@inproceedings{ohta-etal-2012-developing,
title = "Developing Partially-Transcribed Speech Corpus from Edited Transcriptions",
author = "Ohta, Kengo and
Tsuchiya, Masatoshi and
Nakagawa, Seiichi",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Do{\u{g}}an, Mehmet U{\u{g}}ur and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}'12)",
month = may,
year = "2012",
address = "Istanbul, Turkey",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2012/pdf/987_Paper.pdf",
pages = "3399--3404",
abstract = "Large-scale spontaneous speech corpora are crucial resource for various domains of spoken language processing. However, the available corpora are usually limited because their construction cost is quite expensive especially in transcribing speech precisely. On the other hand, loosely transcribed corpora like shorthand notes, meeting records and closed captions are more widely available than precisely transcribed ones, because their imperfectness reduces their construction cost. Because these corpora contain both precisely transcribed regions and edited regions, it is difficult to use them directly as speech corpora for learning acoustic models. Under this background, we have been considering to build an efficient semi-automatic framework to convert loose transcriptions to precise ones. This paper describes an improved automatic detection method of precise regions from loosely transcribed corpora for the above framework. Our detection method consists of two steps: the first step is a force alignment between loose transcriptions and their utterances to discover the corresponding utterance for the certain loose transcription, and the second step is a detector of precise regions with a support vector machine using several features obtained from the first step. Our experimental result shows that our method achieves a high accuracy of detecting precise regions, and shows that the precise regions extracted by our method are effective as training labels of lightly supervised speaker adaptation.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ohta-etal-2012-developing">
<titleInfo>
<title>Developing Partially-Transcribed Speech Corpus from Edited Transcriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kengo</namePart>
<namePart type="family">Ohta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Masatoshi</namePart>
<namePart type="family">Tsuchiya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seiichi</namePart>
<namePart type="family">Nakagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)</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">Mehmet</namePart>
<namePart type="given">Uğur</namePart>
<namePart type="family">Doğan</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">Istanbul, Turkey</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Large-scale spontaneous speech corpora are crucial resource for various domains of spoken language processing. However, the available corpora are usually limited because their construction cost is quite expensive especially in transcribing speech precisely. On the other hand, loosely transcribed corpora like shorthand notes, meeting records and closed captions are more widely available than precisely transcribed ones, because their imperfectness reduces their construction cost. Because these corpora contain both precisely transcribed regions and edited regions, it is difficult to use them directly as speech corpora for learning acoustic models. Under this background, we have been considering to build an efficient semi-automatic framework to convert loose transcriptions to precise ones. This paper describes an improved automatic detection method of precise regions from loosely transcribed corpora for the above framework. Our detection method consists of two steps: the first step is a force alignment between loose transcriptions and their utterances to discover the corresponding utterance for the certain loose transcription, and the second step is a detector of precise regions with a support vector machine using several features obtained from the first step. Our experimental result shows that our method achieves a high accuracy of detecting precise regions, and shows that the precise regions extracted by our method are effective as training labels of lightly supervised speaker adaptation.</abstract>
<identifier type="citekey">ohta-etal-2012-developing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/987_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3399</start>
<end>3404</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing Partially-Transcribed Speech Corpus from Edited Transcriptions
%A Ohta, Kengo
%A Tsuchiya, Masatoshi
%A Nakagawa, Seiichi
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Doğan, Mehmet Uğur
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12)
%D 2012
%8 May
%I European Language Resources Association (ELRA)
%C Istanbul, Turkey
%F ohta-etal-2012-developing
%X Large-scale spontaneous speech corpora are crucial resource for various domains of spoken language processing. However, the available corpora are usually limited because their construction cost is quite expensive especially in transcribing speech precisely. On the other hand, loosely transcribed corpora like shorthand notes, meeting records and closed captions are more widely available than precisely transcribed ones, because their imperfectness reduces their construction cost. Because these corpora contain both precisely transcribed regions and edited regions, it is difficult to use them directly as speech corpora for learning acoustic models. Under this background, we have been considering to build an efficient semi-automatic framework to convert loose transcriptions to precise ones. This paper describes an improved automatic detection method of precise regions from loosely transcribed corpora for the above framework. Our detection method consists of two steps: the first step is a force alignment between loose transcriptions and their utterances to discover the corresponding utterance for the certain loose transcription, and the second step is a detector of precise regions with a support vector machine using several features obtained from the first step. Our experimental result shows that our method achieves a high accuracy of detecting precise regions, and shows that the precise regions extracted by our method are effective as training labels of lightly supervised speaker adaptation.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/987_Paper.pdf
%P 3399-3404
Markdown (Informal)
[Developing Partially-Transcribed Speech Corpus from Edited Transcriptions](http://www.lrec-conf.org/proceedings/lrec2012/pdf/987_Paper.pdf) (Ohta et al., LREC 2012)
ACL