Faculty Profiles - KUDO, Hiroaki

Papers - KUDO, Hiroaki

Division display 141 - 160 of about 451 ／ All the affair displays >>

Effect of the Sight Line Shift when a Head-Mounted Display Is Used Reviewed

KUDO Hiroaki and OHNISHI Noboru

CD-ROM Proceedings of the World Congress on Medical Physics and Biomedical Engineering page： 1-4 2000.7

A System Assisting Blind Children to Acquire Spatial Awareness through Body Movement Reviewed

OHNISHI Noboru, YONEDA Takahiro, KUDO Hiroaki, and MINAGAWA Hiroki

Proceedings of The First BMES/EMBS Conference page： 653 1999.10

Modeling Dynamical Grouping Process Reviewed

YAMAMURA Tsuyoshi, KUDO Hiroaki, OHNISHI Noboru, and SUGIE Noboru

IEEE SMC'99 Conference Proceedings Vol. II page： 50-53 1999.10

Measurement of the ability in monocular depth perception during gazing at near visual target - effect of the ocular parallax cue Reviewed

KUDO Hiroaki, SAITO Masaya, YAMAMURA Tsuyoshi, and OHNISHI Noboru

IEEE SMC'99 Conference Proceedings Vol. II page： 34-37 1999.10

A Neural Network Model of Dynamically Fluctuating Perception of Necker Cube as well as Dot Patterns Reviewed

KUDO Hiroaki, YAMAMURA Tsuyoshi, OHNISHI Noboru, KOBAYASHI Shin, and SUGIE Noboru

AAAI-99/IAAI-99 Proceedings page： 194-199 1999.7

Correspondence Procedure for Recovery of Rigid Structure from Orthographically Projected Optical Flow -A Comoputational Aspect of kinetic Depth Effect- Reviewed

Hiroaki Kudo, Masayuki Umeda, Isao Horiba, Noboru Sugie, Tsuyoshi Yamamura and Noboru Ohnishi

Proceedings of the Fifth International Conference on Neural Information Processing Vol. 1 page： 401-404 1998.10

A Neural Network Model of Dynamical Grouping Process Reviewed

Tsuyoshi Yamamura, Shin Kobayashi, Isao Horiba, Noboru Sugie, Hiroaki Kudo and Noboru Ohnishi

Proceedings of the Fifth International Conference on Neural Information Processing Vol. 1 page： 319-322 1998.10

Study on the Ocular Parallax as a Monocular Depth Cue Induced by Small Eye Movements During a Gaze Reviewed

Hiroaki Kudo and Noboru Ohnishi

Proceedings of the Annual Interrational Conference of the IEEE Engineering in Medcine and Biology Society Vol. 20 ( 6 ) page： 3180-3183 1998.10

A Model of Saccade Mechanism Based on Occlusion Detection and Depth Estimation Processes Reviewed

Hiroaki Kudo, Kenya Uomori, Mitsuho Yamada, Noboru Ohnishi and Noboru Sugie

Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Vol. 18 ( 5 ) page： 8,3-6,1-3 1996.10

Binocular Fixation-Point Shifts induced by a Limb Occlution Reviewed

Hiroaki Kudo, Kenya Uomori, Mitsuho Yamada, Noboru Ohnishi and Noboru Sugie

Proceedings of the Annual International Conference of The IEEE Engineering in Medicine and Biology Society Vol. 14 page： 1670-1671 1992.10

多結晶材料における結晶欠陥発生予測モデルの構築と解析

原京花, 小島拓人, 沓掛健太朗, 工藤博章, 宇佐美徳隆

70回応用物理学会春季学術講演会 2023.3

話者間の識別損失の導入による時間領域モノラル音声分離

党　少翔，松本哲也，竹内義則，工藤博章

電子情報通信学会イメージ・メディア・クオリティ研究会 Vol. 122 ( 437 ) page： 375 - 380 2023.3

Ba-122多結晶バルクの粒界組織における新規結晶方位解析法開発

嶋田雄介，長谷川友大，徳田進ノ助，村岡幸樹，小島拓人，郭子萌，波多聰，工藤博章，宇佐美徳隆，山本明保

70回応用物理学会春季学術講演会, 2023.3

Using Semi-supervised Learning for Monaural Time-domain Speech Separation with a Self-supervised Learning-based SI-SNR Estimator

Dang S., Matsumoto T., Takeuchi Y., Kudo H.

Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH Vol. 2023-August page： 3759 - 3763 2023

Publisher：Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH

Speech separation aims to decompose mixed speeches into independent signals. Prior research on monaural time-domain speech separation has made great progress in supervised manners. Almost all of these works are trained on simulated mixed speech signals since obtaining ground truth for real-world mixed signals is problematic. To this end, we propose a novel semi-supervised learning method for speech separation (SSLM-SS), which leverages mixed speeches without ground truth. In particular, for this type of data, we further put forward a non-intrusive separated speech quality prediction network (SSQP-Net) based on self-supervised learning. According to the results, the linear correlation coefficient between the predicted results of SSQP-Net and the ground truth achieves 0.9. Moreover, the performance of SSLM-SS equipped with SSQP-Net exhibits an improvement of 0.2 dB and 1.1 dB compared to the mixture invariant training (MixIT) in the conditions of involving 10% and 50% labeled data respectively, and rivals fully supervised learning.

DOI： 10.21437/Interspeech.2023-85

Scopus

空間アテンションと属性相関関係に基づいた歩行者属性認識システム

陳　奕宸，松本哲也，竹内義則，工藤博章

電子情報通信学会イメージ・メディア・クオリティ研究会 Vol. 122 ( 317 ) page： 16 - 21 2022.12

結晶方位分布を用いた多結晶シリコン成長挙動のインゴットスケール解析

小島拓人, 原京花, 沓掛健太朗, 松本哲也, 工藤博章, 宇佐美徳隆

第83回応用物理学会秋季学術講演会 2022.9

結晶方位に依存した光学画像と粒界画像を用いた敵対的生成ネットワークによる蛍光画像の生成

工藤博章，小島拓人，松本哲也，沓掛健太朗，宇佐美徳隆

第19回次世代の太陽光発電シンポジウム 2022.6

結晶方位推定モデルのためのステージ走査型反射特性測定装置の画像処理パイプライン

小島拓人,原京花,沓掛健太朗,松本哲也,工藤博章,宇佐美徳隆

第19回次世代の太陽光発電シンポジウム 2022.6

太陽電池用多結晶Si 中の転位発生源 -TEM と多結晶材料情報学に基づく解析-

大野裕，山腰健太，横井達也，松永克志，沓掛健太朗，小島拓人，工藤博章，井上耕治，永井康介，宇佐美徳隆

第19回次世代の太陽光発電シンポジウム 2022.6

TEMと多結晶材料情報学に基づくシリコン中の転位発生源の解析

大野裕, 山腰健太, 沓掛健太朗, 小島拓人, 工藤博章, 田中博之, 永井康介,宇佐美徳隆

日本顕微鏡学会第78回学術講演会 2022.5

　 PREV - NEXT 　

<KUDO, Hiroaki>

Papers - KUDO, Hiroaki