@inproceedings{yamamoto-etal-2012-nict,
title = "The {NICT} {ASR} system for {IWSLT}2012",
author = "Yamamoto, Hitoshi and
Wu, Youzheng and
Huang, Chien-Lin and
Lu, Xugang and
Dixon, Paul R. and
Matsuda, Shigeki and
Hori, Chiori and
Kashioka, Hideki",
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.2",
pages = "34--37",
abstract = "This paper describes our automatic speech recognition (ASR) system for the IWSLT 2012 evaluation campaign. The target data of the campaign is selected from the TED talks, a collection of public speeches on a variety of topics spoken in English. Our ASR system is based on weighted finite-state transducers and exploits an combination of acoustic models for spontaneous speech, language models based on n-gram and factored recurrent neural network trained with effectively selected corpora, and unsupervised topic adaptation framework utilizing ASR results. Accordingly, the system achieved 10.6{\%} and 12.0{\%} word error rate for the tst2011 and tst2012 evaluation set, respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yamamoto-etal-2012-nict">
<titleInfo>
<title>The NICT ASR system for IWSLT2012</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Yamamoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Youzheng</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chien-Lin</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xugang</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Dixon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shigeki</namePart>
<namePart type="family">Matsuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chiori</namePart>
<namePart type="family">Hori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hideki</namePart>
<namePart type="family">Kashioka</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 automatic speech recognition (ASR) system for the IWSLT 2012 evaluation campaign. The target data of the campaign is selected from the TED talks, a collection of public speeches on a variety of topics spoken in English. Our ASR system is based on weighted finite-state transducers and exploits an combination of acoustic models for spontaneous speech, language models based on n-gram and factored recurrent neural network trained with effectively selected corpora, and unsupervised topic adaptation framework utilizing ASR results. Accordingly, the system achieved 10.6% and 12.0% word error rate for the tst2011 and tst2012 evaluation set, respectively.</abstract>
<identifier type="citekey">yamamoto-etal-2012-nict</identifier>
<location>
<url>https://aclanthology.org/2012.iwslt-evaluation.2</url>
</location>
<part>
<date>2012-dec 6-7</date>
<extent unit="page">
<start>34</start>
<end>37</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The NICT ASR system for IWSLT2012
%A Yamamoto, Hitoshi
%A Wu, Youzheng
%A Huang, Chien-Lin
%A Lu, Xugang
%A Dixon, Paul R.
%A Matsuda, Shigeki
%A Hori, Chiori
%A Kashioka, Hideki
%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 yamamoto-etal-2012-nict
%X This paper describes our automatic speech recognition (ASR) system for the IWSLT 2012 evaluation campaign. The target data of the campaign is selected from the TED talks, a collection of public speeches on a variety of topics spoken in English. Our ASR system is based on weighted finite-state transducers and exploits an combination of acoustic models for spontaneous speech, language models based on n-gram and factored recurrent neural network trained with effectively selected corpora, and unsupervised topic adaptation framework utilizing ASR results. Accordingly, the system achieved 10.6% and 12.0% word error rate for the tst2011 and tst2012 evaluation set, respectively.
%U https://aclanthology.org/2012.iwslt-evaluation.2
%P 34-37
Markdown (Informal)
[The NICT ASR system for IWSLT2012](https://aclanthology.org/2012.iwslt-evaluation.2) (Yamamoto et al., IWSLT 2012)
ACL
- Hitoshi Yamamoto, Youzheng Wu, Chien-Lin Huang, Xugang Lu, Paul R. Dixon, Shigeki Matsuda, Chiori Hori, and Hideki Kashioka. 2012. The NICT ASR system for IWSLT2012. In Proceedings of the 9th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 34–37, Hong Kong, Table of contents.