@inproceedings{della-corte-stymne-2020-iestac,
title = "{IESTAC}: {E}nglish-{I}talian Parallel Corpus for End-to-End Speech-to-Text Machine Translation",
author = "Della Corte, Giuseppe and
Stymne, Sara",
editor = "Castellucci, Giuseppe and
Filice, Simone and
Poria, Soujanya and
Cambria, Erik and
Specia, Lucia",
booktitle = "Proceedings of the First International Workshop on Natural Language Processing Beyond Text",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlpbt-1.5/",
doi = "10.18653/v1/2020.nlpbt-1.5",
pages = "41--50",
abstract = "We discuss a set of methods for the creation of IESTAC: a English-Italian speech and text parallel corpus designed for the training of end-to-end speech-to-text machine translation models and publicly released as part of this work. We first mapped English LibriVox audiobooks and their corresponding English Gutenberg Project e-books to Italian e-books with a set of three complementary methods. Then we aligned the English and the Italian texts using both traditional Gale-Church based alignment methods and a recently proposed tool to perform bilingual sentences alignment computing the cosine similarity of multilingual sentence embeddings. Finally, we forced the alignment between the English audiobooks and the English side of our textual parallel corpus with a text-to-speech and dynamic time warping based forced alignment tool. For each step, we provide the reader with a critical discussion based on detailed evaluation and comparison of the results of the different methods."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="della-corte-stymne-2020-iestac">
<titleInfo>
<title>IESTAC: English-Italian Parallel Corpus for End-to-End Speech-to-Text Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Della Corte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Stymne</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First International Workshop on Natural Language Processing Beyond Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">Giuseppe</namePart>
<namePart type="family">Castellucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simone</namePart>
<namePart type="family">Filice</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soujanya</namePart>
<namePart type="family">Poria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Erik</namePart>
<namePart type="family">Cambria</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We discuss a set of methods for the creation of IESTAC: a English-Italian speech and text parallel corpus designed for the training of end-to-end speech-to-text machine translation models and publicly released as part of this work. We first mapped English LibriVox audiobooks and their corresponding English Gutenberg Project e-books to Italian e-books with a set of three complementary methods. Then we aligned the English and the Italian texts using both traditional Gale-Church based alignment methods and a recently proposed tool to perform bilingual sentences alignment computing the cosine similarity of multilingual sentence embeddings. Finally, we forced the alignment between the English audiobooks and the English side of our textual parallel corpus with a text-to-speech and dynamic time warping based forced alignment tool. For each step, we provide the reader with a critical discussion based on detailed evaluation and comparison of the results of the different methods.</abstract>
<identifier type="citekey">della-corte-stymne-2020-iestac</identifier>
<identifier type="doi">10.18653/v1/2020.nlpbt-1.5</identifier>
<location>
<url>https://aclanthology.org/2020.nlpbt-1.5/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>41</start>
<end>50</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IESTAC: English-Italian Parallel Corpus for End-to-End Speech-to-Text Machine Translation
%A Della Corte, Giuseppe
%A Stymne, Sara
%Y Castellucci, Giuseppe
%Y Filice, Simone
%Y Poria, Soujanya
%Y Cambria, Erik
%Y Specia, Lucia
%S Proceedings of the First International Workshop on Natural Language Processing Beyond Text
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F della-corte-stymne-2020-iestac
%X We discuss a set of methods for the creation of IESTAC: a English-Italian speech and text parallel corpus designed for the training of end-to-end speech-to-text machine translation models and publicly released as part of this work. We first mapped English LibriVox audiobooks and their corresponding English Gutenberg Project e-books to Italian e-books with a set of three complementary methods. Then we aligned the English and the Italian texts using both traditional Gale-Church based alignment methods and a recently proposed tool to perform bilingual sentences alignment computing the cosine similarity of multilingual sentence embeddings. Finally, we forced the alignment between the English audiobooks and the English side of our textual parallel corpus with a text-to-speech and dynamic time warping based forced alignment tool. For each step, we provide the reader with a critical discussion based on detailed evaluation and comparison of the results of the different methods.
%R 10.18653/v1/2020.nlpbt-1.5
%U https://aclanthology.org/2020.nlpbt-1.5/
%U https://doi.org/10.18653/v1/2020.nlpbt-1.5
%P 41-50
Markdown (Informal)
[IESTAC: English-Italian Parallel Corpus for End-to-End Speech-to-Text Machine Translation](https://aclanthology.org/2020.nlpbt-1.5/) (Della Corte & Stymne, nlpbt 2020)
ACL