@inproceedings{strunk-etal-2014-untrained,
title = "Untrained Forced Alignment of Transcriptions and Audio for Language Documentation Corpora using {W}eb{MAUS}",
author = "Strunk, Jan and
Schiel, Florian and
Seifart, Frank",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/1176_Paper.pdf",
pages = "3940--3947",
abstract = "Language documentation projects supported by recent funding intiatives have created a large number of multimedia corpora of typologically diverse languages. Most of these corpora provide a manual alignment of transcription and audio data at the level of larger units, such as sentences or intonation units. Their usefulness both for corpus-linguistic and psycholinguistic research and for the development of tools and teaching materials could, however, be increased by achieving a more fine-grained alignment of transcription and audio at the word or even phoneme level. Since most language documentation corpora contain data on small languages, there usually do not exist any speech recognizers or acoustic models specifically trained on these languages. We therefore investigate the feasibility of untrained forced alignment for such corpora. We report on an evaluation of the tool (Web)MAUS (Kisler, 2012) on several language documentation corpora and discuss practical issues in the application of forced alignment. Our evaluation shows that (Web)MAUS with its existing acoustic models combined with simple grapheme-to-phoneme conversion can be successfully used for word-level forced alignment of a diverse set of languages without additional training, especially if a manual prealignment of larger annotation units is already avaible.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="strunk-etal-2014-untrained">
<titleInfo>
<title>Untrained Forced Alignment of Transcriptions and Audio for Language Documentation Corpora using WebMAUS</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Strunk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Schiel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Seifart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language documentation projects supported by recent funding intiatives have created a large number of multimedia corpora of typologically diverse languages. Most of these corpora provide a manual alignment of transcription and audio data at the level of larger units, such as sentences or intonation units. Their usefulness both for corpus-linguistic and psycholinguistic research and for the development of tools and teaching materials could, however, be increased by achieving a more fine-grained alignment of transcription and audio at the word or even phoneme level. Since most language documentation corpora contain data on small languages, there usually do not exist any speech recognizers or acoustic models specifically trained on these languages. We therefore investigate the feasibility of untrained forced alignment for such corpora. We report on an evaluation of the tool (Web)MAUS (Kisler, 2012) on several language documentation corpora and discuss practical issues in the application of forced alignment. Our evaluation shows that (Web)MAUS with its existing acoustic models combined with simple grapheme-to-phoneme conversion can be successfully used for word-level forced alignment of a diverse set of languages without additional training, especially if a manual prealignment of larger annotation units is already avaible.</abstract>
<identifier type="citekey">strunk-etal-2014-untrained</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/1176_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>3940</start>
<end>3947</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Untrained Forced Alignment of Transcriptions and Audio for Language Documentation Corpora using WebMAUS
%A Strunk, Jan
%A Schiel, Florian
%A Seifart, Frank
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F strunk-etal-2014-untrained
%X Language documentation projects supported by recent funding intiatives have created a large number of multimedia corpora of typologically diverse languages. Most of these corpora provide a manual alignment of transcription and audio data at the level of larger units, such as sentences or intonation units. Their usefulness both for corpus-linguistic and psycholinguistic research and for the development of tools and teaching materials could, however, be increased by achieving a more fine-grained alignment of transcription and audio at the word or even phoneme level. Since most language documentation corpora contain data on small languages, there usually do not exist any speech recognizers or acoustic models specifically trained on these languages. We therefore investigate the feasibility of untrained forced alignment for such corpora. We report on an evaluation of the tool (Web)MAUS (Kisler, 2012) on several language documentation corpora and discuss practical issues in the application of forced alignment. Our evaluation shows that (Web)MAUS with its existing acoustic models combined with simple grapheme-to-phoneme conversion can be successfully used for word-level forced alignment of a diverse set of languages without additional training, especially if a manual prealignment of larger annotation units is already avaible.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/1176_Paper.pdf
%P 3940-3947
Markdown (Informal)
[Untrained Forced Alignment of Transcriptions and Audio for Language Documentation Corpora using WebMAUS](http://www.lrec-conf.org/proceedings/lrec2014/pdf/1176_Paper.pdf) (Strunk et al., LREC 2014)
ACL