論文 - 北村 達也
-
System Integration for Component-Based Manzai Robots with Improved Scalability
Tomohiro Umetani, Satoshi Aoki, Tatsuya Kitamura, Akiyo Nadamoto
Journal of Robotics and Mechatronics 32 ( 2 ) 459 - 468 2020年4月
出版者・発行元：Fuji Technology Press Ltd.
This paper describes system developments for integrating control systems of Manzai robot duos that automatically generate Manzai scripts from Internet articles based on given keywords, as well as improvements in the scalability of the integrated control system. Component-based Manzai robots controlled by RT-Middleware have been developed. However, conventional Manzai robot systems, the control systems of which are individually developed, experience some difficulties in interface integration and system maintenance as well as in scalability. In this study, we built a Manzai robot system excellent in reusability, maintainability and scalability by separating the common part from the hardware-dependent part by using the RT components of RT-Middleware. We also verify the reusability and scalability of the hardware-constrained component groups by implementing the Manzai robot control system into ready-made robots with different types of mechanism. We proved the effectiveness of the developed Manzai robot control system on its implementation results.
-
東京方言話者の単語音声におけるおそ下がりの生起条件の調査 査読あり
北村 達也, 天川 雄太, 波多野 博顕
音声研究 23 ( 0 ) 165 - 173 2019年12月
共著
出版者・発行元：日本音声学会
おそ下がりは，アクセント核に後続するモーラに基本周波数の下がり目が生じる現象である。本研究では，東京方言話者の男性21名，女性27名，計48名が読み上げた230語の単語音声を対象にしておそ下がりの生起条件を調査した。その結果，おそ下がりは(1) 男性よりも女性の方が生じやすい，(2) 中高型よりも頭高型の語に現れやすい，(3) 語に含まれるモーラ数が多い方が現れやすい，(4) アクセント核のあるモーラに後続するモーラに広母音を持つ語で現れやすいことが示された。
-
Further observations on a principal components analysis of head-related transfer functions 査読あり
Parham Mokhtari, Hiroaki Kato, Hironori Takemoto, Ryouichi Nishimura, Seigo Enomoto, Seiji Adachi, Tatsuya Kitamura
Scientific Reports 9 7477 2019年5月
-
大学生・大学院生を対象とした発話のしにくさの自覚に関するアンケート調査 査読あり
北村達也, 能田由紀子, 吐師道子, 竹本浩典
日本音響学会誌 75 ( 3 ) 118 - 124 2019年3月
共著
日本国内の15大学の日本語を母語とする大学生，大学院生を対象にして日常的な発話のしにくさの自覚に関するアンケート調査を行った。調査は質問紙法により実施した。回答のうち，言葉や聞こえの問題がないと回答した1,831名を対象に分析した。その結果，普段の会話で発音がうまくいかないと感じることが「ある」又は「どちらかと言えばある」と回答した者は全体の31.0%であった。男女別に分析すると，男性の35.5%，女性の24.4%が普段の会話で発音がうまくいかないと感じることが「ある」又は「どちらかと言えばある」と回答し，発話のしにくさを自覚する人は自分の音声が聞き返されることが多いと感じる傾向があった。
-
教科書中の単語の初出課を判定する日本語教育支援システムの利用状況の分析
北村 達也
甲南大学紀要 知能情報学編 11 ( 2 ) 209 - 215 2019年2月
単著
出版者・発行元：甲南大学
日本語教育用の教科書に含まれる単語がその教科書において初めて現れる課（初出課）を自動的に判定するシステムを開発し，その利用状況を調査した．その結果，2018年4月1日から7月31日までの四半期に10,000回を超えるアクセスがあり，そのうちの約9割は日本国内からのアクセスであった．また，利用者100名を対象としたアンケート調査の結果，利用者の約6割が日本語教師を職業としている人であった．そして，利用者の約8割がこのようなシステムの有無が教科書の選定に影響すると回答した．
DOI： 10.14990/00003307
その他リンク： http://doi.org/10.14990/00003307
-
Morphological characteristics of male and female hypopharynx: A magnetic resonance imaging-based study 査読あり
Ju Zhang, Kiyoshi Honda, Jianguo Wei, Tatsuya Kitamura
Journal of the Acoustical Society of America 145 734 2019年2月
-
チューブ発声時の皮膚振動を利用したバイオフィードバックシステムの開発と効果の検討 査読あり
川村直子, 北村達也, 城本修
音声言語医学 59 ( 4 ) 334 - 341 2018年9月
-
Audio-Visual Teaching Aid for Instructing English Stress Timings
Tatsuya Kitamura, Ryo Nagata, Kotaro Funakoshi
甲南大学紀要 知能情報学編 11 ( 1 ) 1 - 17 2018年7月
共著
出版者・発行元：甲南大学
This study proposed and evaluated an audio-visual teaching aid for teaching rhythm of spoken English. The teaching aid instructs stress timing of English by movements of a circle marker on PC screen. Native Japanese participants exercised English sentences with and without the teaching aid and their speech sounds were recorded before and after the exercise. The results of analyses of the speech sounds showed that the teaching aid could improve in learning the English stress timing.
DOI： 10.14990/00003196
その他リンク： http://doi.org/10.14990/00003196
-
Tatsuya Kitamura, Yukiko Nota, Michiko Hashi, Hiroaki Hatano
JASA Express Letters 143 ( 3 ) EL154 - EL159 2018年3月
-
自己完結性を有するコンポーネント駆動型の卓上ロボット環境の構築
梅谷智弘, 清瀬大貴, 榊原洋之, 青木哲, 北村達也
計測自動制御学会論文誌 54 ( 1 ) 126 - 128 2018年
-
Scalable Component-Based Manzai Robots as Automated Funny Content Generators
Tomohiro Umetani, Satoshi Aoki, Kazuhiro Akiyama, Ryo Mashimo, Tatsuya Kitamura, Akiyo Nadamoto
Journal of Robotics and Mechatronics 28 ( 6 ) 862 - 869 2016年12月
-
Implicit Communication Robots based on Automatic Scenario Generation using Web Intelligence
MASHIMO Ryo, KITAMURA Tatsuya, UMETANI Tomohiro, NADAMOTO Akiyo
International Journal of Web Information Systems 12 ( 3 ) 312 - 335 2016年9月
-
Manzai robot system with scalability based on distributed software components
Tomohiro Umetani, Satoshi Aoki, Kazuhiro Akiyama, Ryo Mashimo, Tatsuya Kitamura, Akiyo Nadamoto
2015 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2015 2016年3月
共著
出版者・発行元：Institute of Electrical and Electronics Engineers Inc.
This paper describes a manzai robot system with scalability that is developed based on the distributed software components. Manzai is a Japanese traditional stand-up comedy that is usually performed by two comedians. The manzai robots generate their manzai scripts based on web news articles related to keywords given by audiences and the searching results on WWW automatically, and then the robots perform the manzai scripts. Each robot is controlled by distributed RT components executed on the Raspberry Pi controller. The RT components control the manzai robots synchronously. The paper focuses on the scalability of the manzai robot system. Experimental results show the feasibility of manzai performance robots with scalability of the functions of the robot systems.
-
磁気センサシステムに基づく調音運動と口蓋形状の関係の観測
北村 達也, 能田 由紀子, 吐師 道子, 波多野 博顕, 梅谷 智弘
音声言語医学 57 ( 1 ) 52 - 52 2016年1月
-
Human-Robots Implicit Communication based on Dialogue between Robots using Automatic Generation of Funny Scenarios from Web
Ryo Mashimo, Tomohiro Umetani, Tatsuya Kitamura, Akiyo Nadamoto
ELEVENTH ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN ROBOT INTERACTION (HRI'16) 327 - 334 2016年
共著
出版者・発行元：ASSOC COMPUTING MACHINERY
Numerous studies have examined communication robots that communicate with people, but it is difficult for robots to communicate with people smoothly. We call the communication style based on dialogue between robots as "human-robot implicit communication". As described herein, we propose a Manzai-robots for which the interaction style is human-robot implicit communication based on an automatically generated scenario from web news. Our generated Manzai scenario consists of snappy patter and a misunderstanding of dialogue based on the four kinds of gap of structure of funny points. Our purpose is that people feel familiarity from smoothly human-robot communication using dialogue between robots based on a Manzai scenario. We conducted experiment of three kinds to assess (1) the effectiveness of automatic creation of Manzai scenario for the robots, (2) the effectiveness of the Manzai-robots as a media, and (3) the effectiveness of types of familiarity for Manzai-robots. Based on their results, we measured the familiarity and smooth communication of our Manzai-robots.
-
Automatic generation of Japanese traditional funny scenario from web content based on web intelligence
Ryo Mashimo, Tomohiro Umetani, Tatsuya Kitamura, Akiyo Nadamoto
17th International Conference on Information Integration and Web-Based Applications and Services, iiWAS 2015 - Proceedings 2015年12月
共著
出版者・発行元：Association for Computing Machinery, Inc
Today there is much information and knowledge on the internet, and many studies have examined the extraction of many kinds of knowledge from the internet. In addition, numerous studies have examined entertainment robots that communicate with people, but it is difficult for robots to communicate smoothly with people. We specifically examine communication between robots based on dialogue. Here, we create a dialogue-based scenario for the robots to undertake automatically, but it is difficult because the dialogue requires knowledge of many kinds. We consider the use of the knowledge from the web and create scenarios automatically. As described herein, we propose a system that generates dialogue scenarios automatically from web news articles in real time. We used the Manzai metaphor, which is Japanese traditional humorous comedy in our system. Our generated Manzai scenario consists of snappy patter and a misunderstanding dialogue based on the gap of our structure of funny points. We create communication robots to amuse people with our generated humorous robot dialogue scenarios.
-
話しにくさを自覚する若年成人の調音動態 : 歯茎弾き音について
立川 渉, 小澤 由嗣, 吐師 道子, 北村 達也, 能田 由紀子
音声研究 19 ( 3 ) 50 - 56 2015年12月
-
Crucial Prosodic Features in Japanese Learners' Pronunciation: Evidence from Naturalness Judgments of Synthetic Speech 査読あり
Rongna A, Ryoko Hayashi, Tatsuya Kitamura
音声研究 19 ( 3 ) 37 - 42 2015年12月
-
Non-contact measurement of facial surface vibration patterns during singing by scanning laser Doppler vibrometer
Tatsuya Kitamura, Keisuke Ohtani
Frontiers in Psychology, section Performance Science 6 2015年11月