A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion
碩士 === 國立成功大學 === 電機工程學系 === 102 === In this thesis, a vivid storytelling system is proposed for making audience immerse deeply into the story and also enhancing the interest of storytelling. For conveying emotion more vividly, the nonverbal paralinguistic cues like affective prosody and nonverbal v...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2014
|
Online Access: | http://ndltd.ncl.edu.tw/handle/4q83r4 |
id |
ndltd-TW-102NCKU5442193 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-102NCKU54421932019-05-15T21:42:47Z http://ndltd.ncl.edu.tw/handle/4q83r4 A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion 非語言情緒線索產生與故事角色轉換之生動說故事系統 Chia-HaoChang 張家豪 碩士 國立成功大學 電機工程學系 102 In this thesis, a vivid storytelling system is proposed for making audience immerse deeply into the story and also enhancing the interest of storytelling. For conveying emotion more vividly, the nonverbal paralinguistic cues like affective prosody and nonverbal vocalizations (laughter, shout, weeping and etc.) play an important roles in storytelling. In addition, role-playing element such like speaker style applied into storytelling can improve the dramatic impression of story. For this purpose, this storytelling system is with two artifices: 1) convey emotions by nonverbal emotional cues 2) convert the voice of storyteller to the specific story role. In order to generate the nonverbal emotional cues, we synthesis expressive speech by HMM-based TTS and insert nonverbal emotional vocalization (NEV) by a generation module consisted of emotion classification based on SVM and a template-based NEV prediction model. In addition, for generating different story role’s voice, the speaker conversion based on formant warping is used to conquer the problem of recording a heavy amount of multiple speaker’s expressive style speech corpora. The experimental result shows that our storytelling system can achieve a MOS of 4.43, it indicates that the proposed storytelling is more near to real storyteller except a slight unnaturalness. Furthermore, the storytelling with emotional expression and role-playing is more natural for audience, and captures more audience’s attention. Jhing-Fa Wang 王駿發 2014 學位論文 ; thesis 46 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立成功大學 === 電機工程學系 === 102 === In this thesis, a vivid storytelling system is proposed for making audience immerse deeply into the story and also enhancing the interest of storytelling. For conveying emotion more vividly, the nonverbal paralinguistic cues like affective prosody and nonverbal vocalizations (laughter, shout, weeping and etc.) play an important roles in storytelling. In addition, role-playing element such like speaker style applied into storytelling can improve the dramatic impression of story. For this purpose, this storytelling system is with two artifices: 1) convey emotions by nonverbal emotional cues 2) convert the voice of storyteller to the specific story role.
In order to generate the nonverbal emotional cues, we synthesis expressive speech by HMM-based TTS and insert nonverbal emotional vocalization (NEV) by a generation module consisted of emotion classification based on SVM and a template-based NEV prediction model. In addition, for generating different story role’s voice, the speaker conversion based on formant warping is used to conquer the problem of recording a heavy amount of multiple speaker’s expressive style speech corpora.
The experimental result shows that our storytelling system can achieve a MOS of 4.43, it indicates that the proposed storytelling is more near to real storyteller except a slight unnaturalness. Furthermore, the storytelling with emotional expression and role-playing is more natural for audience, and captures more audience’s attention.
|
author2 |
Jhing-Fa Wang |
author_facet |
Jhing-Fa Wang Chia-HaoChang 張家豪 |
author |
Chia-HaoChang 張家豪 |
spellingShingle |
Chia-HaoChang 張家豪 A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion |
author_sort |
Chia-HaoChang |
title |
A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion |
title_short |
A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion |
title_full |
A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion |
title_fullStr |
A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion |
title_full_unstemmed |
A Vivid Storytelling System with Nonverbal Emotional Cues Generation and Story Role Conversion |
title_sort |
vivid storytelling system with nonverbal emotional cues generation and story role conversion |
publishDate |
2014 |
url |
http://ndltd.ncl.edu.tw/handle/4q83r4 |
work_keys_str_mv |
AT chiahaochang avividstorytellingsystemwithnonverbalemotionalcuesgenerationandstoryroleconversion AT zhāngjiāháo avividstorytellingsystemwithnonverbalemotionalcuesgenerationandstoryroleconversion AT chiahaochang fēiyǔyánqíngxùxiànsuǒchǎnshēngyǔgùshìjiǎosèzhuǎnhuànzhīshēngdòngshuōgùshìxìtǒng AT zhāngjiāháo fēiyǔyánqíngxùxiànsuǒchǎnshēngyǔgùshìjiǎosèzhuǎnhuànzhīshēngdòngshuōgùshìxìtǒng AT chiahaochang vividstorytellingsystemwithnonverbalemotionalcuesgenerationandstoryroleconversion AT zhāngjiāháo vividstorytellingsystemwithnonverbalemotionalcuesgenerationandstoryroleconversion |
_version_ |
1719119185178525696 |