@inproceedings{yamashita-etal-2020-dnn,
title = "{DNN}-based Speech Synthesis Using Abundant Tags of Spontaneous Speech Corpus",
author = "Yamashita, Yuki and
Koriyama, Tomoki and
Saito, Yuki and
Takamichi, Shinnosuke and
Ijima, Yusuke and
Masumura, Ryo and
Saruwatari, Hiroshi",
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-1.792",
pages = "6438--6443",
abstract = "In this paper, we investigate the effectiveness of using rich annotations in deep neural network (DNN)-based statistical speech synthesis. DNN-based frameworks typically use linguistic information as input features called context instead of directly using text. In such frameworks, we can synthesize not only reading-style speech but also speech with paralinguistic and nonlinguistic features by adding such information to the context. However, it is not clear what kind of information is crucial for reproducing paralinguistic and nonlinguistic features. Therefore, we investigate the effectiveness of rich tags in DNN-based speech synthesis according to the Corpus of Spontaneous Japanese (CSJ), which has a large amount of annotations on paralinguistic features such as prosody, disfluency, and morphological features. Experimental evaluation results shows that the reproducibility of paralinguistic features of synthetic speech was enhanced by adding such information as context.",
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="yamashita-etal-2020-dnn">
<titleInfo>
<title>DNN-based Speech Synthesis Using Abundant Tags of Spontaneous Speech Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Yamashita</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomoki</namePart>
<namePart type="family">Koriyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuki</namePart>
<namePart type="family">Saito</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinnosuke</namePart>
<namePart type="family">Takamichi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusuke</namePart>
<namePart type="family">Ijima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryo</namePart>
<namePart type="family">Masumura</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiroshi</namePart>
<namePart type="family">Saruwatari</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>
<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 this paper, we investigate the effectiveness of using rich annotations in deep neural network (DNN)-based statistical speech synthesis. DNN-based frameworks typically use linguistic information as input features called context instead of directly using text. In such frameworks, we can synthesize not only reading-style speech but also speech with paralinguistic and nonlinguistic features by adding such information to the context. However, it is not clear what kind of information is crucial for reproducing paralinguistic and nonlinguistic features. Therefore, we investigate the effectiveness of rich tags in DNN-based speech synthesis according to the Corpus of Spontaneous Japanese (CSJ), which has a large amount of annotations on paralinguistic features such as prosody, disfluency, and morphological features. Experimental evaluation results shows that the reproducibility of paralinguistic features of synthetic speech was enhanced by adding such information as context.</abstract>
<identifier type="citekey">yamashita-etal-2020-dnn</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.792</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>6438</start>
<end>6443</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DNN-based Speech Synthesis Using Abundant Tags of Spontaneous Speech Corpus
%A Yamashita, Yuki
%A Koriyama, Tomoki
%A Saito, Yuki
%A Takamichi, Shinnosuke
%A Ijima, Yusuke
%A Masumura, Ryo
%A Saruwatari, Hiroshi
%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 yamashita-etal-2020-dnn
%X In this paper, we investigate the effectiveness of using rich annotations in deep neural network (DNN)-based statistical speech synthesis. DNN-based frameworks typically use linguistic information as input features called context instead of directly using text. In such frameworks, we can synthesize not only reading-style speech but also speech with paralinguistic and nonlinguistic features by adding such information to the context. However, it is not clear what kind of information is crucial for reproducing paralinguistic and nonlinguistic features. Therefore, we investigate the effectiveness of rich tags in DNN-based speech synthesis according to the Corpus of Spontaneous Japanese (CSJ), which has a large amount of annotations on paralinguistic features such as prosody, disfluency, and morphological features. Experimental evaluation results shows that the reproducibility of paralinguistic features of synthetic speech was enhanced by adding such information as context.
%U https://aclanthology.org/2020.lrec-1.792
%P 6438-6443
Markdown (Informal)
[DNN-based Speech Synthesis Using Abundant Tags of Spontaneous Speech Corpus](https://aclanthology.org/2020.lrec-1.792) (Yamashita et al., LREC 2020)
ACL