@inproceedings{saam-etal-2012-2012,
title = "The 2012 {KIT} and {KIT}-{NAIST} {E}nglish {ASR} systems for the {IWSLT} evaluation",
author = {Saam, Christian and
Mohr, Christian and
Kilgour, Kevin and
Heck, Michael and
Sperber, Matthias and
Kubo, Keigo and
St{\"u}ker, Sebatian and
Sakri, Sakriani and
Neubig, Graham and
Toda, Tomoki and
Nakamura, Satoshi and
Waibel, Alex},
booktitle = "Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign",
month = dec # " 6-7",
year = "2012",
address = "Hong Kong, Table of contents",
url = "https://aclanthology.org/2012.iwslt-evaluation.10",
pages = "87--90",
abstract = "This paper describes our English Speech-to-Text (STT) systems for the 2012 IWSLT TED ASR track evaluation. The systems consist of 10 subsystems that are combinations of different front-ends, e.g. MVDR based and MFCC based ones, and two different phone sets. The outputs of the subsystems are combined via confusion network combination. Decoding is done in two stages, where the systems of the second stage are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cM-LLR.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="saam-etal-2012-2012">
<titleInfo>
<title>The 2012 KIT and KIT-NAIST English ASR systems for the IWSLT evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Saam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christian</namePart>
<namePart type="family">Mohr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Kilgour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Heck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthias</namePart>
<namePart type="family">Sperber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keigo</namePart>
<namePart type="family">Kubo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebatian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Neubig</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Toda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Satoshi</namePart>
<namePart type="family">Nakamura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2012-dec 6-7</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign</title>
</titleInfo>
<originInfo>
<place>
<placeTerm type="text">Hong Kong, Table of contents</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes our English Speech-to-Text (STT) systems for the 2012 IWSLT TED ASR track evaluation. The systems consist of 10 subsystems that are combinations of different front-ends, e.g. MVDR based and MFCC based ones, and two different phone sets. The outputs of the subsystems are combined via confusion network combination. Decoding is done in two stages, where the systems of the second stage are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cM-LLR.</abstract>
<identifier type="citekey">saam-etal-2012-2012</identifier>
<location>
<url>https://aclanthology.org/2012.iwslt-evaluation.10</url>
</location>
<part>
<date>2012-dec 6-7</date>
<extent unit="page">
<start>87</start>
<end>90</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The 2012 KIT and KIT-NAIST English ASR systems for the IWSLT evaluation
%A Saam, Christian
%A Mohr, Christian
%A Kilgour, Kevin
%A Heck, Michael
%A Sperber, Matthias
%A Kubo, Keigo
%A Stüker, Sebatian
%A Sakri, Sakriani
%A Neubig, Graham
%A Toda, Tomoki
%A Nakamura, Satoshi
%A Waibel, Alex
%S Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign
%D 2012
%8 dec 6 7
%C Hong Kong, Table of contents
%F saam-etal-2012-2012
%X This paper describes our English Speech-to-Text (STT) systems for the 2012 IWSLT TED ASR track evaluation. The systems consist of 10 subsystems that are combinations of different front-ends, e.g. MVDR based and MFCC based ones, and two different phone sets. The outputs of the subsystems are combined via confusion network combination. Decoding is done in two stages, where the systems of the second stage are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cM-LLR.
%U https://aclanthology.org/2012.iwslt-evaluation.10
%P 87-90
Markdown (Informal)
[The 2012 KIT and KIT-NAIST English ASR systems for the IWSLT evaluation](https://aclanthology.org/2012.iwslt-evaluation.10) (Saam et al., IWSLT 2012)
ACL
- Christian Saam, Christian Mohr, Kevin Kilgour, Michael Heck, Matthias Sperber, Keigo Kubo, Sebatian Stüker, Sakriani Sakri, Graham Neubig, Tomoki Toda, Satoshi Nakamura, and Alex Waibel. 2012. The 2012 KIT and KIT-NAIST English ASR systems for the IWSLT evaluation. In Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 87–90, Hong Kong, Table of contents.