@inproceedings{ircing-etal-2006-exploiting,
title = "Exploiting Linguistic Knowledge in Language Modeling of {C}zech Spontaneous Speech",
author = "Ircing, Pavel and
Hoidekr, Jan and
Psutka, Josef",
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/591_pdf.pdf",
abstract = "In our paper, we present a method for incorporating available linguistic information into a statistical language model that is used in ASR system for transcribing spontaneous speech. We employ the class-based language model paradigm and use the morphological tags as the basis for world-to-class mapping. Since the number of different tags is at least by one order of magnitude lower than the number of words even in the tasks with moderately-sized vocabularies, the tag-based model can be rather robustly estimated using even the relatively small text corpora. Unfortunately, this robustness goes hand in hand with restricted predictive ability of the class-based model. Hence we apply the two-pass recognition strategy, where the first pass is performed with the standard word-based n-gram and the resulting lattices are rescored in the second pass using the aforementioned class-based model. Using this decoding scenario, we have managed to moderately improve the word error rate in the performed ASR experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ircing-etal-2006-exploiting">
<titleInfo>
<title>Exploiting Linguistic Knowledge in Language Modeling of Czech Spontaneous Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pavel</namePart>
<namePart type="family">Ircing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Hoidekr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Josef</namePart>
<namePart type="family">Psutka</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>In our paper, we present a method for incorporating available linguistic information into a statistical language model that is used in ASR system for transcribing spontaneous speech. We employ the class-based language model paradigm and use the morphological tags as the basis for world-to-class mapping. Since the number of different tags is at least by one order of magnitude lower than the number of words even in the tasks with moderately-sized vocabularies, the tag-based model can be rather robustly estimated using even the relatively small text corpora. Unfortunately, this robustness goes hand in hand with restricted predictive ability of the class-based model. Hence we apply the two-pass recognition strategy, where the first pass is performed with the standard word-based n-gram and the resulting lattices are rescored in the second pass using the aforementioned class-based model. Using this decoding scenario, we have managed to moderately improve the word error rate in the performed ASR experiments.</abstract>
<identifier type="citekey">ircing-etal-2006-exploiting</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2006/pdf/591_pdf.pdf</url>
</location>
<part>
<date>2006-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploiting Linguistic Knowledge in Language Modeling of Czech Spontaneous Speech
%A Ircing, Pavel
%A Hoidekr, Jan
%A Psutka, Josef
%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 ircing-etal-2006-exploiting
%X In our paper, we present a method for incorporating available linguistic information into a statistical language model that is used in ASR system for transcribing spontaneous speech. We employ the class-based language model paradigm and use the morphological tags as the basis for world-to-class mapping. Since the number of different tags is at least by one order of magnitude lower than the number of words even in the tasks with moderately-sized vocabularies, the tag-based model can be rather robustly estimated using even the relatively small text corpora. Unfortunately, this robustness goes hand in hand with restricted predictive ability of the class-based model. Hence we apply the two-pass recognition strategy, where the first pass is performed with the standard word-based n-gram and the resulting lattices are rescored in the second pass using the aforementioned class-based model. Using this decoding scenario, we have managed to moderately improve the word error rate in the performed ASR experiments.
%U http://www.lrec-conf.org/proceedings/lrec2006/pdf/591_pdf.pdf
Markdown (Informal)
[Exploiting Linguistic Knowledge in Language Modeling of Czech Spontaneous Speech](http://www.lrec-conf.org/proceedings/lrec2006/pdf/591_pdf.pdf) (Ircing et al., LREC 2006)
ACL