@inproceedings{pham-etal-2013-speech,
title = "The speech recognition and machine translation system of {IOIT} for {IWSLT} 2013",
author = "Pham, Ngoc-Quan and
Le, Hai-Son and
Vu, Tat-Thang and
Luong, Chi-Mai",
editor = "Zhang, Joy Ying",
booktitle = "Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign",
month = dec # " 5-6",
year = "2013",
address = "Heidelberg, Germany",
url = "https://aclanthology.org/2013.iwslt-evaluation.18",
abstract = "This paper describes the Automatic Speech Recognition (ASR) and Machine Translation (MT) systems developed by IOIT for the evaluation campaign of IWSLT2013. For the ASR task, using Kaldi toolkit, we developed the system based on weighted finite state transducer. The system is constructed by applying several techniques, notably, subspace Gaussian mixture models, speaker adaptation, discriminative training, system combination and SOUL, a neural network language model. The techniques used for automatic segmentation are also clarified. Besides, we compared different types of SOUL models in order to study the impact of words of previous sentences in predicting words in language modeling. For the MT task, the baseline system was built based on the open source toolkit N-code, then being augmented by using SOUL on top, i.e., in N-best rescoring phase.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pham-etal-2013-speech">
<titleInfo>
<title>The speech recognition and machine translation system of IOIT for IWSLT 2013</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ngoc-Quan</namePart>
<namePart type="family">Pham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hai-Son</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tat-Thang</namePart>
<namePart type="family">Vu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chi-Mai</namePart>
<namePart type="family">Luong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2013-dec 5-6</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joy</namePart>
<namePart type="given">Ying</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<place>
<placeTerm type="text">Heidelberg, Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the Automatic Speech Recognition (ASR) and Machine Translation (MT) systems developed by IOIT for the evaluation campaign of IWSLT2013. For the ASR task, using Kaldi toolkit, we developed the system based on weighted finite state transducer. The system is constructed by applying several techniques, notably, subspace Gaussian mixture models, speaker adaptation, discriminative training, system combination and SOUL, a neural network language model. The techniques used for automatic segmentation are also clarified. Besides, we compared different types of SOUL models in order to study the impact of words of previous sentences in predicting words in language modeling. For the MT task, the baseline system was built based on the open source toolkit N-code, then being augmented by using SOUL on top, i.e., in N-best rescoring phase.</abstract>
<identifier type="citekey">pham-etal-2013-speech</identifier>
<location>
<url>https://aclanthology.org/2013.iwslt-evaluation.18</url>
</location>
<part>
<date>2013-dec 5-6</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T The speech recognition and machine translation system of IOIT for IWSLT 2013
%A Pham, Ngoc-Quan
%A Le, Hai-Son
%A Vu, Tat-Thang
%A Luong, Chi-Mai
%Y Zhang, Joy Ying
%S Proceedings of the 10th International Workshop on Spoken Language Translation: Evaluation Campaign
%D 2013
%8 dec 5 6
%C Heidelberg, Germany
%F pham-etal-2013-speech
%X This paper describes the Automatic Speech Recognition (ASR) and Machine Translation (MT) systems developed by IOIT for the evaluation campaign of IWSLT2013. For the ASR task, using Kaldi toolkit, we developed the system based on weighted finite state transducer. The system is constructed by applying several techniques, notably, subspace Gaussian mixture models, speaker adaptation, discriminative training, system combination and SOUL, a neural network language model. The techniques used for automatic segmentation are also clarified. Besides, we compared different types of SOUL models in order to study the impact of words of previous sentences in predicting words in language modeling. For the MT task, the baseline system was built based on the open source toolkit N-code, then being augmented by using SOUL on top, i.e., in N-best rescoring phase.
%U https://aclanthology.org/2013.iwslt-evaluation.18
Markdown (Informal)
[The speech recognition and machine translation system of IOIT for IWSLT 2013](https://aclanthology.org/2013.iwslt-evaluation.18) (Pham et al., IWSLT 2013)
ACL