@inproceedings{bahar-etal-2023-speech,
title = "Speech Translation with Style: {A}pp{T}ek{'}s Submissions to the {IWSLT} Subtitling and Formality Tracks in 2023",
author = {Bahar, Parnia and
Wilken, Patrick and
Iranzo-S{\'a}nchez, Javier and
Di Gangi, Mattia and
Matusov, Evgeny and
T{\"u}ske, Zolt{\'a}n},
editor = "Salesky, Elizabeth and
Federico, Marcello and
Carpuat, Marine",
booktitle = "Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)",
month = jul,
year = "2023",
address = "Toronto, Canada (in-person and online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.iwslt-1.22",
doi = "10.18653/v1/2023.iwslt-1.22",
pages = "251--260",
abstract = "AppTek participated in the subtitling and formality tracks of the IWSLT 2023 evaluation. This paper describes the details of our subtitling pipeline - speech segmentation, speech recognition, punctuation prediction and inverse text normalization, text machine translation and direct speech-to-text translation, intelligent line segmentation - and how we make use of the provided subtitling-specific data in training and fine-tuning. The evaluation results show that our final submissions are competitive, in particular outperforming the submissions by other participants by 5{\%} absolute as measured by the SubER subtitle quality metric. For the formality track, we participate with our En-Ru and En-Pt production models, which support formality control via prefix tokens. Except for informal Portuguese, we achieve near perfect formality level accuracy while at the same time offering high general translation quality.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahar-etal-2023-speech">
<titleInfo>
<title>Speech Translation with Style: AppTek’s Submissions to the IWSLT Subtitling and Formality Tracks in 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parnia</namePart>
<namePart type="family">Bahar</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">Javier</namePart>
<namePart type="family">Iranzo-Sánchez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mattia</namePart>
<namePart type="family">Di Gangi</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">Zoltán</namePart>
<namePart type="family">Tüske</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)</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">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada (in-person and online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>AppTek participated in the subtitling and formality tracks of the IWSLT 2023 evaluation. This paper describes the details of our subtitling pipeline - speech segmentation, speech recognition, punctuation prediction and inverse text normalization, text machine translation and direct speech-to-text translation, intelligent line segmentation - and how we make use of the provided subtitling-specific data in training and fine-tuning. The evaluation results show that our final submissions are competitive, in particular outperforming the submissions by other participants by 5% absolute as measured by the SubER subtitle quality metric. For the formality track, we participate with our En-Ru and En-Pt production models, which support formality control via prefix tokens. Except for informal Portuguese, we achieve near perfect formality level accuracy while at the same time offering high general translation quality.</abstract>
<identifier type="citekey">bahar-etal-2023-speech</identifier>
<identifier type="doi">10.18653/v1/2023.iwslt-1.22</identifier>
<location>
<url>https://aclanthology.org/2023.iwslt-1.22</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>251</start>
<end>260</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech Translation with Style: AppTek’s Submissions to the IWSLT Subtitling and Formality Tracks in 2023
%A Bahar, Parnia
%A Wilken, Patrick
%A Iranzo-Sánchez, Javier
%A Di Gangi, Mattia
%A Matusov, Evgeny
%A Tüske, Zoltán
%Y Salesky, Elizabeth
%Y Federico, Marcello
%Y Carpuat, Marine
%S Proceedings of the 20th International Conference on Spoken Language Translation (IWSLT 2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada (in-person and online)
%F bahar-etal-2023-speech
%X AppTek participated in the subtitling and formality tracks of the IWSLT 2023 evaluation. This paper describes the details of our subtitling pipeline - speech segmentation, speech recognition, punctuation prediction and inverse text normalization, text machine translation and direct speech-to-text translation, intelligent line segmentation - and how we make use of the provided subtitling-specific data in training and fine-tuning. The evaluation results show that our final submissions are competitive, in particular outperforming the submissions by other participants by 5% absolute as measured by the SubER subtitle quality metric. For the formality track, we participate with our En-Ru and En-Pt production models, which support formality control via prefix tokens. Except for informal Portuguese, we achieve near perfect formality level accuracy while at the same time offering high general translation quality.
%R 10.18653/v1/2023.iwslt-1.22
%U https://aclanthology.org/2023.iwslt-1.22
%U https://doi.org/10.18653/v1/2023.iwslt-1.22
%P 251-260
Markdown (Informal)
[Speech Translation with Style: AppTek’s Submissions to the IWSLT Subtitling and Formality Tracks in 2023](https://aclanthology.org/2023.iwslt-1.22) (Bahar et al., IWSLT 2023)
ACL