@inproceedings{seara-etal-2016-enhanced,
title = "Enhanced {CORILGA}: Introducing the Automatic Phonetic Alignment Tool for Continuous Speech",
author = "Seara, Roberto and
Martinez, Marta and
Varela, Roc{\'\i}o and
Mateo, Carmen Garc{\'\i}a and
Rei, Elisa Fernandez and
Regueira, Xos{\'e} Luis",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1616",
pages = "3893--3898",
abstract = "The {``}Corpus Oral Informatizado da Lingua Galega (CORILGA){''} project aims at building a corpus of oral language for Galician, primarily designed to study the linguistic variation and change. This project is currently under development and it is periodically enriched with new contributions. The long-term goal is that all the speech recordings will be enriched with phonetic, syllabic, morphosyntactic, lexical and sentence ELAN-complaint annotations. A way to speed up the process of annotation is to use automatic speech-recognition-based tools tailored to the application. Therefore, CORILGA repository has been enhanced with an automatic alignment tool, available to the administrator of the repository, that aligns speech with an orthographic transcription. In the event that no transcription, or just a partial one, were available, a speech recognizer for Galician is used to generate word and phonetic segmentations. These recognized outputs may contain errors that will have to be manually corrected by the administrator. For assisting this task, the tool also provides an ELAN tier with the confidence measure of each recognized word. In this paper, after the description of the main facts of the CORILGA corpus, the speech alignment and recognition tools are described. Both have been developed using the Kaldi toolkit.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="seara-etal-2016-enhanced">
<titleInfo>
<title>Enhanced CORILGA: Introducing the Automatic Phonetic Alignment Tool for Continuous Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Seara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="family">Martinez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rocío</namePart>
<namePart type="family">Varela</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carmen</namePart>
<namePart type="given">García</namePart>
<namePart type="family">Mateo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elisa</namePart>
<namePart type="given">Fernandez</namePart>
<namePart type="family">Rei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xosé</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Regueira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</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">Khalid</namePart>
<namePart type="family">Choukri</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">Marko</namePart>
<namePart type="family">Grobelnik</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">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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 (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The “Corpus Oral Informatizado da Lingua Galega (CORILGA)” project aims at building a corpus of oral language for Galician, primarily designed to study the linguistic variation and change. This project is currently under development and it is periodically enriched with new contributions. The long-term goal is that all the speech recordings will be enriched with phonetic, syllabic, morphosyntactic, lexical and sentence ELAN-complaint annotations. A way to speed up the process of annotation is to use automatic speech-recognition-based tools tailored to the application. Therefore, CORILGA repository has been enhanced with an automatic alignment tool, available to the administrator of the repository, that aligns speech with an orthographic transcription. In the event that no transcription, or just a partial one, were available, a speech recognizer for Galician is used to generate word and phonetic segmentations. These recognized outputs may contain errors that will have to be manually corrected by the administrator. For assisting this task, the tool also provides an ELAN tier with the confidence measure of each recognized word. In this paper, after the description of the main facts of the CORILGA corpus, the speech alignment and recognition tools are described. Both have been developed using the Kaldi toolkit.</abstract>
<identifier type="citekey">seara-etal-2016-enhanced</identifier>
<location>
<url>https://aclanthology.org/L16-1616</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>3893</start>
<end>3898</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enhanced CORILGA: Introducing the Automatic Phonetic Alignment Tool for Continuous Speech
%A Seara, Roberto
%A Martinez, Marta
%A Varela, Rocío
%A Mateo, Carmen García
%A Rei, Elisa Fernandez
%A Regueira, Xosé Luis
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F seara-etal-2016-enhanced
%X The “Corpus Oral Informatizado da Lingua Galega (CORILGA)” project aims at building a corpus of oral language for Galician, primarily designed to study the linguistic variation and change. This project is currently under development and it is periodically enriched with new contributions. The long-term goal is that all the speech recordings will be enriched with phonetic, syllabic, morphosyntactic, lexical and sentence ELAN-complaint annotations. A way to speed up the process of annotation is to use automatic speech-recognition-based tools tailored to the application. Therefore, CORILGA repository has been enhanced with an automatic alignment tool, available to the administrator of the repository, that aligns speech with an orthographic transcription. In the event that no transcription, or just a partial one, were available, a speech recognizer for Galician is used to generate word and phonetic segmentations. These recognized outputs may contain errors that will have to be manually corrected by the administrator. For assisting this task, the tool also provides an ELAN tier with the confidence measure of each recognized word. In this paper, after the description of the main facts of the CORILGA corpus, the speech alignment and recognition tools are described. Both have been developed using the Kaldi toolkit.
%U https://aclanthology.org/L16-1616
%P 3893-3898
Markdown (Informal)
[Enhanced CORILGA: Introducing the Automatic Phonetic Alignment Tool for Continuous Speech](https://aclanthology.org/L16-1616) (Seara et al., LREC 2016)
ACL