@inproceedings{bauer-etal-2010-wtimit,
title = "{WTIMIT}: The {TIMIT} Speech Corpus Transmitted Over The 3{G} {AMR} Wideband Mobile Network",
author = "Bauer, Patrick and
Scheler, David and
Fingscheidt, Tim",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Rosner, Mike and
Tapias, Daniel",
booktitle = "Proceedings of the Seventh International Conference on Language Resources and Evaluation ({LREC}'10)",
month = may,
year = "2010",
address = "Valletta, Malta",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2010/pdf/285_Paper.pdf",
abstract = "In anticipation of upcoming mobile telephony services with higher speech quality, a wideband (50 Hz to 7 kHz) mobile telephony derivative of TIMIT has been recorded called WTIMIT. It opens up various scientific investigations; e.g., on speech quality and intelligibility, as well as on wideband upgrades of network-side interactive voice response (IVR) systems with retrained or bandwidth-extended acoustic models for automatic speech recognition (ASR). Wideband telephony could enable network-side speech recognition applications such as remote dictation or spelling without the need of distributed speech recognition techniques. The WTIMIT corpus was transmitted via two prepared Nokia 6220 mobile phones over T-Mobile's 3G wideband mobile network in The Hague, The Netherlands, employing the Adaptive Multirate Wideband (AMR-WB) speech codec. The paper presents observations of transmission effects and phoneme recognition experiments. It turns out that in the case of wideband telephony, server-side ASR should not be carried out by simply decimating received signals to 8 kHz and applying existent narrowband acoustic models. Nor do we recommend just simulating the AMR-WB codec for training of wideband acoustic models. Instead, real-world wideband telephony channel data (such as WTIMIT) provides the best training material for wideband IVR systems.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bauer-etal-2010-wtimit">
<titleInfo>
<title>WTIMIT: The TIMIT Speech Corpus Transmitted Over The 3G AMR Wideband Mobile Network</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Bauer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Scheler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Fingscheidt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2010-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)</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">Mike</namePart>
<namePart type="family">Rosner</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">Valletta, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In anticipation of upcoming mobile telephony services with higher speech quality, a wideband (50 Hz to 7 kHz) mobile telephony derivative of TIMIT has been recorded called WTIMIT. It opens up various scientific investigations; e.g., on speech quality and intelligibility, as well as on wideband upgrades of network-side interactive voice response (IVR) systems with retrained or bandwidth-extended acoustic models for automatic speech recognition (ASR). Wideband telephony could enable network-side speech recognition applications such as remote dictation or spelling without the need of distributed speech recognition techniques. The WTIMIT corpus was transmitted via two prepared Nokia 6220 mobile phones over T-Mobile’s 3G wideband mobile network in The Hague, The Netherlands, employing the Adaptive Multirate Wideband (AMR-WB) speech codec. The paper presents observations of transmission effects and phoneme recognition experiments. It turns out that in the case of wideband telephony, server-side ASR should not be carried out by simply decimating received signals to 8 kHz and applying existent narrowband acoustic models. Nor do we recommend just simulating the AMR-WB codec for training of wideband acoustic models. Instead, real-world wideband telephony channel data (such as WTIMIT) provides the best training material for wideband IVR systems.</abstract>
<identifier type="citekey">bauer-etal-2010-wtimit</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2010/pdf/285_Paper.pdf</url>
</location>
<part>
<date>2010-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WTIMIT: The TIMIT Speech Corpus Transmitted Over The 3G AMR Wideband Mobile Network
%A Bauer, Patrick
%A Scheler, David
%A Fingscheidt, Tim
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Rosner, Mike
%Y Tapias, Daniel
%S Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10)
%D 2010
%8 May
%I European Language Resources Association (ELRA)
%C Valletta, Malta
%F bauer-etal-2010-wtimit
%X In anticipation of upcoming mobile telephony services with higher speech quality, a wideband (50 Hz to 7 kHz) mobile telephony derivative of TIMIT has been recorded called WTIMIT. It opens up various scientific investigations; e.g., on speech quality and intelligibility, as well as on wideband upgrades of network-side interactive voice response (IVR) systems with retrained or bandwidth-extended acoustic models for automatic speech recognition (ASR). Wideband telephony could enable network-side speech recognition applications such as remote dictation or spelling without the need of distributed speech recognition techniques. The WTIMIT corpus was transmitted via two prepared Nokia 6220 mobile phones over T-Mobile’s 3G wideband mobile network in The Hague, The Netherlands, employing the Adaptive Multirate Wideband (AMR-WB) speech codec. The paper presents observations of transmission effects and phoneme recognition experiments. It turns out that in the case of wideband telephony, server-side ASR should not be carried out by simply decimating received signals to 8 kHz and applying existent narrowband acoustic models. Nor do we recommend just simulating the AMR-WB codec for training of wideband acoustic models. Instead, real-world wideband telephony channel data (such as WTIMIT) provides the best training material for wideband IVR systems.
%U http://www.lrec-conf.org/proceedings/lrec2010/pdf/285_Paper.pdf
Markdown (Informal)
[WTIMIT: The TIMIT Speech Corpus Transmitted Over The 3G AMR Wideband Mobile Network](http://www.lrec-conf.org/proceedings/lrec2010/pdf/285_Paper.pdf) (Bauer et al., LREC 2010)
ACL