@inproceedings{karakanta-etal-2021-simultaneous,
title = "Simultaneous Speech Translation for Live Subtitling: from Delay to Display",
author = "Karakanta, Alina and
Papi, Sara and
Negri, Matteo and
Turchi, Marco",
editor = "Turchi, Marco and
Fantinuoli, Claudio",
booktitle = "Proceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW)",
month = aug,
year = "2021",
address = "Virtual",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2021.mtsummit-asltrw.4/",
pages = "35--48",
abstract = "With the increased audiovisualisation of communication, the need for live subtitles in multilingual events is more relevant than ever. In an attempt to automatise the process, we aim at exploring the feasibility of simultaneous speech translation (SimulST) for live subtitling. However, the word-for-word rate of generation of SimulST systems is not optimal for displaying the subtitles in a comprehensible and readable way. In this work, we adapt SimulST systems to predict subtitle breaks along with the translation. We then propose a display mode that exploits the predicted break structure by presenting the subtitles in scrolling lines. We compare our proposed mode with a display 1) word-for-word and 2) in blocks, in terms of reading speed and delay. Experiments on three language pairs (en{\textrightarrow}it, de, fr) show that scrolling lines is the only mode achieving an acceptable reading speed while keeping delay close to a 4-second threshold. We argue that simultaneous translation for readable live subtitles still faces challenges, the main one being poor translation quality, and propose directions for steering future research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karakanta-etal-2021-simultaneous">
<titleInfo>
<title>Simultaneous Speech Translation for Live Subtitling: from Delay to Display</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="family">Karakanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Papi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matteo</namePart>
<namePart type="family">Negri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Turchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudio</namePart>
<namePart type="family">Fantinuoli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Machine Translation in the Americas</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the increased audiovisualisation of communication, the need for live subtitles in multilingual events is more relevant than ever. In an attempt to automatise the process, we aim at exploring the feasibility of simultaneous speech translation (SimulST) for live subtitling. However, the word-for-word rate of generation of SimulST systems is not optimal for displaying the subtitles in a comprehensible and readable way. In this work, we adapt SimulST systems to predict subtitle breaks along with the translation. We then propose a display mode that exploits the predicted break structure by presenting the subtitles in scrolling lines. We compare our proposed mode with a display 1) word-for-word and 2) in blocks, in terms of reading speed and delay. Experiments on three language pairs (en→it, de, fr) show that scrolling lines is the only mode achieving an acceptable reading speed while keeping delay close to a 4-second threshold. We argue that simultaneous translation for readable live subtitles still faces challenges, the main one being poor translation quality, and propose directions for steering future research.</abstract>
<identifier type="citekey">karakanta-etal-2021-simultaneous</identifier>
<location>
<url>https://aclanthology.org/2021.mtsummit-asltrw.4/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>35</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simultaneous Speech Translation for Live Subtitling: from Delay to Display
%A Karakanta, Alina
%A Papi, Sara
%A Negri, Matteo
%A Turchi, Marco
%Y Turchi, Marco
%Y Fantinuoli, Claudio
%S Proceedings of the 1st Workshop on Automatic Spoken Language Translation in Real-World Settings (ASLTRW)
%D 2021
%8 August
%I Association for Machine Translation in the Americas
%C Virtual
%F karakanta-etal-2021-simultaneous
%X With the increased audiovisualisation of communication, the need for live subtitles in multilingual events is more relevant than ever. In an attempt to automatise the process, we aim at exploring the feasibility of simultaneous speech translation (SimulST) for live subtitling. However, the word-for-word rate of generation of SimulST systems is not optimal for displaying the subtitles in a comprehensible and readable way. In this work, we adapt SimulST systems to predict subtitle breaks along with the translation. We then propose a display mode that exploits the predicted break structure by presenting the subtitles in scrolling lines. We compare our proposed mode with a display 1) word-for-word and 2) in blocks, in terms of reading speed and delay. Experiments on three language pairs (en→it, de, fr) show that scrolling lines is the only mode achieving an acceptable reading speed while keeping delay close to a 4-second threshold. We argue that simultaneous translation for readable live subtitles still faces challenges, the main one being poor translation quality, and propose directions for steering future research.
%U https://aclanthology.org/2021.mtsummit-asltrw.4/
%P 35-48
Markdown (Informal)
[Simultaneous Speech Translation for Live Subtitling: from Delay to Display](https://aclanthology.org/2021.mtsummit-asltrw.4/) (Karakanta et al., MTSummit 2021)
ACL