@inproceedings{abe-etal-2011-nict,
title = "The {NICT} {ASR} system for {IWSLT}2011",
author = "Abe, Kazuhiko and
Wu, Youzheng and
Huang, Chien-lin and
Dixon, Paul R. and
Matsuda, Shigeki and
Hori, Chiori and
Kashioka, Hideki",
editor = {Federico, Marcello and
Hwang, Mei-Yuh and
R{\"o}dder, Margit and
St{\"u}ker, Sebastian},
booktitle = "Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign",
month = dec # " 8-9",
year = "2011",
address = "San Francisco, California",
url = "https://aclanthology.org/2011.iwslt-evaluation.2",
pages = "28--33",
abstract = "In this paper, we describe NICT{'}s participation in the IWSLT 2011 evaluation campaign for the ASR Track. To recognize spontaneous speech, we prepared an acoustic model trained by more spontaneous speech corpora and a language model constructed with text corpora distributed by the organizer. We built the multi-pass ASR system by adapting the acoustic and language models with previous ASR results. The target speech was selected from talks on the TED (Technology, Entertainment, Design) program. Here, a large reduction in word error rate was obtained by the speaker adaptation of the acoustic model with MLLR. Additional improvement was achieved not only by adaptation of the language model but also by parallel usage of the baseline and speaker-dependent acoustic models. Accordingly, the final WER was reduced by 30{\%} from the baseline ASR for the distributed test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abe-etal-2011-nict">
<titleInfo>
<title>The NICT ASR system for IWSLT2011</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kazuhiko</namePart>
<namePart type="family">Abe</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">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>2011-dec 8-9</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei-Yuh</namePart>
<namePart type="family">Hwang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Margit</namePart>
<namePart type="family">Rödder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stüker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">San Francisco, California</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we describe NICT’s participation in the IWSLT 2011 evaluation campaign for the ASR Track. To recognize spontaneous speech, we prepared an acoustic model trained by more spontaneous speech corpora and a language model constructed with text corpora distributed by the organizer. We built the multi-pass ASR system by adapting the acoustic and language models with previous ASR results. The target speech was selected from talks on the TED (Technology, Entertainment, Design) program. Here, a large reduction in word error rate was obtained by the speaker adaptation of the acoustic model with MLLR. Additional improvement was achieved not only by adaptation of the language model but also by parallel usage of the baseline and speaker-dependent acoustic models. Accordingly, the final WER was reduced by 30% from the baseline ASR for the distributed test set.</abstract>
<identifier type="citekey">abe-etal-2011-nict</identifier>
<location>
<url>https://aclanthology.org/2011.iwslt-evaluation.2</url>
</location>
<part>
<date>2011-dec 8-9</date>
<extent unit="page">
<start>28</start>
<end>33</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The NICT ASR system for IWSLT2011
%A Abe, Kazuhiko
%A Wu, Youzheng
%A Huang, Chien-lin
%A Dixon, Paul R.
%A Matsuda, Shigeki
%A Hori, Chiori
%A Kashioka, Hideki
%Y Federico, Marcello
%Y Hwang, Mei-Yuh
%Y Rödder, Margit
%Y Stüker, Sebastian
%S Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign
%D 2011
%8 dec 8 9
%C San Francisco, California
%F abe-etal-2011-nict
%X In this paper, we describe NICT’s participation in the IWSLT 2011 evaluation campaign for the ASR Track. To recognize spontaneous speech, we prepared an acoustic model trained by more spontaneous speech corpora and a language model constructed with text corpora distributed by the organizer. We built the multi-pass ASR system by adapting the acoustic and language models with previous ASR results. The target speech was selected from talks on the TED (Technology, Entertainment, Design) program. Here, a large reduction in word error rate was obtained by the speaker adaptation of the acoustic model with MLLR. Additional improvement was achieved not only by adaptation of the language model but also by parallel usage of the baseline and speaker-dependent acoustic models. Accordingly, the final WER was reduced by 30% from the baseline ASR for the distributed test set.
%U https://aclanthology.org/2011.iwslt-evaluation.2
%P 28-33
Markdown (Informal)
[The NICT ASR system for IWSLT2011](https://aclanthology.org/2011.iwslt-evaluation.2) (Abe et al., IWSLT 2011)
ACL
- Kazuhiko Abe, Youzheng Wu, Chien-lin Huang, Paul R. Dixon, Shigeki Matsuda, Chiori Hori, and Hideki Kashioka. 2011. The NICT ASR system for IWSLT2011. In Proceedings of the 8th International Workshop on Spoken Language Translation: Evaluation Campaign, pages 28–33, San Francisco, California.