@inproceedings{petrick-etal-2025-appteks,
title = "{A}pp{T}ek{'}s Automatic Speech Translation: Generating Accurate and Well-Readable Subtitles",
author = "Petrick, Frithjof and
Wilken, Patrick and
Matusov, Evgeny and
Unai Rosell{\'o} Beneitez, Nahuel and
Beranek, Sarah",
editor = "Salesky, Elizabeth and
Federico, Marcello and
Anastasopoulos, Antonis",
booktitle = "Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.iwslt-1.21/",
doi = "10.18653/v1/2025.iwslt-1.21",
pages = "222--231",
ISBN = "979-8-89176-272-5",
abstract = "We describe AppTek{'}s submission to the subtitling track of the IWSLT 2025 evaluation. We enhance our cascaded speech translation approach by adapting the ASR and the MT models on in-domain data. All components, including intermediate steps such as subtitle source language template creation and line segmentation, are optimized to ensure that the resulting target language subtitles respect the subtitling constraints not only on the number of characters per line and the number of lines in each subtitle block, but also with respect to the desired reading speed. AppTek{'}s machine translation with length control plays the key role in this process, effectively condensing subtitles to these constraints. Our experiments show that this condensation results in high-quality translations that convey the most important information, as measured by metrics such as BLEU or BLEURT, as well as the primary metric subtitle edit rate (SubER)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petrick-etal-2025-appteks">
<titleInfo>
<title>AppTek’s Automatic Speech Translation: Generating Accurate and Well-Readable Subtitles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Frithjof</namePart>
<namePart type="family">Petrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Wilken</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Evgeny</namePart>
<namePart type="family">Matusov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nahuel</namePart>
<namePart type="family">Unai Roselló Beneitez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Beranek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonis</namePart>
<namePart type="family">Anastasopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-272-5</identifier>
</relatedItem>
<abstract>We describe AppTek’s submission to the subtitling track of the IWSLT 2025 evaluation. We enhance our cascaded speech translation approach by adapting the ASR and the MT models on in-domain data. All components, including intermediate steps such as subtitle source language template creation and line segmentation, are optimized to ensure that the resulting target language subtitles respect the subtitling constraints not only on the number of characters per line and the number of lines in each subtitle block, but also with respect to the desired reading speed. AppTek’s machine translation with length control plays the key role in this process, effectively condensing subtitles to these constraints. Our experiments show that this condensation results in high-quality translations that convey the most important information, as measured by metrics such as BLEU or BLEURT, as well as the primary metric subtitle edit rate (SubER).</abstract>
<identifier type="citekey">petrick-etal-2025-appteks</identifier>
<identifier type="doi">10.18653/v1/2025.iwslt-1.21</identifier>
<location>
<url>https://aclanthology.org/2025.iwslt-1.21/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>222</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AppTek’s Automatic Speech Translation: Generating Accurate and Well-Readable Subtitles
%A Petrick, Frithjof
%A Wilken, Patrick
%A Matusov, Evgeny
%A Unai Roselló Beneitez, Nahuel
%A Beranek, Sarah
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Anastasopoulos, Antonis
%S Proceedings of the 22nd International Conference on Spoken Language Translation (IWSLT 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria (in-person and online)
%@ 979-8-89176-272-5
%F petrick-etal-2025-appteks
%X We describe AppTek’s submission to the subtitling track of the IWSLT 2025 evaluation. We enhance our cascaded speech translation approach by adapting the ASR and the MT models on in-domain data. All components, including intermediate steps such as subtitle source language template creation and line segmentation, are optimized to ensure that the resulting target language subtitles respect the subtitling constraints not only on the number of characters per line and the number of lines in each subtitle block, but also with respect to the desired reading speed. AppTek’s machine translation with length control plays the key role in this process, effectively condensing subtitles to these constraints. Our experiments show that this condensation results in high-quality translations that convey the most important information, as measured by metrics such as BLEU or BLEURT, as well as the primary metric subtitle edit rate (SubER).
%R 10.18653/v1/2025.iwslt-1.21
%U https://aclanthology.org/2025.iwslt-1.21/
%U https://doi.org/10.18653/v1/2025.iwslt-1.21
%P 222-231
Markdown (Informal)
[AppTek’s Automatic Speech Translation: Generating Accurate and Well-Readable Subtitles](https://aclanthology.org/2025.iwslt-1.21/) (Petrick et al., IWSLT 2025)
ACL