@inproceedings{fukuda-etal-2020-improving,
title = "Improving Speech Recognition for the Elderly: A New Corpus of Elderly {J}apanese Speech and Investigation of Acoustic Modeling for Speech Recognition",
author = "Fukuda, Meiko and
Nishizaki, Hiromitsu and
Iribe, Yurie and
Nishimura, Ryota and
Kitaoka, Norihide",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.810",
pages = "6578--6585",
abstract = "In an aging society like Japan, a highly accurate speech recognition system is needed for use in electronic devices for the elderly, but this level of accuracy cannot be obtained using conventional speech recognition systems due to the unique features of the speech of elderly people. S-JNAS, a corpus of elderly Japanese speech, is widely used for acoustic modeling in Japan, but the average age of its speakers is 67.6 years old. Since average life expectancy in Japan is now 84.2 years, we are constructing a new speech corpus, which currently consists of the utterances of 221 speakers with an average age of 79.2, collected from four regions of Japan. In addition, we expand on our previous study (Fukuda, 2019) by further investigating the construction of acoustic models suitable for elderly speech. We create new acoustic models and train them using a combination of existing Japanese speech corpora (JNAS, S-JNAS, CSJ), with and without our {`}super-elderly{'} speech data, and conduct speech recognition experiments. Our new acoustic models achieve word error rates (WER) as low as 13.38{\%}, exceeding the results of our previous study in which we used the CSJ acoustic model adapted for elderly speech (17.4{\%} WER).",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fukuda-etal-2020-improving">
<titleInfo>
<title>Improving Speech Recognition for the Elderly: A New Corpus of Elderly Japanese Speech and Investigation of Acoustic Modeling for Speech Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meiko</namePart>
<namePart type="family">Fukuda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiromitsu</namePart>
<namePart type="family">Nishizaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yurie</namePart>
<namePart type="family">Iribe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryota</namePart>
<namePart type="family">Nishimura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norihide</namePart>
<namePart type="family">Kitaoka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</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">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</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">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</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">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</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>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>In an aging society like Japan, a highly accurate speech recognition system is needed for use in electronic devices for the elderly, but this level of accuracy cannot be obtained using conventional speech recognition systems due to the unique features of the speech of elderly people. S-JNAS, a corpus of elderly Japanese speech, is widely used for acoustic modeling in Japan, but the average age of its speakers is 67.6 years old. Since average life expectancy in Japan is now 84.2 years, we are constructing a new speech corpus, which currently consists of the utterances of 221 speakers with an average age of 79.2, collected from four regions of Japan. In addition, we expand on our previous study (Fukuda, 2019) by further investigating the construction of acoustic models suitable for elderly speech. We create new acoustic models and train them using a combination of existing Japanese speech corpora (JNAS, S-JNAS, CSJ), with and without our ‘super-elderly’ speech data, and conduct speech recognition experiments. Our new acoustic models achieve word error rates (WER) as low as 13.38%, exceeding the results of our previous study in which we used the CSJ acoustic model adapted for elderly speech (17.4% WER).</abstract>
<identifier type="citekey">fukuda-etal-2020-improving</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.810</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6578</start>
<end>6585</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Speech Recognition for the Elderly: A New Corpus of Elderly Japanese Speech and Investigation of Acoustic Modeling for Speech Recognition
%A Fukuda, Meiko
%A Nishizaki, Hiromitsu
%A Iribe, Yurie
%A Nishimura, Ryota
%A Kitaoka, Norihide
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F fukuda-etal-2020-improving
%X In an aging society like Japan, a highly accurate speech recognition system is needed for use in electronic devices for the elderly, but this level of accuracy cannot be obtained using conventional speech recognition systems due to the unique features of the speech of elderly people. S-JNAS, a corpus of elderly Japanese speech, is widely used for acoustic modeling in Japan, but the average age of its speakers is 67.6 years old. Since average life expectancy in Japan is now 84.2 years, we are constructing a new speech corpus, which currently consists of the utterances of 221 speakers with an average age of 79.2, collected from four regions of Japan. In addition, we expand on our previous study (Fukuda, 2019) by further investigating the construction of acoustic models suitable for elderly speech. We create new acoustic models and train them using a combination of existing Japanese speech corpora (JNAS, S-JNAS, CSJ), with and without our ‘super-elderly’ speech data, and conduct speech recognition experiments. Our new acoustic models achieve word error rates (WER) as low as 13.38%, exceeding the results of our previous study in which we used the CSJ acoustic model adapted for elderly speech (17.4% WER).
%U https://aclanthology.org/2020.lrec-1.810
%P 6578-6585
Markdown (Informal)
[Improving Speech Recognition for the Elderly: A New Corpus of Elderly Japanese Speech and Investigation of Acoustic Modeling for Speech Recognition](https://aclanthology.org/2020.lrec-1.810) (Fukuda et al., LREC 2020)
ACL