@inproceedings{bahar-etal-2021-without,
title = "Without Further Ado: Direct and Simultaneous Speech Translation by {A}pp{T}ek in 2021",
author = "Bahar, Parnia and
Wilken, Patrick and
Di Gangi, Mattia A. and
Matusov, Evgeny",
editor = "Federico, Marcello and
Waibel, Alex and
Costa-juss{\`a}, Marta R. and
Niehues, Jan and
Stuker, Sebastian and
Salesky, Elizabeth",
booktitle = "Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)",
month = aug,
year = "2021",
address = "Bangkok, Thailand (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.iwslt-1.5",
doi = "10.18653/v1/2021.iwslt-1.5",
pages = "52--63",
abstract = "This paper describes the offline and simultaneous speech translation systems developed at AppTek for IWSLT 2021. Our offline ST submission includes the direct end-to-end system and the so-called posterior tight integrated model, which is akin to the cascade system but is trained in an end-to-end fashion, where all the cascaded modules are end-to-end models themselves. For simultaneous ST, we combine hybrid automatic speech recognition with a machine translation approach whose translation policy decisions are learned from statistical word alignments. Compared to last year, we improve general quality and provide a wider range of quality/latency trade-offs, both due to a data augmentation method making the MT model robust to varying chunk sizes. Finally, we present a method for ASR output segmentation into sentences that introduces a minimal additional delay.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bahar-etal-2021-without">
<titleInfo>
<title>Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021</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">Mattia</namePart>
<namePart type="given">A</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>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)</title>
</titleInfo>
<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">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stuker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the offline and simultaneous speech translation systems developed at AppTek for IWSLT 2021. Our offline ST submission includes the direct end-to-end system and the so-called posterior tight integrated model, which is akin to the cascade system but is trained in an end-to-end fashion, where all the cascaded modules are end-to-end models themselves. For simultaneous ST, we combine hybrid automatic speech recognition with a machine translation approach whose translation policy decisions are learned from statistical word alignments. Compared to last year, we improve general quality and provide a wider range of quality/latency trade-offs, both due to a data augmentation method making the MT model robust to varying chunk sizes. Finally, we present a method for ASR output segmentation into sentences that introduces a minimal additional delay.</abstract>
<identifier type="citekey">bahar-etal-2021-without</identifier>
<identifier type="doi">10.18653/v1/2021.iwslt-1.5</identifier>
<location>
<url>https://aclanthology.org/2021.iwslt-1.5</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>52</start>
<end>63</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021
%A Bahar, Parnia
%A Wilken, Patrick
%A Di Gangi, Mattia A.
%A Matusov, Evgeny
%Y Federico, Marcello
%Y Waibel, Alex
%Y Costa-jussà, Marta R.
%Y Niehues, Jan
%Y Stuker, Sebastian
%Y Salesky, Elizabeth
%S Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (online)
%F bahar-etal-2021-without
%X This paper describes the offline and simultaneous speech translation systems developed at AppTek for IWSLT 2021. Our offline ST submission includes the direct end-to-end system and the so-called posterior tight integrated model, which is akin to the cascade system but is trained in an end-to-end fashion, where all the cascaded modules are end-to-end models themselves. For simultaneous ST, we combine hybrid automatic speech recognition with a machine translation approach whose translation policy decisions are learned from statistical word alignments. Compared to last year, we improve general quality and provide a wider range of quality/latency trade-offs, both due to a data augmentation method making the MT model robust to varying chunk sizes. Finally, we present a method for ASR output segmentation into sentences that introduces a minimal additional delay.
%R 10.18653/v1/2021.iwslt-1.5
%U https://aclanthology.org/2021.iwslt-1.5
%U https://doi.org/10.18653/v1/2021.iwslt-1.5
%P 52-63
Markdown (Informal)
[Without Further Ado: Direct and Simultaneous Speech Translation by AppTek in 2021](https://aclanthology.org/2021.iwslt-1.5) (Bahar et al., IWSLT 2021)
ACL