@inproceedings{mauclair-etal-2006-automatic,
title = "Automatic Detection of Well Recognized Words in Automatic Speech Transcriptions",
author = "Mauclair, Julie and
Est{\`e}ve, Yannick and
Petit-Renaud, Simon and
Del{\'e}glise, Paul",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Gangemi, Aldo and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Tapias, Daniel",
booktitle = "Proceedings of the Fifth International Conference on Language Resources and Evaluation ({LREC}{'}06)",
month = may,
year = "2006",
address = "Genoa, Italy",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2006/pdf/630_pdf.pdf",
abstract = "This work adresses the use of confidence measures for extracting well recognized words with very low error rate from automatically transcribed segments in a unsupervised way. We present and compare several confidence measures and propose a method to merge them into a new one. We study its capabilities on extracting correct recognized word-segments compared to the amount of rejected words. We apply this fusion measure to select audio segments composed of words with a high confidence score. These segments come from an automatic transcription of french broadcast news given by our speech recognition system based on the CMU Sphinx3.3 decoder. Injecting new data resulting from unsupervised treatments of raw audio recordings in the training corpus of acoustic models gives statistically significant improvement (95{\%} confident interval) in terms of word error rate. Experiments have been carried out on the corpus used during ESTER, the french evaluation campaign.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mauclair-etal-2006-automatic">
<titleInfo>
<title>Automatic Detection of Well Recognized Words in Automatic Speech Transcriptions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Julie</namePart>
<namePart type="family">Mauclair</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">Simon</namePart>
<namePart type="family">Petit-Renaud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Deléglise</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2006-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)</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">Aldo</namePart>
<namePart type="family">Gangemi</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">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">Genoa, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This work adresses the use of confidence measures for extracting well recognized words with very low error rate from automatically transcribed segments in a unsupervised way. We present and compare several confidence measures and propose a method to merge them into a new one. We study its capabilities on extracting correct recognized word-segments compared to the amount of rejected words. We apply this fusion measure to select audio segments composed of words with a high confidence score. These segments come from an automatic transcription of french broadcast news given by our speech recognition system based on the CMU Sphinx3.3 decoder. Injecting new data resulting from unsupervised treatments of raw audio recordings in the training corpus of acoustic models gives statistically significant improvement (95% confident interval) in terms of word error rate. Experiments have been carried out on the corpus used during ESTER, the french evaluation campaign.</abstract>
<identifier type="citekey">mauclair-etal-2006-automatic</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/630_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Detection of Well Recognized Words in Automatic Speech Transcriptions
%A Mauclair, Julie
%A Estève, Yannick
%A Petit-Renaud, Simon
%A Deléglise, Paul
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Gangemi, Aldo
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Tapias, Daniel
%S Proceedings of the Fifth International Conference on Language Resources and Evaluation (LREC’06)
%D 2006
%8 May
%I European Language Resources Association (ELRA)
%C Genoa, Italy
%F mauclair-etal-2006-automatic
%X This work adresses the use of confidence measures for extracting well recognized words with very low error rate from automatically transcribed segments in a unsupervised way. We present and compare several confidence measures and propose a method to merge them into a new one. We study its capabilities on extracting correct recognized word-segments compared to the amount of rejected words. We apply this fusion measure to select audio segments composed of words with a high confidence score. These segments come from an automatic transcription of french broadcast news given by our speech recognition system based on the CMU Sphinx3.3 decoder. Injecting new data resulting from unsupervised treatments of raw audio recordings in the training corpus of acoustic models gives statistically significant improvement (95% confident interval) in terms of word error rate. Experiments have been carried out on the corpus used during ESTER, the french evaluation campaign.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/630_pdf.pdf
Markdown (Informal)
[Automatic Detection of Well Recognized Words in Automatic Speech Transcriptions](http://www.lrec-conf.org/proceedings/lrec2006/pdf/630_pdf.pdf) (Mauclair et al., LREC 2006)
ACL