Speech Synthesis of Emotions in a Sentence using Vowel Features

Speech Synthesis of Emotions in a Sentence using Vowel Features

We previously proposed a method for adding emotions to synthetic speech using the vowel features of a speaker. For the initial investigation in this earlier study, we used utterances of Japanese names to demonstrate the method. In the present study, we use the proposed method to construct emotional...

Full description

Bibliographic Details
Main Authors: Rintaro Makino, Yasunari Yoshitomi, Taro Asada, Masayoshi Tabuse
Format: Article
Language:English
Published: Atlantis Press 2020-06-01
Series:Journal of Robotics, Networking and Artificial Life (JRNAL)
Subjects:
Emotional speech
feature parameter
emotional synthetic speech
vowel
sentence
Online Access:https://www.atlantis-press.com/article/125941068/view
id doaj-2e149bb758044d4598eccdc91bec1fd7
record_format Article
spelling doaj-2e149bb758044d4598eccdc91bec1fd72020-11-25T02:36:57ZengAtlantis PressJournal of Robotics, Networking and Artificial Life (JRNAL)2352-63862020-06-017210.2991/jrnal.k.200528.007Speech Synthesis of Emotions in a Sentence using Vowel FeaturesRintaro MakinoYasunari YoshitomiTaro AsadaMasayoshi TabuseWe previously proposed a method for adding emotions to synthetic speech using the vowel features of a speaker. For the initial investigation in this earlier study, we used utterances of Japanese names to demonstrate the method. In the present study, we use the proposed method to construct emotional synthetic speech for a sentence formed from the emotional speech of a single male subject and produce results that are discriminable with good accuracy.https://www.atlantis-press.com/article/125941068/viewEmotional speechfeature parameteremotional synthetic speechvowelsentence
collection DOAJ
language English
format Article
sources DOAJ
author Rintaro Makino
Yasunari Yoshitomi
Taro Asada
Masayoshi Tabuse
spellingShingle Rintaro Makino
Yasunari Yoshitomi
Taro Asada
Masayoshi Tabuse
Speech Synthesis of Emotions in a Sentence using Vowel Features
Journal of Robotics, Networking and Artificial Life (JRNAL)
Emotional speech
feature parameter
emotional synthetic speech
vowel
sentence
author_facet Rintaro Makino
Yasunari Yoshitomi
Taro Asada
Masayoshi Tabuse
author_sort Rintaro Makino
title Speech Synthesis of Emotions in a Sentence using Vowel Features
title_short Speech Synthesis of Emotions in a Sentence using Vowel Features
title_full Speech Synthesis of Emotions in a Sentence using Vowel Features
title_fullStr Speech Synthesis of Emotions in a Sentence using Vowel Features
title_full_unstemmed Speech Synthesis of Emotions in a Sentence using Vowel Features
title_sort speech synthesis of emotions in a sentence using vowel features
publisher Atlantis Press
series Journal of Robotics, Networking and Artificial Life (JRNAL)
issn 2352-6386
publishDate 2020-06-01
description We previously proposed a method for adding emotions to synthetic speech using the vowel features of a speaker. For the initial investigation in this earlier study, we used utterances of Japanese names to demonstrate the method. In the present study, we use the proposed method to construct emotional synthetic speech for a sentence formed from the emotional speech of a single male subject and produce results that are discriminable with good accuracy.
topic Emotional speech
feature parameter
emotional synthetic speech
vowel
sentence
url https://www.atlantis-press.com/article/125941068/view
work_keys_str_mv AT rintaromakino speechsynthesisofemotionsinasentenceusingvowelfeatures
AT yasunariyoshitomi speechsynthesisofemotionsinasentenceusingvowelfeatures
AT taroasada speechsynthesisofemotionsinasentenceusingvowelfeatures
AT masayoshitabuse speechsynthesisofemotionsinasentenceusingvowelfeatures
_version_ 1724797774561542144

Similar Items