@inproceedings{korybski-etal-2022-semi,
title = "A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking",
author = "Korybski, Tomasz and
Davitti, Elena and
Orasan, Constantin and
Braun, Sabine",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.468/",
pages = "4405--4413",
abstract = {In this paper, we present a semi-automated workflow for live interlingual speech-to-text communication which seeks to reduce the shortcomings of existing ASR systems: a human respeaker works with a speaker-dependent speech recognition software (e.g., Dragon Naturally Speaking) to deliver punctuated same-language output of superior quality than obtained using out-of-the-box automatic speech recognition of the original speech. This is fed into a machine translation engine (the EU`s eTranslation) to produce live-caption ready text. We benchmark the quality of the output against the output of best-in-class (human) simultaneous interpreters working with the same source speeches from plenary sessions of the European Parliament. To evaluate the accuracy and facilitate the comparison between the two types of output, we use a tailored annotation approach based on the NTR model (Romero-Fresco and P{\"o}chhacker, 2017). We find that the semi-automated workflow combining intralingual respeaking and machine translation is capable of generating outputs that are similar in terms of accuracy and completeness to the outputs produced in the benchmarking workflow, although the small scale of our experiment requires caution in interpreting this result.}
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="korybski-etal-2022-semi">
<titleInfo>
<title>A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tomasz</namePart>
<namePart type="family">Korybski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Davitti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Constantin</namePart>
<namePart type="family">Orasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabine</namePart>
<namePart type="family">Braun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a semi-automated workflow for live interlingual speech-to-text communication which seeks to reduce the shortcomings of existing ASR systems: a human respeaker works with a speaker-dependent speech recognition software (e.g., Dragon Naturally Speaking) to deliver punctuated same-language output of superior quality than obtained using out-of-the-box automatic speech recognition of the original speech. This is fed into a machine translation engine (the EU‘s eTranslation) to produce live-caption ready text. We benchmark the quality of the output against the output of best-in-class (human) simultaneous interpreters working with the same source speeches from plenary sessions of the European Parliament. To evaluate the accuracy and facilitate the comparison between the two types of output, we use a tailored annotation approach based on the NTR model (Romero-Fresco and Pöchhacker, 2017). We find that the semi-automated workflow combining intralingual respeaking and machine translation is capable of generating outputs that are similar in terms of accuracy and completeness to the outputs produced in the benchmarking workflow, although the small scale of our experiment requires caution in interpreting this result.</abstract>
<identifier type="citekey">korybski-etal-2022-semi</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.468/</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4405</start>
<end>4413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking
%A Korybski, Tomasz
%A Davitti, Elena
%A Orasan, Constantin
%A Braun, Sabine
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F korybski-etal-2022-semi
%X In this paper, we present a semi-automated workflow for live interlingual speech-to-text communication which seeks to reduce the shortcomings of existing ASR systems: a human respeaker works with a speaker-dependent speech recognition software (e.g., Dragon Naturally Speaking) to deliver punctuated same-language output of superior quality than obtained using out-of-the-box automatic speech recognition of the original speech. This is fed into a machine translation engine (the EU‘s eTranslation) to produce live-caption ready text. We benchmark the quality of the output against the output of best-in-class (human) simultaneous interpreters working with the same source speeches from plenary sessions of the European Parliament. To evaluate the accuracy and facilitate the comparison between the two types of output, we use a tailored annotation approach based on the NTR model (Romero-Fresco and Pöchhacker, 2017). We find that the semi-automated workflow combining intralingual respeaking and machine translation is capable of generating outputs that are similar in terms of accuracy and completeness to the outputs produced in the benchmarking workflow, although the small scale of our experiment requires caution in interpreting this result.
%U https://aclanthology.org/2022.lrec-1.468/
%P 4405-4413
Markdown (Informal)
[A Semi-Automated Live Interlingual Communication Workflow Featuring Intralingual Respeaking: Evaluation and Benchmarking](https://aclanthology.org/2022.lrec-1.468/) (Korybski et al., LREC 2022)
ACL