@inproceedings{zablotskiy-etal-2012-speech,
title = "Speech and Language Resources for {LVCSR} of {R}ussian",
author = "Zablotskiy, Sergey and
Shvets, Alexander and
Sidorov, Maxim and
Semenkin, Eugene and
Minker, Wolfgang",
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/485_Paper.pdf",
pages = "3374--3377",
abstract = "A syllable-based language model reduces the lexicon size by hundreds of times. It is especially beneficial in case of highly inflective languages like Russian due to the abundance of word forms according to various grammatical categories. However, the main arising challenge is the concatenation of recognised syllables into the originally spoken sentence or phrase, particularly in the presence of syllable recognition mistakes. Natural fluent speech does not usually incorporate clear information about the outside borders of the spoken words. In this paper a method for the syllable concatenation and error correction is suggested and tested. It is based on the designed co-evolutionary asymptotic probabilistic genetic algorithm for the determination of the most likely sentence corresponding to the recognized chain of syllables within an acceptable time frame. The advantage of this genetic algorithm modification is the minimum number of settings to be manually adjusted comparing to the standard algorithm. Data used for acoustic and language modelling are also described here. A special issue is the preprocessing of the textual data, particularly, handling of abbreviations, Arabic and Roman numerals, since their inflection mostly depends on the context and grammar.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zablotskiy-etal-2012-speech">
<titleInfo>
<title>Speech and Language Resources for LVCSR of Russian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sergey</namePart>
<namePart type="family">Zablotskiy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Shvets</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eugene</namePart>
<namePart type="family">Semenkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Minker</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>A syllable-based language model reduces the lexicon size by hundreds of times. It is especially beneficial in case of highly inflective languages like Russian due to the abundance of word forms according to various grammatical categories. However, the main arising challenge is the concatenation of recognised syllables into the originally spoken sentence or phrase, particularly in the presence of syllable recognition mistakes. Natural fluent speech does not usually incorporate clear information about the outside borders of the spoken words. In this paper a method for the syllable concatenation and error correction is suggested and tested. It is based on the designed co-evolutionary asymptotic probabilistic genetic algorithm for the determination of the most likely sentence corresponding to the recognized chain of syllables within an acceptable time frame. The advantage of this genetic algorithm modification is the minimum number of settings to be manually adjusted comparing to the standard algorithm. Data used for acoustic and language modelling are also described here. A special issue is the preprocessing of the textual data, particularly, handling of abbreviations, Arabic and Roman numerals, since their inflection mostly depends on the context and grammar.</abstract>
<identifier type="citekey">zablotskiy-etal-2012-speech</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2012/pdf/485_Paper.pdf</url>
</location>
<part>
<date>2012-05</date>
<extent unit="page">
<start>3374</start>
<end>3377</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Speech and Language Resources for LVCSR of Russian
%A Zablotskiy, Sergey
%A Shvets, Alexander
%A Sidorov, Maxim
%A Semenkin, Eugene
%A Minker, Wolfgang
%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 zablotskiy-etal-2012-speech
%X A syllable-based language model reduces the lexicon size by hundreds of times. It is especially beneficial in case of highly inflective languages like Russian due to the abundance of word forms according to various grammatical categories. However, the main arising challenge is the concatenation of recognised syllables into the originally spoken sentence or phrase, particularly in the presence of syllable recognition mistakes. Natural fluent speech does not usually incorporate clear information about the outside borders of the spoken words. In this paper a method for the syllable concatenation and error correction is suggested and tested. It is based on the designed co-evolutionary asymptotic probabilistic genetic algorithm for the determination of the most likely sentence corresponding to the recognized chain of syllables within an acceptable time frame. The advantage of this genetic algorithm modification is the minimum number of settings to be manually adjusted comparing to the standard algorithm. Data used for acoustic and language modelling are also described here. A special issue is the preprocessing of the textual data, particularly, handling of abbreviations, Arabic and Roman numerals, since their inflection mostly depends on the context and grammar.
%U http://www.lrec-conf.org/proceedings/lrec2012/pdf/485_Paper.pdf
%P 3374-3377
Markdown (Informal)
[Speech and Language Resources for LVCSR of Russian](http://www.lrec-conf.org/proceedings/lrec2012/pdf/485_Paper.pdf) (Zablotskiy et al., LREC 2012)
ACL
- Sergey Zablotskiy, Alexander Shvets, Maxim Sidorov, Eugene Semenkin, and Wolfgang Minker. 2012. Speech and Language Resources for LVCSR of Russian. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC'12), pages 3374–3377, Istanbul, Turkey. European Language Resources Association (ELRA).