@inproceedings{wang-etal-2022-multimodal-simultaneous,
title = "A Multimodal Simultaneous Interpretation Prototype: Who Said What",
author = "Wang, Xiaolin and
Utiyama, Masao and
Sumita, Eiichiro",
editor = "Campbell, Janice and
Larocca, Stephen and
Marciano, Jay and
Savenkov, Konstantin and
Yanishevsky, Alex",
booktitle = "Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)",
month = sep,
year = "2022",
address = "Orlando, USA",
publisher = "Association for Machine Translation in the Americas",
url = "https://aclanthology.org/2022.amta-upg.10",
pages = "132--143",
abstract = "{``}Who said what{''} is essential for users to understand video streams that have more than one speaker, but conventional simultaneous interpretation systems merely present {``}what was said{''} in the form of subtitles. Because the translations unavoidably have delays and errors, users often find it difficult to trace the subtitles back to speakers. To address this problem, we propose a multimodal SI system that presents users {``}who said what{''}. Our system takes audio-visual approaches to recognize the speaker of each sentence, and then annotates its translation with the textual tag and face icon of the speaker, so that users can quickly understand the scenario. Furthermore, our system is capable of interpreting video streams in real-time on a single desktop equipped with two Quadro RTX 4000 GPUs owing to an efficient sentence-based architecture.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2022-multimodal-simultaneous">
<titleInfo>
<title>A Multimodal Simultaneous Interpretation Prototype: Who Said What</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaolin</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masao</namePart>
<namePart type="family">Utiyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eiichiro</namePart>
<namePart type="family">Sumita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Janice</namePart>
<namePart type="family">Campbell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephen</namePart>
<namePart type="family">Larocca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jay</namePart>
<namePart type="family">Marciano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Konstantin</namePart>
<namePart type="family">Savenkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Yanishevsky</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">Orlando, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Who said what” is essential for users to understand video streams that have more than one speaker, but conventional simultaneous interpretation systems merely present “what was said” in the form of subtitles. Because the translations unavoidably have delays and errors, users often find it difficult to trace the subtitles back to speakers. To address this problem, we propose a multimodal SI system that presents users “who said what”. Our system takes audio-visual approaches to recognize the speaker of each sentence, and then annotates its translation with the textual tag and face icon of the speaker, so that users can quickly understand the scenario. Furthermore, our system is capable of interpreting video streams in real-time on a single desktop equipped with two Quadro RTX 4000 GPUs owing to an efficient sentence-based architecture.</abstract>
<identifier type="citekey">wang-etal-2022-multimodal-simultaneous</identifier>
<location>
<url>https://aclanthology.org/2022.amta-upg.10</url>
</location>
<part>
<date>2022-09</date>
<extent unit="page">
<start>132</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multimodal Simultaneous Interpretation Prototype: Who Said What
%A Wang, Xiaolin
%A Utiyama, Masao
%A Sumita, Eiichiro
%Y Campbell, Janice
%Y Larocca, Stephen
%Y Marciano, Jay
%Y Savenkov, Konstantin
%Y Yanishevsky, Alex
%S Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track)
%D 2022
%8 September
%I Association for Machine Translation in the Americas
%C Orlando, USA
%F wang-etal-2022-multimodal-simultaneous
%X “Who said what” is essential for users to understand video streams that have more than one speaker, but conventional simultaneous interpretation systems merely present “what was said” in the form of subtitles. Because the translations unavoidably have delays and errors, users often find it difficult to trace the subtitles back to speakers. To address this problem, we propose a multimodal SI system that presents users “who said what”. Our system takes audio-visual approaches to recognize the speaker of each sentence, and then annotates its translation with the textual tag and face icon of the speaker, so that users can quickly understand the scenario. Furthermore, our system is capable of interpreting video streams in real-time on a single desktop equipped with two Quadro RTX 4000 GPUs owing to an efficient sentence-based architecture.
%U https://aclanthology.org/2022.amta-upg.10
%P 132-143
Markdown (Informal)
[A Multimodal Simultaneous Interpretation Prototype: Who Said What](https://aclanthology.org/2022.amta-upg.10) (Wang et al., AMTA 2022)
ACL
- Xiaolin Wang, Masao Utiyama, and Eiichiro Sumita. 2022. A Multimodal Simultaneous Interpretation Prototype: Who Said What. In Proceedings of the 15th Biennial Conference of the Association for Machine Translation in the Americas (Volume 2: Users and Providers Track and Government Track), pages 132–143, Orlando, USA. Association for Machine Translation in the Americas.