@inproceedings{vanhainen-salvi-2014-free,
title = "Free Acoustic and Language Models for Large Vocabulary Continuous Speech Recognition in {S}wedish",
author = "Vanhainen, Niklas and
Salvi, Giampiero",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Loftsson, Hrafn and
Maegaard, Bente and
Mariani, Joseph and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Ninth International Conference on Language Resources and Evaluation ({LREC}'14)",
month = may,
year = "2014",
address = "Reykjavik, Iceland",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2014/pdf/312_Paper.pdf",
pages = "388--392",
abstract = "This paper presents results for large vocabulary continuous speech recognition (LVCSR) in Swedish. We trained acoustic models on the public domain NST Swedish corpus and made them freely available to the community. The training procedure corresponds to the reference recogniser (RefRec) developed for the SpeechDat databases during the COST249 action. We describe the modifications we made to the procedure in order to train on the NST database, and the language models we created based on the N-gram data available at the Norwegian Language Council. Our tests include medium vocabulary isolated word recognition and LVCSR. Because no previous results are available for LVCSR in Swedish, we use as baseline the performance of the SpeechDat models on the same tasks. We also compare our best results to the ones obtained in similar conditions on resource rich languages such as American English. We tested the acoustic models with HTK and Julius and plan to make them available in CMU Sphinx format as well in the near future. We believe that the free availability of these resources will boost research in speech and language technology in Swedish, even in research groups that do not have resources to develop ASR systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vanhainen-salvi-2014-free">
<titleInfo>
<title>Free Acoustic and Language Models for Large Vocabulary Continuous Speech Recognition in Swedish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niklas</namePart>
<namePart type="family">Vanhainen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giampiero</namePart>
<namePart type="family">Salvi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2014-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)</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">Hrafn</namePart>
<namePart type="family">Loftsson</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">Reykjavik, Iceland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents results for large vocabulary continuous speech recognition (LVCSR) in Swedish. We trained acoustic models on the public domain NST Swedish corpus and made them freely available to the community. The training procedure corresponds to the reference recogniser (RefRec) developed for the SpeechDat databases during the COST249 action. We describe the modifications we made to the procedure in order to train on the NST database, and the language models we created based on the N-gram data available at the Norwegian Language Council. Our tests include medium vocabulary isolated word recognition and LVCSR. Because no previous results are available for LVCSR in Swedish, we use as baseline the performance of the SpeechDat models on the same tasks. We also compare our best results to the ones obtained in similar conditions on resource rich languages such as American English. We tested the acoustic models with HTK and Julius and plan to make them available in CMU Sphinx format as well in the near future. We believe that the free availability of these resources will boost research in speech and language technology in Swedish, even in research groups that do not have resources to develop ASR systems.</abstract>
<identifier type="citekey">vanhainen-salvi-2014-free</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/312_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>388</start>
<end>392</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Free Acoustic and Language Models for Large Vocabulary Continuous Speech Recognition in Swedish
%A Vanhainen, Niklas
%A Salvi, Giampiero
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Loftsson, Hrafn
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC’14)
%D 2014
%8 May
%I European Language Resources Association (ELRA)
%C Reykjavik, Iceland
%F vanhainen-salvi-2014-free
%X This paper presents results for large vocabulary continuous speech recognition (LVCSR) in Swedish. We trained acoustic models on the public domain NST Swedish corpus and made them freely available to the community. The training procedure corresponds to the reference recogniser (RefRec) developed for the SpeechDat databases during the COST249 action. We describe the modifications we made to the procedure in order to train on the NST database, and the language models we created based on the N-gram data available at the Norwegian Language Council. Our tests include medium vocabulary isolated word recognition and LVCSR. Because no previous results are available for LVCSR in Swedish, we use as baseline the performance of the SpeechDat models on the same tasks. We also compare our best results to the ones obtained in similar conditions on resource rich languages such as American English. We tested the acoustic models with HTK and Julius and plan to make them available in CMU Sphinx format as well in the near future. We believe that the free availability of these resources will boost research in speech and language technology in Swedish, even in research groups that do not have resources to develop ASR systems.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/312_Paper.pdf
%P 388-392
Markdown (Informal)
[Free Acoustic and Language Models for Large Vocabulary Continuous Speech Recognition in Swedish](http://www.lrec-conf.org/proceedings/lrec2014/pdf/312_Paper.pdf) (Vanhainen & Salvi, LREC 2014)
ACL