates> <language>en</language> <resourceType resourceTypeGeneral="Text">Conference paper</resourceType> <alternateIdentifiers> <alternateIdentifier alternateIdentifierType="url">https://zenodo.org/record/3525498</alternateIdentifier> </alternateIdentifiers> <relatedIdentifiers> <relatedIdentifier relatedIdentifierType="DOI" relationType="IsVersionOf">10.5281/zenodo.3525497</relatedIdentifier> <relatedIdentifier relatedIdentifierType="URL" relationType="IsPartOf">https://zenodo.org/communities/iwslt2019</relatedIdentifier> </relatedIdentifiers> <rightsList> <rights rightsURI="https://creativecommons.org/licenses/by/4.0/legalcode">Creative Commons Attribution 4.0 International</rights> <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights> </rightsList> <descriptions> <description descriptionType="Abstract"><p>This paper describes the submission to IWSLT 2019 End- to-End speech translation task by Samsung R&amp;D Institute, Poland. We decided to focus on end-to-end English to German TED lectures translation and did not provide any submission for other speech tasks. We used a slightly altered Transformer&nbsp;architecture with standard convolutional layer preparing the audio input to Transformer en- coder. Additionally, we propose an audio segmentation al- gorithm maximizing BLEU score on tst2015 test set.</p></description> </descriptions> </resource>
All versions | This version | |
---|---|---|
Views | 404 | 404 |
Downloads | 309 | 309 |
Data volume | 32.4 MB | 32.4 MB |
Unique views | 357 | 357 |
Unique downloads | 282 | 282 |