@inproceedings{morales-etal-2008-stc,
title = "{STC}-{TIMIT}: Generation of a Single-channel Telephone Corpus",
author = "Morales, Nicol{\'a}s and
Tejedor, Javier and
Garrido, Javier and
Col{\'a}s, Jos{\'e} and
Toledano, Doroteo T.",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/102_paper.pdf",
abstract = "This paper describes a new speech corpus, STC-TIMIT, and discusses the process of design, development and its distribution through LDC. The STC-TIMIT corpus is derived from the widely used TIMIT corpus by sending it through a real and single telephone channel. TIMIT is phonetically balanced, covers the dialectal diversity in continental USA and has been extensively used as a benchmark for speech recognition algorithms, especially in early stages of development. The experimental usability of TIMIT has been increased eventually with the creation of derived corpora, passing the original data through different channels. One such example is the well-known NTIMIT corpus, where the original files in TIMIT are re-recorded after being sent through different telephone calls, resulting in a corpus that characterizes telephone channels in a wide sense. In STC-TIMIT, we followed a similar procedure, but the whole corpus was transmitted in a single telephone call with the goal of obtaining data from a real and yet highly stable telephone channel across the whole corpus. Files in STC-TIMIT are aligned to those of TIMIT with a theoretical precision of 0.125 ms, making TIMIT labels valid for the new corpus. The experimental section presents several results on speech recognition accuracy.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="morales-etal-2008-stc">
<titleInfo>
<title>STC-TIMIT: Generation of a Single-channel Telephone Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolás</namePart>
<namePart type="family">Morales</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Tejedor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Javier</namePart>
<namePart type="family">Garrido</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="family">Colás</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Doroteo</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Toledano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">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">Stelios</namePart>
<namePart type="family">Piperidis</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">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes a new speech corpus, STC-TIMIT, and discusses the process of design, development and its distribution through LDC. The STC-TIMIT corpus is derived from the widely used TIMIT corpus by sending it through a real and single telephone channel. TIMIT is phonetically balanced, covers the dialectal diversity in continental USA and has been extensively used as a benchmark for speech recognition algorithms, especially in early stages of development. The experimental usability of TIMIT has been increased eventually with the creation of derived corpora, passing the original data through different channels. One such example is the well-known NTIMIT corpus, where the original files in TIMIT are re-recorded after being sent through different telephone calls, resulting in a corpus that characterizes telephone channels in a wide sense. In STC-TIMIT, we followed a similar procedure, but the whole corpus was transmitted in a single telephone call with the goal of obtaining data from a real and yet highly stable telephone channel across the whole corpus. Files in STC-TIMIT are aligned to those of TIMIT with a theoretical precision of 0.125 ms, making TIMIT labels valid for the new corpus. The experimental section presents several results on speech recognition accuracy.</abstract>
<identifier type="citekey">morales-etal-2008-stc</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/102_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T STC-TIMIT: Generation of a Single-channel Telephone Corpus
%A Morales, Nicolás
%A Tejedor, Javier
%A Garrido, Javier
%A Colás, José
%A Toledano, Doroteo T.
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F morales-etal-2008-stc
%X This paper describes a new speech corpus, STC-TIMIT, and discusses the process of design, development and its distribution through LDC. The STC-TIMIT corpus is derived from the widely used TIMIT corpus by sending it through a real and single telephone channel. TIMIT is phonetically balanced, covers the dialectal diversity in continental USA and has been extensively used as a benchmark for speech recognition algorithms, especially in early stages of development. The experimental usability of TIMIT has been increased eventually with the creation of derived corpora, passing the original data through different channels. One such example is the well-known NTIMIT corpus, where the original files in TIMIT are re-recorded after being sent through different telephone calls, resulting in a corpus that characterizes telephone channels in a wide sense. In STC-TIMIT, we followed a similar procedure, but the whole corpus was transmitted in a single telephone call with the goal of obtaining data from a real and yet highly stable telephone channel across the whole corpus. Files in STC-TIMIT are aligned to those of TIMIT with a theoretical precision of 0.125 ms, making TIMIT labels valid for the new corpus. The experimental section presents several results on speech recognition accuracy.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/102_paper.pdf
Markdown (Informal)
[STC-TIMIT: Generation of a Single-channel Telephone Corpus](http://www.lrec-conf.org/proceedings/lrec2008/pdf/102_paper.pdf) (Morales et al., LREC 2008)
ACL
- Nicolás Morales, Javier Tejedor, Javier Garrido, José Colás, and Doroteo T. Toledano. 2008. STC-TIMIT: Generation of a Single-channel Telephone Corpus. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).