Papers - SUGIURA, Komei

Dialogue strategy optimization to assist user's decision for spoken consulting dialogue systems

T Misu, K Sugiura, K Ohtake, C Hori, H Kashioka, H Kawai, S Nakamura

2010 IEEE Spoken Language Technology Workshop, 354-359    354 - 359 2010

• Access to Document (DOI)

Detection of Robot-Directed Speech by Situated Understanding in Physical Interaction

左祥， 岩橋直人， 田口亮， 松田繁樹， 杉浦孔明， 船越孝太郎， 中野幹生， ...

Proceedings of the Annual Conference of JSAI (The Japanese Society for Artificial Intelligence)  2010 ( 0 ) 1J1OS134 - 1J1OS134 2010

　View Summary

<p>In this paper, we propose a novel method for a robot to detect robot-directed speech from other speech: to distinguish speech that users speak to a robot from speech that users speak to other people or to himself. The originality of this work is the introduction of Multimodal Semantic Confidence measure, which is used for domain classification of input speech based on deciding whether the speech can be interpreted as a feasible action under the current physical situation in an object manipulation task. This measure is calculated by integrating speech, object, and motion confidence with weightings that are optimized by logistic regression. Then we integrate this measure with gaze tracking, and conduct experiments under conditions of natural human-robot interactions. Experimental results show that the proposed method achieved a high performance of 94% and 96% in average recall and precision rates for robot-directed speech detection.</p>

• Access to Document (DOI)

Detecting robot-directed speech by situated understanding in physical interaction

X Zuo, N Iwahashi, K Funakoshi, M Nakano, R Taguchi, S Matsuda, ...

Information and Media Technologies 5 (4), 1314-1326 (一般社団法人 人工知能学会)  25 ( 6 ) 670 - 682 2010

ISSN  1346-0714

　View Summary

In this paper, we propose a novel method for a robot to detect robot-directed speech: to distinguish speech that users speak to a robot from speech that users speak to other people or to themselves. The originality of this work is the introduction of a multimodal semantic confidence (MSC) measure, which is used for domain classification of input speech based on the decision on whether the speech can be interpreted as a feasible action under the current physical situation in an object manipulation task. This measure is calculated by integrating speech, object, and motion confidence with weightings that are optimized by logistic regression. Then we integrate this measure with gaze tracking and conduct experiments under conditions of natural human-robot interactions. Experimental results show that the proposed method achieves a high performance of 94% and 96% in average recall and precision rates, respectively, for robot-directed speech detection.

• Access to Document (DOI)

Detecting robot-directed speech by situated understanding in object manipulation tasks

X Zuo, N Iwahashi, R Taguchi, K Funakoshi, M Nakano, S Matsuda, ...

19th International Symposium in Robot and Human Interactive Communication …    608 - 613 2010

• Access to Document (DOI)

Active learning of confidence measure function in robot language acquisition framework

K Sugiura, N Iwahashi, H Kashioka, S Nakamura

2010 IEEE/RSJ International Conference on Intelligent Robots and Systems …    1774 - 1779 2010

• Access to Document (DOI)

Active learning for generating motion and utterances in object manipulation dialogue tasks

K Sugiura, N Iwahashi, H Kawai, S Nakamura

2010 AAAI Fall Symposium Series  2010

日用品を扱う物体操作の模倣学習による動作の言語化

杉浦孔明， 岩橋直人， 柏岡秀紀， 中村哲

人工知能学会全国大会論文集 第 24 回全国大会 (2010), 1J1OS136-1J1OS136 (The Japanese Society for Artificial Intelligence)  2010 ( 0 ) 1J1OS136 - 1J1OS136 2010

　View Summary

<p>生活環境で人間を支援するロボットへの期待が高まっている．ロボカップ＠ホームなど生活環境で日用品を扱うロボットが見られるようになってきたが，物体操作はヒューリスティックな手法により実現されている．本論文では，ユーザが日用品をハンドリングする軌道から，動作の確率モデルを統計学習する手法を提案する．本手法と音声処理を統合することにより，物体操作の学習・認識・生成を行う対話ロボットについて報告する．</p>

• Access to Document (DOI)

Learning novel objects using out-of-vocabulary word segmentation and object extraction for home assistant robots

M Attamimi, A Mizutani, T Nakamura, K Sugiura, T Nagai, N Iwahashi, ...

2010 IEEE International Conference on Robotics and Automation, 745-750    745 - 750 2010

• Access to Document (DOI)

Statistical imitation learning in sequential object manipulation tasks

K Sugiura, H Kashioka, N Iwahashi, S Nakamura

INTECH Open Access Publisher  2010

Simultaneous design of the sensory morphology and controller of mobile robots

K Sugiura, H Kawakami, O Katai

Electrical Engineering in Japan 172 (1), 48-57  2010

Robots that learn to communicate: A developmental approach to personally and physically situated human-robot conversations

N Iwahashi, K Sugiura, R Taguchi, T Nagai, T Taniguchi

2010 AAAI Fall Symposium Series  2010

Robot-directed speech detection using multimodal semantic confidence based on speech, image, and motion

X Zuo, N Iwahashi, R Taguchi, S Matsuda, K Sugiura, K Funakoshi, ...

2010 IEEE International Conference on Acoustics, Speech and Signal …    2458 - 2461 2010

• Access to Document (DOI)

Modeling spoken decision making dialogue and optimization of its dialogue strategy

T Misu, K Sugiura, K Ohtake, C Hori, H Kashioka, H Kawai, S Nakamura

Proceedings of the 11th Annual Meeting of the Special Interest Group on …    221 - 224 2010

言語獲得ロボットによる発話理解確率の推定に基づく物体操作対話確認発話

SUGIURA Komei, IWAHASHI Naoto

日本ロボット学会誌 Vol.28, No.8    978 - 988 2010

Accepted

Bayesian learning of confidence measure function for generation of utterances and motions in object manipulation dialogue task

K Sugiura, N Iwahashi, H Kashioka, S Nakamura

Tenth Annual Conference of the International Speech Communication Association    2483 - 2486 2009

Robots that learn to converse: Developmental approach to situated language processing

N Iwahashi, R Taguchi, K Sugiura, K Funakoshi, M Nakano

Proceedings of International Symposium on Speech and Language Processing …  2009

対話戦略最適化としての発話理解確信度の能動学習

杉浦 孔明, 岩橋 直人

Proceedings of the Annual Conference of JSAI (The Japanese Society for Artificial Intelligence)  2009 ( 0 ) 1F2OS79 - 1F2OS79 2009

　View Summary

<p>本論文では，ユーザとロボットが対話を行うことにより，ユーザ発話に対する発話理解確信度を学習する手法を提案する．発話理解確信度は，音声・画像・動作・文法を統合した確率モデルにより表現され，実環境でユーザの教示に基づく統計的学習により獲得される．本論文では，物体操作タスクを行うロボットに提案手法を実装し，発話理解確信度の効率的な学習のために最適な発話を行わせた実験について報告する．</p>

• Access to Document (DOI)

対話戦略最適化としての発話理解確信度の能動学習

杉浦孔明， 岩橋直人

人工知能学会全国大会論文集 第 23 回全国大会 (2009), 1F2OS79-1F2OS79  2009

Simultaneous Design Method of the Sensory Morphology and Controller of Mobile Robots

SUGIURA Komei, KAWAKAMI Hiroshi, KATAI Osamu

IEEJ Transactions on Electronics, Information and Systems (The Institute of Electrical Engineers of Japan)  128 ( 7 ) 1154 - 1161 2008.07

ISSN  03854221

　View Summary

This paper proposes a method that automatically designs the sensory morphology of a mobile robot. The proposed method employs two types of adaptations -ontogenetic and phylogenetic- to optimize the sensory morphology of the robot. In ontogenetic adaptation, reinforcement learning searches for the optimal policy which is highly dependent on the sensory morphology. In phylogenetic adaptation, a genetic algorithm is used to select morphologies with which the robot can learn tasks faster. Our proposed method is applied to the design of the sensory morphology of a line-following robot. We carried out simulation experiments to compare the design solution with a hand-coded robot. The results of the experiments revealed that our robot outperforms a hand-coded robot in terms of the line-following accuracy and learning speed, although our robot has fewer sensors than the hand-coded one. We also manufactured a physical robot using the design solution. The experimental results revealed that this physical robot uses its morphology effectively and outperforms the hand-coded robot.

• Access to Document (DOI)

音声からの未登録語切り出しと画像からの物体抽出の統合による新規物体の学習

杉浦孔明， 水谷了， 中村友昭， 長井隆行， 岩橋直人， 岡田浩之， 大森隆司

第 26 回日本ロボット学会学術講演会論文集, 2008  2008