Presentation | 2018-10-28 Neural Network based articulation feature analysis system and its application to speech of cleft palate children Akihiro Eto, Hiroki Arakawa, Masahiro Tezuka, Norihumi Nakamura, Tadashi Sakata, Yuichi Ueda, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Speech therapists or dentists evaluate the presence or absence of dysarthria by his/her auditory. However, its diagnosis is not objective since those evaluations are influenced by listener's auditory experiences. Therefore, we analyzed abnormal articulation features using a neural network(NN) to diagnose dysarthria objectively. We applied the NN to healthy and cleft palate voices of commercially speech data in order to capture the articulation features of cleft palate. Then, we consider practicality of the NN by applying the NN to recorded sound in the same way. In the end, we applied non-metric multi dimensional scaling to the NN results. As a result, possibility of visualizing presence or absence of dysarthria is confirmed. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Cleft palate / Dysarthria / Neural Network / Non-metric Multi Dimentional Scaling |
Paper # | SP2018-47,WIT2018-35 |
Date of Issue | 2018-10-20 (SP, WIT) |
Conference Information | |
Committee | WIT / SP |
---|---|
Conference Date | 2018/10/27(2days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | Kyushu Institute of Technology(Kitakyushu) |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | Chikamune Wada(Kyushu Inst. of Tech.) / Yoichi Yamashita(Ritsumeikan Univ.) |
Vice Chair | Daisuke Wakatsuki(Tsukuba Univ. of Tech.) / Akinobu Ri(Nagoya Inst. of Tech.) |
Secretary | Daisuke Wakatsuki(AIST) / Akinobu Ri(Nagoya Inst. of Tech.) |
Assistant | Manabi Miyagi(Tsukuba Univ. of Tech.) / Takeaki Shionome(Teikyo Univ.) / Takashi Handa(Saitama Industrial Tech. Center) / Tomoki Koriyama(Tokyo Inst. of Tech.) / Satoshi Kobashikawa(NTT) |
Paper Information | |
Registration To | Technical Committee on Well-being Information Technology / Technical Committee on Speech |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Neural Network based articulation feature analysis system and its application to speech of cleft palate children |
Sub Title (in English) | |
Keyword(1) | Cleft palate |
Keyword(2) | Dysarthria |
Keyword(3) | Neural Network |
Keyword(4) | Non-metric Multi Dimentional Scaling |
1st Author's Name | Akihiro Eto |
1st Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
2nd Author's Name | Hiroki Arakawa |
2nd Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
3rd Author's Name | Masahiro Tezuka |
3rd Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
4th Author's Name | Norihumi Nakamura |
4th Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
5th Author's Name | Tadashi Sakata |
5th Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
6th Author's Name | Yuichi Ueda |
6th Author's Affiliation | Kumamoto University(Kumamoto Univ.) |
Date | 2018-10-28 |
Paper # | SP2018-47,WIT2018-35 |
Volume (vol) | vol.118 |
Number (no) | SP-269,WIT-270 |
Page | pp.pp.79-84(SP), pp.79-84(WIT), |
#Pages | 6 |
Date of Issue | 2018-10-20 (SP, WIT) |