Misc - NISIMURA Ryuichi

音声認識に用いた劣化音声に含まれる情報の検討

松村 勇作, 入野 俊夫, 西村 竜一, 河原 英紀

日本音響学会2007年春季研究発表会講演論文集     475-476   2007.03

言語バリア解消を目指した音声認識医療受付対話支援システム

宮部 真衣,吉野 孝,西村 竜一

情報処理学会第69回全国大会講演論文集     5F-5   2007.03

ネットワーク公開試験に向けた音声対話Webアプリケーションの開発

西村 竜一, 三宅 純平, 河原 英紀, 入野 俊夫

日本音響学会2007年春季研究発表会講演論文集     17-18   2007.03

母音情報に基づく話者変換システムの提案--音声テクスチャマッピングの一実装例

高橋徹,森勢将雅,西村竜一,入野俊夫,河原英紀,坂野秀樹

電子情報通信学会技術研究報告 ( 日本音響学会聴覚研究委員会 )  37 ( 2 ) SP2006-162 - 92   2007.03

Insights gained from development and long-term operation of a real-environment speech-oriented guidance system

Tobias Cincarek, Ryuichi Nisimura, Akinobu Lee, Kiyohiro Shikano

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings   4   IV157 - IV160   2007  [Refereed]

　View Summary

This paper presents insights gained from operating a public speech-oriented guidance system. A real-environment speech database (300 hours) collected with the system over four years is described and analyzed regarding usage frequency, content and diversity. Having the first two years of the data completely transcribed, simulation of system development and evaluation of system performance over time is possible. The database is employed for acoustic and language modeling as well as construction of a question and answer database. Since the system input is not text but speech, the database enables also research on open-domain speech-based information access. Apart from that research on unsupervised acoustic modeling, language modeling and system portability can be carried out. A performance evaluation of the system in an early stage as well as late stage when using two years of real-environment data for constructing all system components shows the relative importance of developing each system component. The system's response accuracy is 83% for adults and 68% for children. © 2007 IEEE.

DOI

The Speech-oriented Guidance System Takemaru and its Portability

CINCAREK Tobias, KAWANAMI Hiromichi, KIDA Manabu, SARUWATARI Hiroshi, SHIKANO Kiyohiro, NISHIMURA Ryuichi, LEE Akinobu

IEICE technical report. Speech ( The Institute of Electronics, Information and Communication Engineers )  106 ( 443 ) 173 - 178   2006.12

　View Summary

The development of the speech-oriented guidance system Takemaru is simulated using the data collected during the first two-years of regular operation. The relationship between the period of data collection, the number of speech inputs, number of words, language model perplexity, OOV rate, speech recognition performance and response accuracy is investigated. Based on this analysis, the relative importance of developing each system component can be assessed. Most important are efforts regarding the Q&A database followed by the acoustic and the language model. Moreover, a maximum in system performance seems to be reached after one year of data collection and overall improvement has the tendency to stagnate even if more data becomes available. Apart from that, the portability of the Takemaru system regarding a different environment, the Kitachan system installed at a local subway station, is investigated. Assuming a more realistic setting, only the data collected during twenty days is employed for system development. While the Takemaru ASR component shows a high portability, more efforts regarding the question and answer database have to be carried out in the future.

「たけまるくん」実環境音声案内システムのデータベースの整備と「キタちゃん」へのポータビリティーの検討

Tobias Cincarek, 川波 弘道, 木田 学, 鹿野 清宏, 西村 竜一, 李 晃伸

情報処理学会研究報告     2006-SLP-64-31   2006.12

(サーベイ) ICSLPにおける研究動向 -言語モデル・対話システムを中心に-

西村 竜一, 秋田 祐哉, 須藤 克仁, 大庭 隆伸

情報処理学会研究報告, ( Information Processing Society of Japan (IPSJ) )  2006 ( 136 ) 2006-SLP-64-42 - 244   2006.12

　View Summary

This paper reports survey studies of Interspeech2006-ICSLP held at Pittsburgh, USA in September 2006. The major topics are consisted of technologies such as ASR, Language Modeling, Language Processing, Spoken Dialog, Spoken Information Retrieval, Speech Summarization, and Speech Translation.

Development of nonvoice dialogue interface for robot systems

Ryuichi Nisimura, Aki Hashizume （Part： Lead author,　Last author,　Corresponding author )

4th Joint Meeting Acoustical Society of America and Acoustical Society of Japan (The Journal of the Acousitcal Society of America)     Vol.120, No.5, Pt.2 of 2, p.3040   2006.11  [Refereed]

[招待講演] 音声情報案内システム「たけまるくん」および「キタちゃん」の開発

鹿野 清宏, Tobias Cincarek, 川波 弘道, 西村 竜一, 李 晃伸

情報処理学会研究報告   2006 ( 7 ) 2006-SLP-63-7 - 38   2006.10

ロボット対話のための雑音認識手法に関する検討

橋爪 亜希, 西村 竜一, 入野 俊夫, 河原 英紀

日本音響学会2006年秋季研究発表会講演論文集     135-136   2006.09

Analyzing Dialogue Data for Real-World Emotional Speech Classification

Ryuichi Nisimura, Souji Omae, Hideki Kawahara, Toshio Irino

Proc. Interspeech2006 - ICSLP (The Ninth International Conference on Spoken Language Processing)     2006.09  [Refereed]

Human-robot interaction interface using GMM-based noise recognition

Ryuichi Nisimura, Aki Hashizume, Toshio Irino, Hideki Kawahara

Proc. WESPAC IX 2006 (9th Western Pacific Acoustics Conference)   347   347 - 28   2006.06  [Refereed]

雑音認識能力を持つロボット対話インタフェース

西村竜一, 橋爪亜希, 入野俊夫, 河原英紀

日本音響学会2006年春季研究発表会講演論文集     pp.203-204   2006.03

ユビキタスホームにおける対話ロボットのための音声・雑音認識

西村竜一

情報通信研究機構 第3回ユビキタスホームワークショップ     35-39   2006.03

回帰分析による実環境対話音声の快・不快感情識別

大前 壮司, 西村 竜一,河原 英紀, 入野 俊夫

日本音響学会2006年春季研究発表会講演論文集   2006   pp.359-360 - Q-13"   2006.03

Humanoid with interaction ability using vision and speech information

Junichi Ido, Yoshio Matsumoto, Tsukasa Ogasawara, Ryuichi Nisimura

IEEE International Conference on Intelligent Robots and Systems     1316 - 1321   2006  [Refereed]

　View Summary

Intelligent robots will make a chance for us to use a computer in our daily life. We implemented a humanoid robot for the computerized university guidance at first and then some capabilities for the natural interaction are added. This paper describes the hardware and software system of this humanoid with interaction ability. HRP-2 sitting opposite to a user across a table can detect gaze direction, head pose and gestures using a stereo camera system attached to the head. In addition, our system can recognize the user's question utterance and non-stationary noise such as coughing and sneezing using microphones. Using efficiently such information, HRP-2 can answer the question by its synthesized voice with gestures and do tasks such as passing objects on the table. © 2006 IEEE.

DOI

Spectral fluctuation mapping model for Japanese speech style conversion based on statistics in emotional speech database

Toru Takahashi, Hideki Banno, Ryuichi Nisimura, Toshio Irino, Hideki Kawahara

Proc. Oriental COCOSDA2005     111-116   2005.12  [Refereed]

HRP-2によるマルチモーダルインタラクション ～視覚と音声を利用した対話システムの構築～

怡土順一, 西村竜一, 末永剛, 佐々尾直樹, 近藤理, 松本吉央, 小笠原司

第23回日本ロボット学会学術講演会予稿集     1H12   2005.09

Operating A Public Spoken Guidance System In Real Environment

Ryuichi Nisimura, Akinobu Lee, Masashi Yamada, Kiyohiro Shikano

Proc. 9th European Conference on Speech Communication and Technology (Interspeech'2005 - Eurospeech)     845 - 848   2005.09  [Refereed]