@inproceedings{bazillon-etal-2008-manual,
title = "Manual vs Assisted Transcription of Prepared and Spontaneous Speech",
author = "Bazillon, Thierry and
Est{\`e}ve, Yannick and
Luzzati, Daniel",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/277_paper.pdf",
abstract = "Our paper focuses on the gain which can be achieved on human transcription of spontaneous and prepared speech, by using the assistance of an ASR system. This experiment has shown interesting results, first about the duration of the transcription task itself: even with the combination of prepared speech + ASR, an experimented annotator needs approximately 4 hours to transcribe 1 hours of audio data. Then, using an ASR system is mostly time-saving, although this gain is much more significant on prepared speech: assisted transcriptions are up to 4 times faster than manual ones. This ratio falls to 2 with spontaneous speech, because of ASR limits for these data. Detailed results reveal interesting correlations between the transcription task and phenomena such as Word Error Rate, telephonic or non-native speech turns, the number of fillers or propers nouns. The latter make spelling correction very time-consuming with prepared speech because of their frequency. As a consequence, watching for low averages of proper nouns may be a way to detect spontaneous speech.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bazillon-etal-2008-manual">
<titleInfo>
<title>Manual vs Assisted Transcription of Prepared and Spontaneous Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Bazillon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yannick</namePart>
<namePart type="family">Estève</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Luzzati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Our paper focuses on the gain which can be achieved on human transcription of spontaneous and prepared speech, by using the assistance of an ASR system. This experiment has shown interesting results, first about the duration of the transcription task itself: even with the combination of prepared speech + ASR, an experimented annotator needs approximately 4 hours to transcribe 1 hours of audio data. Then, using an ASR system is mostly time-saving, although this gain is much more significant on prepared speech: assisted transcriptions are up to 4 times faster than manual ones. This ratio falls to 2 with spontaneous speech, because of ASR limits for these data. Detailed results reveal interesting correlations between the transcription task and phenomena such as Word Error Rate, telephonic or non-native speech turns, the number of fillers or propers nouns. The latter make spelling correction very time-consuming with prepared speech because of their frequency. As a consequence, watching for low averages of proper nouns may be a way to detect spontaneous speech.</abstract>
<identifier type="citekey">bazillon-etal-2008-manual</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/277_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Manual vs Assisted Transcription of Prepared and Spontaneous Speech
%A Bazillon, Thierry
%A Estève, Yannick
%A Luzzati, Daniel
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F bazillon-etal-2008-manual
%X Our paper focuses on the gain which can be achieved on human transcription of spontaneous and prepared speech, by using the assistance of an ASR system. This experiment has shown interesting results, first about the duration of the transcription task itself: even with the combination of prepared speech + ASR, an experimented annotator needs approximately 4 hours to transcribe 1 hours of audio data. Then, using an ASR system is mostly time-saving, although this gain is much more significant on prepared speech: assisted transcriptions are up to 4 times faster than manual ones. This ratio falls to 2 with spontaneous speech, because of ASR limits for these data. Detailed results reveal interesting correlations between the transcription task and phenomena such as Word Error Rate, telephonic or non-native speech turns, the number of fillers or propers nouns. The latter make spelling correction very time-consuming with prepared speech because of their frequency. As a consequence, watching for low averages of proper nouns may be a way to detect spontaneous speech.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/277_paper.pdf
Markdown (Informal)
[Manual vs Assisted Transcription of Prepared and Spontaneous Speech](http://www.lrec-conf.org/proceedings/lrec2008/pdf/277_paper.pdf) (Bazillon et al., LREC 2008)
ACL