@inproceedings{cavar-etal-2016-generating,
title = "Generating a {Y}iddish Speech Corpus, Forced Aligner and Basic {ASR} System for the {AHEYM} Project",
author = "{\'C}avar, Malgorzata and
{\'C}avar, Damir and
Kerler, Dov-Ber and
Quilitzsch, Anya",
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/L16-1744",
pages = "4688--4693",
abstract = "To create automatic transcription and annotation tools for the AHEYM corpus of recorded interviews with Yiddish speakers in Eastern Europe we develop initial Yiddish language resources that are used for adaptations of speech and language technologies. Our project aims at the development of resources and technologies that can make the entire AHEYM corpus and other Yiddish resources more accessible to not only the community of Yiddish speakers or linguists with language expertise, but also historians and experts from other disciplines or the general public. In this paper we describe the rationale behind our approach, the procedures and methods, and challenges that are not specific to the AHEYM corpus, but apply to all documentary language data that is collected in the field. To the best of our knowledge, this is the first attempt to create a speech corpus and speech technologies for Yiddish. This is also the first attempt to work out speech and language technologies to transcribe and translate a large collection of Yiddish spoken language resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cavar-etal-2016-generating">
<titleInfo>
<title>Generating a Yiddish Speech Corpus, Forced Aligner and Basic ASR System for the AHEYM Project</title>
</titleInfo>
<name type="personal">
<namePart type="given">Malgorzata</namePart>
<namePart type="family">Ćavar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damir</namePart>
<namePart type="family">Ćavar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dov-Ber</namePart>
<namePart type="family">Kerler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anya</namePart>
<namePart type="family">Quilitzsch</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>To create automatic transcription and annotation tools for the AHEYM corpus of recorded interviews with Yiddish speakers in Eastern Europe we develop initial Yiddish language resources that are used for adaptations of speech and language technologies. Our project aims at the development of resources and technologies that can make the entire AHEYM corpus and other Yiddish resources more accessible to not only the community of Yiddish speakers or linguists with language expertise, but also historians and experts from other disciplines or the general public. In this paper we describe the rationale behind our approach, the procedures and methods, and challenges that are not specific to the AHEYM corpus, but apply to all documentary language data that is collected in the field. To the best of our knowledge, this is the first attempt to create a speech corpus and speech technologies for Yiddish. This is also the first attempt to work out speech and language technologies to transcribe and translate a large collection of Yiddish spoken language resources.</abstract>
<identifier type="citekey">cavar-etal-2016-generating</identifier>
<location>
<url>https://aclanthology.org/L16-1744</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4688</start>
<end>4693</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generating a Yiddish Speech Corpus, Forced Aligner and Basic ASR System for the AHEYM Project
%A Ćavar, Malgorzata
%A Ćavar, Damir
%A Kerler, Dov-Ber
%A Quilitzsch, Anya
%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 cavar-etal-2016-generating
%X To create automatic transcription and annotation tools for the AHEYM corpus of recorded interviews with Yiddish speakers in Eastern Europe we develop initial Yiddish language resources that are used for adaptations of speech and language technologies. Our project aims at the development of resources and technologies that can make the entire AHEYM corpus and other Yiddish resources more accessible to not only the community of Yiddish speakers or linguists with language expertise, but also historians and experts from other disciplines or the general public. In this paper we describe the rationale behind our approach, the procedures and methods, and challenges that are not specific to the AHEYM corpus, but apply to all documentary language data that is collected in the field. To the best of our knowledge, this is the first attempt to create a speech corpus and speech technologies for Yiddish. This is also the first attempt to work out speech and language technologies to transcribe and translate a large collection of Yiddish spoken language resources.
%U https://aclanthology.org/L16-1744
%P 4688-4693
Markdown (Informal)
[Generating a Yiddish Speech Corpus, Forced Aligner and Basic ASR System for the AHEYM Project](https://aclanthology.org/L16-1744) (Ćavar et al., LREC 2016)
ACL