@inproceedings{pinnis-etal-2014-designing,
title = "Designing the {L}atvian Speech Recognition Corpus",
author = "Pinnis, M{\=a}rcis and
Auzi{\c{n}}a, Ilze and
Goba, K{\=a}rlis",
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/284_Paper.pdf",
pages = "1547--1553",
abstract = "In this paper the authors present the first Latvian speech corpus designed specifically for speech recognition purposes. The paper outlines the decisions made in the corpus designing process through analysis of related work on speech corpora creation for different languages. The authors provide also guidelines that were used for the creation of the Latvian speech recognition corpus. The corpus creation guidelines are fairly general for them to be re-used by other researchers when working on different language speech recognition corpora. The corpus consists of two parts ― an orthographically annotated corpus containing 100 hours of orthographically transcribed audio data and a phonetically annotated corpus containing 4 hours of phonetically transcribed audio data. Metadata files in XML format provide additional details about the speakers, noise levels, speech styles, etc. The speech recognition corpus is phonetically balanced and phonetically rich and the paper describes also the methodology how the phonetical balancedness has been assessed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pinnis-etal-2014-designing">
<titleInfo>
<title>Designing the Latvian Speech Recognition Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mārcis</namePart>
<namePart type="family">Pinnis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilze</namePart>
<namePart type="family">Auziņa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kārlis</namePart>
<namePart type="family">Goba</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>In this paper the authors present the first Latvian speech corpus designed specifically for speech recognition purposes. The paper outlines the decisions made in the corpus designing process through analysis of related work on speech corpora creation for different languages. The authors provide also guidelines that were used for the creation of the Latvian speech recognition corpus. The corpus creation guidelines are fairly general for them to be re-used by other researchers when working on different language speech recognition corpora. The corpus consists of two parts ― an orthographically annotated corpus containing 100 hours of orthographically transcribed audio data and a phonetically annotated corpus containing 4 hours of phonetically transcribed audio data. Metadata files in XML format provide additional details about the speakers, noise levels, speech styles, etc. The speech recognition corpus is phonetically balanced and phonetically rich and the paper describes also the methodology how the phonetical balancedness has been assessed.</abstract>
<identifier type="citekey">pinnis-etal-2014-designing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2014/pdf/284_Paper.pdf</url>
</location>
<part>
<date>2014-05</date>
<extent unit="page">
<start>1547</start>
<end>1553</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Designing the Latvian Speech Recognition Corpus
%A Pinnis, Mārcis
%A Auziņa, Ilze
%A Goba, Kārlis
%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 pinnis-etal-2014-designing
%X In this paper the authors present the first Latvian speech corpus designed specifically for speech recognition purposes. The paper outlines the decisions made in the corpus designing process through analysis of related work on speech corpora creation for different languages. The authors provide also guidelines that were used for the creation of the Latvian speech recognition corpus. The corpus creation guidelines are fairly general for them to be re-used by other researchers when working on different language speech recognition corpora. The corpus consists of two parts ― an orthographically annotated corpus containing 100 hours of orthographically transcribed audio data and a phonetically annotated corpus containing 4 hours of phonetically transcribed audio data. Metadata files in XML format provide additional details about the speakers, noise levels, speech styles, etc. The speech recognition corpus is phonetically balanced and phonetically rich and the paper describes also the methodology how the phonetical balancedness has been assessed.
%U http://www.lrec-conf.org/proceedings/lrec2014/pdf/284_Paper.pdf
%P 1547-1553
Markdown (Informal)
[Designing the Latvian Speech Recognition Corpus](http://www.lrec-conf.org/proceedings/lrec2014/pdf/284_Paper.pdf) (Pinnis et al., LREC 2014)
ACL
- Mārcis Pinnis, Ilze Auziņa, and Kārlis Goba. 2014. Designing the Latvian Speech Recognition Corpus. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 1547–1553, Reykjavik, Iceland. European Language Resources Association (ELRA).