Publications
2024
Journal Papers
Egocentric Human Activities Recognition With Multimodal Interaction Sensing
Yuzhe Hao, Asako Kanezaki, Ikuro Sato, Rei Kawakami, Koichi Shinoda
IEEE Sensors Journal, vol. 24, no. 5, pp. 7085-7096, Mar. 1, 2024, https://doi.org/10.1109/JSEN.2023.3349191
Conference Proceedings (peer reviewed)
Co-speech Gesture Generation with Variational Auto Encoder
Shinichi Ka, Koichi Shinoda
Proc. International Conference on Multimedia Modeling, Amsterdam, The Netherlands, Jan. 29 - Feb. 2, 2024, https://doi.org/10.1007/978-3-031-53311-2_12
CAMOT: Camera Angle-Aware Multi-Object Tracking
Felix Limanta, Kuniaki Uto, Koichi Shinoda
Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan. 4-8, 2024, pp. 6479-6488
Domestic Conference Proceedings
Multitask Learning of Speaker Separation and Direction-of-Arrival Estimation
Roland Hartanto, Sakriani Sakti, Koichi Shinoda
ASJ Spring Meeting, Mar. 6-8, 2024
2023
Conference Proceedings (peer reviewed)
Multimodal Recognition of Speech and Electrocorticogram
Mitali Ahuja, Shuji Komeiji, Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano, Koichi Shinoda, and Toshihisa Tanaka
Proc. 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Taipei, Taiwan, Oct. 31 - Nov. 3, 2023. https://doi.org/10.1109/APSIPAASC58517.2023.10317527
Sensor Data Representation with Transformer-Based Contrastive Learning for Human Action Recognition and Detection
Lei Yang, Yuzhe Hao, Koichi Shinoda
Proc. EUSIPCO, Sept. 4-8, 2023. https://doi.org/10.23919/EUSIPCO58844.2023.10289883
Synthesizing Speech from ECoG with a Combination of Transformer-Based Encoder and Neural Vocoder
Kai Shigemi, Shuji Komeiji, Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano, Koichi Shinoda, Kohei Yatabe, Toshihisa Tanaka
Proc. 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), June 4-10, 2023, Rhodes Island, Greece. https://doi.org/10.1109/ICASSP49357.2023.10097004
EvIs-Kitchen: Egocentric Human Activities Recognition with Video and Inertial Sensor data
Yuzhe Hao, Kuniaki Uto, Asako Kanezaki, Ikuro Sato, Rei Kawakami, Koichi Shinoda
Proc. International Conference on MULTIMEDIA MODELING, Jan. 9 - 12, 2023, Bergen, Norway. https://doi.org/10.1007/978-3-031-27077-2_29
Text-Guided Object Detector for Multi-modal Video Question Answering
Ruoyue Shen, Nakamasa Inoue, Koichi Shinoda
Proc. IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Jan. 3-7, 2023, pp. 1032 - 1042. https://doi.org/10.1109/WACV56688.2023.00109
Domestic Conference Proceedings
A Multimodal Model for Personality Recognition through Speech
Nathania Nah, Takafumi Koshinaka, Koichi Shinoda, Yuri Tsuchiya
ASJ Autumn Meeting, Sep. 26-28, 2024
Mode-Adaptive Transformer by Automatic Optimization of the Receptive Field
Takuya Asakura, Nakamasa Inoue , Rio Yokota , Koichi Shinoda
The 37th Annual Conference of the Japanese Society for Artificial Intelligence, June. 6-9, 2023
Personality Recognition on Dyadic Interactions with Representation Learning
Nathania Nah, Takafumi Koshinaka, Koichi Shinoda
第9回 音声・音響・信号処理ワークショップ（SPEASIP）IEICE Tech. Rep., vol. 122, no. 389, SP2022-81, pp. 241-246, Feb. 2023
Invited Talks & Tutorials
Structural MAP for LR & HMMs
Koichi Shinoda
Symposium for Celebrating 40 Years of Bayesian Learning in Speech and Language Processing and Beyond, IEEE ASRU 2023 Workshop Satellite Event, Taipei, December 20th, 2023.
2022
Conference Proceedings (peer reviewed)
Lattice-Based Data Augmentation for Code-Switching Speech Recognition
Roland Hartanto, Kuniaki Uto, Koichi Shinoda
Proc. 2022 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Chiang Mai, Thailand November 7-10, 2022, pp. 1667-1672. https://doi.org/10.23919/APSIPAASC55919.2022.9980277
Implicit Neural Representations for Variable Length Human Motion Generation
Pablo Cervantes, Yusuke Sekikawa, Ikuro Sato, Koichi Shinoda
Proc. European Conference on Computer Vision (ECCV) 2022: 17th European Conference, Tel Aviv, Israel, October 23–27, 2022, Proceedings, Part XVII Oct 2022, Pages 356–372. https://doi.org/10.1007/978-3-031-19790-1_22
MSR-DARTS: Minimum Stable Rank of Differentiable Architecture Search
Kengo Machida, Kuniaki Uto, Koichi Shinoda, Taiji Suzuki
Proc. IJCNN2022, Jul. 2022. https://doi.org/10.1109/IJCNN55064.2022.9892751
Rotation-invariant detection and classification for wheat head detection
Takeru Ito, Kuniaki Uto, Koichi Shinoda
Proc. IGARSS2022, pp.5750-5753, Jul. 2022. https://doi.org/10.1109/IGARSS46834.2022.9883405
Transformer-Based Estimation of Spoken Sentences Using Electrocorticography
Shuji Komeiji, Kai Shigemi, Takumi Mitsuhashi, Yasushi Iimura, Hiroharu Suzuki, Hidenori Sugano, Koichi Shinoda, and Toshihisa Tanaka
Proc. ICASSP2022, May 11, 2022. https://doi.org/10.1109/ICASSP43922.2022.9747443
Conference Proceedings (non-refereed)
Tokyo Tech at TRECVID 2022: Multi-Stage Framework for Video Action Detection
Ronaldo Prata Amorim, Nakamasa Inoue, Koichi Shinoda
TRECVID Workshop 2022, Dec. 2022.
Domestic Conference Proceedings
Implicit Neural Representation Learning for Human Motion Generation
Pablo Cervantes, Yusuke Sekikawa, Ikuro Sato, Koichi Shinoda
MIRU2022, Jul. 2022
Incorporating Acoustic and Textual Information for Language Modeling in Code-switching Speech Recognition
Roland Hartanto, Kuniaki Uto, Koichi Shinoda
Technical Report of IEICE SP, vol. 121, no. 385, pp. 56-63, Mar. 1 2022}
Invited Talks & Tutorials
Deep Learning and High-Performance Computing
Koichi Shinoda
International Conference on Recent Progresses in Science, Engineering and Technology (ICRPSET 2022), December 26~27, 2022.
2021
Journal Papers
Paralinguistic Approach for Detecting Dementia Using Gated Convolutional Neural Network
Mariana RODRIGUES MAKIUCHI, Tifani WARNITA, Nakamasa INOUE, Koichi SHINODA, Michitaka YOSHIMURA, Momoko KITAZAWA, Kei FUNAKI, Yoko EGUCHI, Taishiro KISHIMOTO
IEICE TRANSACTIONS on Information and Systems, Vol. E104-D, No. 11, pp. 1930-1940, Nov 2021.
Conference Proceedings (peer reviewed)
Multimodal Emotion Recognition with High-Level Speech and Text Features
Mariana Rodrigues Makiuchi, Kuniaki Uto, Koichi Shinoda
Proc. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2021, Dec 2021.
Smooth Transfer Learning for Source-to-Target Generalization
Keita Takayama, Ikuro Sato, Teppei Suzuki, Rei Kawakami, Kuniaki Uto, Koichi Shinoda
Proc. NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications, Dec 2021.
Noise-Tolerant Time-Domain Speech Separation with Noise Bases
Kohei Ozamoto, Kuniaki Uto, Koji Iwano, Koichi Shinoda
Proc. 13th Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), Dec 2021.
2020
Journal Papers
The project for objective measures using computational psychiatry technology (PROMPT): Rationale, design, and methodology
Taishiro Kishimoto, Akihiro Takamiya, Kuo-ching Liang, Kei Funaki, Takanori Fujita, Momoko Kitazawa, Michitaka Yoshimura, Yuki Tazawa, Toshiro Horigome, Yoko Eguchi, Toshiaki Kikuchi, Masayuki Tomita, Shogyoku Bun, Junichi Murakami, Brian Sumali, Tifani Warnita, Aiko Kishi, Mizuki Yotsui, Hiroyoshi Toyoshiba, Yasue Mitsukura, Koichi Shinoda, Yasubumi Sakakibara, Masaru Mimura, on behalf of thePROMPT collaborators
Contemporary Clinical Trials Communications, 100649, Aug. 18, 2020
Conference Proceedings (peer reviewed)
NEC-TT Speaker Verification System for SRE'19 CTS Challenge
Kong Aik Lee, Koji Okabe, Hitoshi Yamamoto, Qiongqiong Wang, Ling Guo, Takafumi Koshinaka, Jiacen Zhang, Keisuke Ishikawa, Koichi Shinoda,
Proc. Interspeech 2020, Oct. 2020
Estimation of leaf angle distribution based on statistical properties of leaf shading distribution
Kuniaki Uto, Mauro Dalla Mura, Yuka Sasaki, Koichi Shinoda
Proc. IGARSS2020, Oct. 2020
Conference Proceedings (non-refereed)
Tokyo Tech at TRECVID 2020: Relation Modeling for Video Action Detection
Ronaldo Prata Amorim, Nakamasa Inoue, Koichi Shinoda
TRECVID 2020 Notebook Papers, Dec. 2020.
Team Takoyaki submission for VoxCeleb Speaker Recognition Challenge 2020
Keisuke Ishikawa, Kuniaki Uto, Koji Iwano, Koichi Shinoda
The VoxSRC Workshop 2020, Oct. 2020.
Invited Talks & Tutorials
Co-design of ML and HPC for video understanding
Koichi Shinoda
1st International Workshop on Deep Video Understanding (DVU 2020）, Oct. 25, 2020.
Fast and cost-effective deep learning algorithm platform for video processing in social infrastructure
Koichi Shinoda
Chinese Academy of Science (CAS), Jan. 14, 2020.
Fast and cost-effective deep learning algorithm platform for video processing in social infrastructure
Koichi Shinoda
2020 International Workshop on AI-Driven Social Innovation (IWAIDSI 2020), Beijing University of Posts and Telecommunications (BUPT), Jan. 13, 2020.
2019
Journal Papers
NEC-TT System for Mixed-Bandwidth and Multi-Domain Speaker Recognition
Kong Aik Lee, Hitoshi Yamamoto, Koji Okabe, Qiongqiong Wang, Ling Guo, Takafumi Koshinaka, Jiacen Zhang, Koichi Shinoda
Computer speech & language, Volume 61, 101033, Nov. 13, 2019
Recurrent out-of-vocabulary word detection based on distribution of features
Taichi Asami, Ryo Masumura, Yushi Aono, Koichi Shinoda
Computer speech & language, Volume 58, Page 247-259, May 9, 2019.
Conference Proceedings (peer reviewed)
Multimodal Fusion of BERT-CNN and Gated CNN Representations for Depression Detection
Mariana Rodrigues Makiuchi, Tifani Warnita, Kuniaki Uto, Koichi Shinoda
Proc. AVEC2019, pp. 55-63, Oct. 2019
A Modified Algorithm for Multiple Input Spectrogram Inversion
Dongxiao Wang, Hirokazu Kameoka, Koichi Shinoda
Proc. INTERSPEECH2019, Sep. 2019
The NEC-TT 2018 Speaker Verification System
Kong Aik Lee, Hitoshi Yamamoto, Koji Okabe, Qiongqiong Wang, Ling Guo, Takafumi Koshinaka, Jiacen Zhang, Koichi Shinoda
Proc. INTERSPEECH2019, Sep. 2019
Estimation of Diffuse Component of Global Radiation Based on Leaf-Scale Crop Images
Kuniaki Uto, Mauro Dalla Mura, Jocelyn Chanussot, Koichi Shinoda
Proc. IGARSS2019, pp. 6263--6266, Jul. 2019
Sequence-level knowledge distillation for model compression of attention-based sequence-to-sequence speech recognition
Raden Mu’az Mun’im, Nakamasa Inoue, Koichi Shinoda
Proc. ICASSP2019, pp. 6151-6155, May 2019
Conference Proceedings (non-refereed)
Estimation of skylight conditions based on leaf-scale wheat images
Kuniaki Uto, Mauro Dalla Mura, Jocelyn Chanussot, Koichi Shinoda
Images et data : méthodes d'analyse et modélisation pour l'agriculture numérique, Mar. 14, 2019
Domestic Conference Proceedings
Speech-linguistic Multimodal Representation for Depression Severity Assessment
Mariana Rodrigues Makiuchi, Tifani Warnita, Kuniaki Uto, Koichi Shinoda
IPSJ SIG Technical Report, Vol.2019-SLP-130 No.8, Dec. 2019.
Improving the robustness of multiple input spectrogram inversion
Dongxiao Wang, Hirokazu Kameoka, Koichi Shinoda
ASJ 2019 Spring Meeting, pp. 1307-1308, Mar. 7, 2019
A robust algorithm of phase recovery for speech enhancement
Dongxiao Wang, Hirokazu Kameoka, Koichi Shinoda
Technical Reports of IEICE SP, vol. 118, no. 497, pp. 137-142, Mar. 14, 2019
2018
Conference Proceedings (peer reviewed)
Few-Shot Adaptation for Multimedia Semantic Indexing
Nakamasa Inoue, Koichi Shinoda
Proc. ACM Multimedia, pp. 1110-1118, Oct. 23, 2018
Attentive Statistics Pooling for Deep Speaker Embedding
Koji Okabe, Takafumi Koshinaka, Koichi Shinoda
Proc. Interspeech, pp. 2252--2256, Sep. 4, 2018
I-vector Transformation Using Conditional Generative Adversarial Networks for Short Utterance Speaker Verification
Jiacen Zhang, Nakamasa Inoue, Koichi Shinoda
Proc. Interspeech, pp. 3613-3617, Sep. 4, 2018
Detecting Alzheimer's Disease Using Gated Convolutional Neural Network from Audio Data
Tifani Warnita, Nakamasa Inoue, Koichi Shinoda
Proc. Interspeech, pp. 1706-1710, Sep. 4, 2018
A Fine-to-Coarse Convolutional Neural Network for 3D Human Action Recognition
Thao Minh Le, Nakamasa Inoue, Koichi Shinoda
Proc. British Machine Vision Conference (BMVC), Sep. 3, 2018
Deep Learning Based Multi-modal Addressee Recognition in Visual Scenes with Utterances
Thao Le Minh, Nobuyuki Shimizu, Takashi Miyazaki, Koichi Shinoda
Proc. International Joint Conference on Artificial Intelligence (IJCAI), pp. 1546-1553, Jul. 13, 2018
Multi-Task Autoencoder for Noise-Robust Speech Recognition
Haoyi Zhang, Conggui Liu, Nakamasa Inoue, Koichi Shinoda
Proc. ICASSP, pp. 5599-5603, Apr. 15, 2018
Conference Proceedings (non-refereed)
The NEC-TT Speaker Verification System for SRE’18
K. A. Lee, H. Yamamoto, K. Okabe, Q. Wang, L. Guo, T. Koshinaka, J. Zhang, K. Shinoda.
Proc. NIST 2018 Speaker Recognition Evaluation, Dec. 2018
VANT at TRECVID 2018
Nakamasa Inoue, Chihiro Shiraishi, Aleksandr Drozd, Koichi Shinoda, Shi-wook Lee, Alex Chichung Kot
Proc. TRECVID workshop, Nov. 13, 2018
Domestic Conference Proceedings
Skeleton-based Human Action Recognition with Fine-to-Coarse Convolutional Neural Network
Thao Minh Le, Nakamasa Inoue, Koichi Shinoda
Technical Reports of IEICE PRMU, vol. 118, no. 362, pp. 61-64, Dec. 13, 2018
Generative Adversarial Network Based i-Vector Transformation for Short Utterance Speaker Verification
Jiacen Zhang, Nakamasa Inoue, Koichi Shinoda
ASJ 2018 Autumn Meeting, pp. 1345-1346, Aug. 29, 2018
Alzheimer's Disease Prediction Using Audio Gated Convolutional Neural Network
Tifani Warnita, Nakamasa Inoue, Koichi Shinoda
ASJ 2018 Autumn Meeting, pp. 1223-1224, Aug. 29, 2018
Astronomical Image Subtraction for Transient Detection Using CNN
Yan Long, Nakamasa Inoue, Koichi Shinoda, Yoichi Yatsu, Ryosuke Itoh, Nobuyuki Kawai
The 21st Meeting on Image Recognition and Understanding (MIRU), Aug. 7, 2018
2017
Journal Papers
Cross-View Human Action Recognition from Depth Maps Using Spectral Graph Sequences
Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
Elsevier Journal of Computer Vision and Image Understanding (CVIU), vol. 154, pp. 108-126, Jan. 1, 2017
Conference Proceedings (peer reviewed)
A Unified Network for Multi-Speaker Speech Recognition with Multi-Channel Recordings
Conggui Liu, Nakamasa Inoue, Koichi Shinoda
Proc. APSIPA, pp. 1304-1307, Dec. 11, 2017
Multimodal Speech Recognition Using Mouth Images from Depth Camera
Yuki Yasui, Nakamasa Inoue, Koji Iwano, Koichi Shinoda
Proc. APSIPA, pp. 1233-1236, Dec. 11, 2017
User Adaptation of Convolutional Neural Network for Human Activity Recognition
Shinya Matsui, Nakamasa Inoue, Yuko Akagi, Goshu Nagino, Koichi Shinoda
2017 25th European Signal Processing Conference (EUSIPCO), pp. 753-757, Oct. 26, 2017
CTC Network with Statistical Language Modeling for Action Sequence Recognition in Videos
Mengxi Lin, Nakamasa Inoue, Koichi Shinoda
Proc. ACM Multimedia Thematic Workshop, pp. 393-401, Oct. 23, 2017
Boredom Recognition based on Users' Spontaneous Behaviors in Multiparty Human-Robot Interactions
Yasuhiro Shibasaki, Kotaro Funakoshi, Koichi Shinoda
Proc. MultiMedia Modeling (MMM), pp. 677-689, Jan. 4, 2017
Conference Proceedings (non-refereed)
TokyoTech-AIST at TRECVID 2017: Multimedia Event Detection Using Deep CNNs and Zero-Shot Classifiers
Nakamasa Inoue, Ryosuke Yamamoto, Na Rong, Satoshi Kanai, Junsuke Masada, Chihiro Shiraishi, Shi-wook Lee, Koichi Shinoda
Proc. TRECVID workshop, pp. 1-6, Nov. 13, 2017
Development of a cloud detection system utilizing image recognition technology
Y. Yatsu, T. Yoshii, N. Kawai, J. Sakuma, N. Inoue, K. Shinoda, T. Shimokawabe
V WORKSHOP ON ROBOTIC AUTONOMOUS OBSERVATORIES, Oct., 2017
Domestic Conference Proceedings
Action Sequence Recognition in Videos by Combining a CTC Network with a Statistical Language Model
Mengxi Lin, Nakamasa Inoue, Koichi Shinoda
Technical Reports of IEICE PRMU, vol. 117, no. 362, pp. 1-6, Dec. 16, 2017
Joint training of speaker separation and speech recognit ion based on deep learning
Conggui Liu, Nakamasa Inoue, Koichi Shinoda
ASJ 2017 Autumn Meeting, pp. 63-64, Sep. 25, 2017
Speaker Separation in Multi-Channel Environment Using Deep Learning
Conggui Liu, Nakamasa Inoue, Koichi Shinoda
Technical Reports of IPSJ SLP, vol. 115, no. 11, pp. 1-6, Feb. 18, 2017
Invited Talks & Tutorials
Video Information Retrieval
Koichi Shinoda
The 2017 IEEE SPS Summer School on Visual Image Search and Visual Analytics (VISVA2017), Jul. 5, 2017
2016
Journal Papers
Experiments with Optical Properties of Skin on Fingers
Martin Drahansky, Ondrej Kanich, Eva Brezinova, Koichi Shinoda
International Journal of Optics and Applications, vol. 6, no. 2, pp. 37-46, Oct. 1, 2016
Semantic Indexing for Large-Scale Video Retrieval
Nakamasa Inoue, Koichi Shinoda
ITE Transactions on Media Technology and Applications, vol. 4, no. 3, pp. 209-217, Jul. 1, 2016
Wise Teachers Train Better DNN Acoustic Models
Ryan Price, Kenichi Iso, Koichi Shinoda
EURASIP Journal on Audio Speech and Music Processing, 10, pp. 1-19, Apr. 12, 2016
Conference Proceedings (peer reviewed)
Graph Regularized Implicit Pose for 3D Human Action Recognition
Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
Proc. APSIPA, pp. 155-159, Dec. 12, 2016
The NEC-TT Speaker Recognition System for NIST SRE16
Hitoshi Yamamoto, Koichi Shinoda
Proc. NIST SRE workshop, Dec. 11, 2016
Adaptation of Word Vectors using Tree Structure for Visual Semantics
Nakamasa Inoue, Koichi Shinoda
Proc. ACM Multimedia, pp. 277-281, Oct. 15, 2016
Recurrent Out-of-Vocabulary Word Detection Using Distribution of Features
Taichi Asami, Ryo Masumura, Yushi Aono, Koichi Shinoda
Proc. Interspeech, pp. 1320-1324, Sep. 10, 2016
Conference Proceedings (non-refereed)
TokyoTech at TRECVID 2016
Nakamasa Inoue, Ryosuke Yamamoto, Na Rong, Koichi Shinoda
Proc. TRECVID workshop, pp. 1-6, Nov. 14, 2016
Domestic Conference Proceedings
Concept Elimination for Zero-Shot Event Detection
Tran Hai Dang, Nakamasa Inoue, Koichi Shinoda
The 22nd Symposium on Sensing via Image Information (SSII), IS2-19, Jun. 9, 2016
Invited Talks & Tutorials
Video Semantic Indexing and Localization
Koichi Shinoda
5th Joint Meeting of the Acoustical Society of America and the Acoustical Society of Japan, vol. 140, no. 4, p. 3009, Nov. 28, 2016
Deep Learning for Speech, Image, and Video
Koichi Shinoda
International Conference on Computer, Control, Informatics, and Its Applications (IC3INA), Oct. 3, 2016
2015
Journal Papers
Error Correction Using Long Context Match for Smartphone Speech Recognition
Yuan Liang, Koji Iwano, Koichi Shinoda
IEICE Transactions on Information and Systems, vol. E98-D, no. 11, pp. 1932-1942, Nov. 1, 2015
Fast Coding of Feature Vectors using Neighbor-To-Neighbor Search
Nakamasa Inoue, Koichi Shinoda
IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), vol. 38, no. 6, pp. 1170-1184, Sep. 23, 2015
Robust Discriminative Training Against Data Insufficiency in PLDA-Based Speaker Verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Elsevier Computer Speech and Language, vol. 35, pp. 32-57, Jun. 20, 2015
Autonomous Selection of i-Vectors for PLDA Modelling in Speaker Verification
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
Elsevier Speech Communication, vol. 72, pp. 32-46, May 8, 2015
Conference Proceedings (peer reviewed)
Vocabulary Expansion Using Word Vectors for Video Semantic Indexing
Nakamasa Inoue, Koichi Shinoda
Proc. ACM Multimedia, pp. 851-854, Oct. 26, 2015
New Materials for Spoofing Touch-based Fingerprint Scanners
Jan Spurny, Michal Dolezel, Ondrej Kanich, Martin Drahansky, Koichi Shinoda
Proc. International Conference on Computer Application Technologies, pp. 207-211, Sep. 1, 2015
Speaker Diarization Using Multi-Modal i-vectors
Fumito Nishi, Nakamasa Inoue, Koichi Shinoda
Proc. International Technical Conference on Circuits/Systems Computers and Communications (ITC-CSCC), pp. 27-30, Jun. 29, 2015
Conference Proceedings (non-refereed)
TokyoTech at TRECVID 2015
Nakamasa Inoue, Tran Hai Dang, Ryosuke Yamamoto, Koichi Shinoda
Proc. TRECVID workshop, pp. 1-10, Nov. 16, 2015
Combining Audio Features and Visual i-vector at MediaEval 2015 Multimodal Person Discovery in Broadcast TV
Fumito Nishi, Nakamasa Inoue, Koichi Shinoda
Proc. MediaEval Workshop, Sep. 14, 2015
Domestic Conference Proceedings
A DNN-Based ASR System for the Indonesian Language
Devin Hoesen, Ryan Price, Puji Lestari Dessi, Koichi Shinoda
Proc. ASJ 2015 Autumn Meeting, pp. 5-6, Sep. 16, 2015
Human Action Retrieval Based on Temporal Matching
Mengxi Lin, Nakamasa Inoue, Koichi Shinoda
Technical Reports of IEICE PRMU, vol. 114, no. 454, pp. 125-130, Feb. 20, 2015
Spectral Graph Wavelets for Skeleton-based 3D Action Recognition
Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
Technical Reports of IEICE PRMU, vol. 114, no. 454, pp. 131-136, Feb. 19, 2015
Invited Talks & Tutorials
Robust Video Information Retrieval using Speech Technologies
Koichi Shinoda
Korea University, Jun. 30, 2015
A New Speech Recognition Paradigm Based on Deep Learning
Koichi Shinoda
University of Science, VNU-HCM, Jan. 15, 2015
Robust video information retrieval using speech technologies
Koichi Shinoda
University of Information Technology, VNU-HCM, Jan. 14, 2015
2014
Conference Proceedings (peer reviewed)
Speaker Adaptation of Deep Neural Networks Using a Hierarchy of Output Layers
Ryan Price, Kenichi Iso, Koichi Shinoda
Proc. Spoken Language Technology (SLT) Workshop, pp. 153-158, Dec. 7, 2014
An Efficient Error Correction Interface for Speech Recognition on Mobile Touchscreen Devices
Yuan Liang, Koji Iwano, Koichi Shinoda
Proc. Spoken Language Technology (SLT) Workshop, pp. 454-459, Dec. 7, 2014
n-Gram Models for Video Semantic Indexing
Nakamasa Inoue, Koichi Shinoda
Proc. ACM Multimedia (MM), pp. 777-780, Nov. 3, 2014
Spectral Graph Skeletons for 3D Action Recognition
Tommi Kerola, Nakamasa Inoue, Koichi Shinoda
Proc. Asian Conference on Computer Vision (ACCV), pp. 1-16, Nov. 1, 2014
Simple Gesture-based Error Correction Interface for Smartphone Speech Recognition
Yuan Liang, Koji Iwano, Koichi Shinoda
Proc. Interspeech, pp. 1194-1198, Sep. 16, 2014
Discriminative PLDA training with application-specific loss functions for speaker verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. Odyssey Workshop, pp. 26-32, Jun. 16, 2014
i-Vector Selection for Effective PLDA Modeling in Speaker Recognition
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
Proc. Odyssey Workshop, pp. 100-105, Jun. 16, 2014
Constrained Discriminative PLDA Training for Speaker Verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. International Conference on Acoustic Speech and Signal Processing (ICASSP), pp. 1689-1693, May 4, 2014
Event Detection by Velocity Pyramid
Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda
Proc. Multimedia Modeling (MMM), pp. 353-364, Jan. 6, 2014
Conference Proceedings (non-refereed)
TokyoTech-Waseda at TRECVID 2014
Nakamasa Inoue, Zhuolin Liang, Mengxi Lin, Tran Hai Dang, Koichi Shinoda, Zhang Xuefeng, Kazuya Ueki
Proc. TRECVID workshop, pp. 1-13, Nov. 9, 2014
Domestic Conference Proceedings
Error Correction Using Long Context Match for Smartphone Speech Recognition
Yuan Liang, Koji Iwano, Koichi Shinoda
Technical Reports of IPSJ SLP, vol. 104, no. 22, pp. 1-6, Dec. 16, 2014
An Efficient Error Correction Method for Smartphone Speech Recognition
Yuan Liang, Koji Iwano, Koichi Shinoda
Proc. ASJ 2014 Autumn Meeting, pp. 29-30, Sep. 5, 2014
Collection and analysis of multi-party interaction data for automatic boredom recognition
Nataliia Biriukova, Kotaro Funakoshi, Koichi Shinoda
Proc. The 28th Annual Conference of the Japanese Society for Artificial Intelligence (JSAI) 2014, pp. 1-4, May 13, 2014
Velocity Pyramid for Event Detection
Zhuolin Liang, Nakamasa Inoue, Koichi Shinoda
Technical Reports of IEICE PRMU, vol. 113, no. 493, pp. 13-18, Mar. 13, 2014
Discriminatively Trained PLDA with Partially Preserved Model Assumptions in Speaker Verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. ASJ 2014 Spring Meeting, pp. 99-100, Mar. 12, 2014
Training Multiple PLDA Models by Clustered I-Vectors for Speaker Verification
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
Proc. ASJ 2014 Spring Meeting, pp. 97-98, Mar. 12, 2014
Robust 0-1 Loss Training for PLDA in Speaker Verification
Johan Rohdin, Sangeeta Biswas, Koichi Shinoda
Proc. ASJ 2014 Spring Meeting, pp. 101-102, Mar. 12, 2014
Invited Talks & Tutorials
Robust Video Information Retrieval using Speech Technologies
Koichi Shinoda
Language Technologies Institute, Carnegie Mellon University, Jun. 20, 2014
Video Semantic Indexing Using Speech Technologies
Koichi Shinoda
Dublin City University, Jan. 6, 2014
Selected Talks
Semantics for Large-Scale Multimedia: New Challenges for NLP
Florian Metze, Koichi Shinoda
ACL2014, Jun. 22, 2014
2013
Journal Papers
q-Gaussian Mixture Models for Image and Video Semantic Indexing
Nakamasa Inoue, Koichi Shinoda
Journal of Visual Communication and Image Representation, vol. 24, no. 8, pp. 1450-1457, Nov. 15, 2013
Event detection in consumer videos using GMM supervectors and SVMs
Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda
EURASIP Journal on Image and Video Processing, vol. 2013:51, pp. 1-13, Sep. 2, 2013
A statistical approach for person verification using human behavioral patterns
Felipe Gomez-Caballero, Takahiro Shinozaki, Sadaoki Furui, Koichi Shinoda
EURASIP Journal on Image and Video Processing 2013, 2013:44, pp. 1-11, Aug., 2013
Detection of overlapped speech using lapel microphones in meeting
Ryo Yokoyama, Yu Nasu, Koji Iwano, Koichi Shinoda
Speech Communication, vol. 55, pp. 941-949, Jun. 27, 2013
Feature normalization based on non-extensive statistics for speech recognition
Hilman F. Pardede, Koji Iwano, Koichi Shinoda
Speech Communication, vol. 55, pp. 587-599, Mar., 2013
Conference Proceedings (peer reviewed)
Neighbor-To-Neighbor Search for Fast Coding of Feature Vectors
Nakamasa Inoue, Koichi Shinoda
2013 IEEE International Conference on Computer Vision, pp. 1233-1240, Dec. 3, 2013
Statistical Person Verification Using Behavioral Patterns from Complex Human Motion
Felipe Gomez-Caballero, Takahiro Shinozaki, Sadaoki Furui, Koichi Shinoda
New Trends in Image Analysis and Processing ICIAP 2013, pp. 550-558, Sep. 9, 2013
Combining Deep Speaker Specific Representations with GMM-SVM for Speaker Verification
Ryan Price, Sangeeta Biswas, Koichi Shinoda
INTERSPEECH2013, pp. 2788-2792, Aug. 25, 2013
Domestic Conference Proceedings
A Regression Approach to Emotion Estimation in Spontaneous Speech
Qiongqiong Wang, Koichi Shinoda
2013 Autumn Meeting ASJ, pp. 87-88, Sep. 25, 2013
Fusing deep speaker specific features and MFCC for robust speaker verification
Ryan Price, Koichi Shinoda, Sangeeta Biswas
IPSJ SIG technical reports, Vol. 2013-SLP-97, No. 3, pp. 1-7, Jul. 25, 2013
Speaker verication using deep speaker-discriminative representations
Ryan Price, Koichi Shinoda
2013 Spring Meeting ASJ, pp. 81-82, Mar. 13, 2013
Commentary and Review
Machine Learning for Multimedia Sequential Pattern Recognition
Koichi Shinoda, Jen-Tzung Chien
2013 APSIPA Tutorial #5, Oct. 29, 2013
What speech researchers should know about video technology!
Koichi Shinoda, Florian Metze
Tutorial at INTERSPEECH2013, Aug. 25, 2013
Reusing Speech Techniques for Video Semantic Indexing
Koichi Shinoda, Nakamasa Inoue
IEEE signal processing magazine, Vol. 30, No. 2, pp. 118-122, Mar., 2013
Invited Talks & Tutorials
TRECVideo Semantic Indexing
Koichi Shinoda
Yahoo! Japan Research, Nov. 25, 2013
Statistical Video Semantic Indexing
Koichi Shinoda
National Chiao Tung University (國立交通大学), Oct. 27, 2013
2012
Journal Papers
Online speaker clustering using incremental learning of an ergodic hidden Markov model
Takafumi Koshinaka, Kentaro Nagatomo, Koichi Shinoda
IEICE TRANS. INF. & SYST, Vol. E95-D, No. 10, pp. 2469-2478, Oct., 2012
Active Learning Using Phone-Error Distribution for Speech Modeling
Hiroko MURAKAMI, Koichi SHINODA, Sadaoki FURUI
IEICE TRANS. INF. & SYST, Vol. E95-D, No. 10, pp. 2486-2494, Oct., 2012
A Fast and Accurate Video Semantic-Indexing System Using Fast MAP Adaptation and GMM Supervectors
Nakamasa Inoue, Koichi Shinoda
IEEE Transactions on Multimedia, vol. 14, Issue: 4 Part 2, pp. 1196-1205, Aug., 2012
Robust Gait-Based Person Identification against Walking Speed Variations
Muhammad Rasyid AQMAR, Koichi SHINODA, Sadaoki FURUI
IEICE Trans. Inf. & Syst, Vol. E95-D, No. 2, pp. 668-676, Feb. 1, 2012
Conference Proceedings (peer reviewed)
Acoustic Model Training Using Committee-Based Active and Semi-Supervised Learning for Speech Recognition
Tsutaoka Takuya, Koichi Shinoda
APSIPA ASC 2012, Dec. 4, 2012
Efficient model training for HMM-based person identification by gait
Muhammad Rasyid Aqmar, Koichi Shinoda, Sadaoki Furui
Proceedings of 2012 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference, Dec., 2012
q-Gaussian Mixture Models Based on Non-Extensive Statistics for Image And Video Semantic Indexing
Nakamasa Inoue, Koichi Shinoda
ACCV2012, Nov. 5, 2012
MULTIMEDIA EVENT DETECTION USING GMM SUPERVECTORS AND SVMS
Yusuke Kamishima, Nakamasa Inoue, Koichi Shinoda, Shunsuke Sato
ICIP 2012, pp. 3089-3092, Oct. 3, 2012
Overlapped Speech Detection in Meeting Using Cross-Channel Spectral Subtraction and Spectrum Similarity
Ryo Yokoyama, Yu Nasu, Koichi Shinoda, Koji Iwano
InterSpeech2012, Sep. 12, 2012
Q-Gaussian based spectral subtraction for robust speech recognition
Hilman F. Pardede, Koichi Shinoda, Koji Iwano
InterSpeech2012, Sep. 11, 2012
Non-extensive Statistics for Feature Normalization in Speech Recognition
Hilman F. Pardede, Koichi Shinoda
Proc. International Workshop on Statistical Machine Learning for Speech Processing (IWSML) 2012, Mar., 2012
Conference Proceedings (non-refereed)
Tokyo Tech Speaker Recognition
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda
NIST SRE 2012, Dec. 11, 2012
TokyoTechCanon at TRECVID 2012
Nakamasa Inoue, Yusuke Kamishima, Kotaro Mori, Koichi Shinoda
TRECVID 2012, Nov. 26, 2012
Domestic Conference Proceedings
Video Semantic Indexing Using GMM-Supervectors
Nakamasa Inoue, Koichi Shinoda
Greater Tokyo Area Multimedia/Vision Workshop, Aug. 30, 2012
A video watermarking method to objects robust against various attacks
Ta Minh THANH, Koichi SHINODA
IEICE Technical Report, Vol. 112, No. 190, pp. 43-48, Aug. 27, 2012
Multimodal Interface for Error Correction in Speech Recognition
Koichi Shinoda
Microsoft Research Asia IJARC CORE7 Project Summary Booklet, pp. 15-16, Jun. 29, 2012
Speaker Adaptation for Dialog Act Recognition
Johan Rohdin, Koichi Shinoda
2012 Spring Meeting ASJ, p. 111, Mar. 21, 2012
MAP Adaptation Using Multiple Priors for Speaker Verication
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda, Sadaoki Furui
2012 Spring Meeting ASJ, pp. 79-82, Mar. 19, 2012
A Compensation Technique Using q-Logarithm for Noisy Speech Recognition
Hilman F. Pardede, Koichi Shinoda, Koji Iwano
2012 Spring Meeting ASJ, pp. 19-20, Mar. 19, 2012
Spectral Subtraction Based on q-Gaussian Assumption for Noise Robust Speech Recognition
Hilman F. Pardede, Koichi Shinoda, Koji Iwano
2012 Spring Meeting ASJ, pp. 21-22, Mar. 19, 2012
Recognition of Indonesian Code-Switching Speech
Yonatan Andy Fajar Nugraha, Koichi Shinoda, Sadaoki Furui, Koji Iwano
2012 Spring Meeting ASJ, pp. 75-76, Mar., 2012
Language Model for Efficient Error Correction in Speech Recognition
Yuan Liang, Koichi Shinoda, Sadaoki Furui
2012 Spring Meeting ASJ, pp. 89-90, Mar., 2012
Subject adaptation and adaptive training for gait-based person identification
Muhammad Rasyid Aqmar, Koichi Shinoda, Sadaoki Furui
IEICE Technical Report, No. PRMU2011-199, pp. 77-82, Feb., 2012
Two-pass approach for recognizing code-switching speech
Yonatan Andy Fajar Nugraha, Koichi Shinoda, Sadaoki Furui
IEICE Technical Report, No. SP2011-150, pp. 225-229, Feb., 2012
Keynote Talks
Speech Technology Plays a Key Role in Video Semantic Indexing
Koichi Shinoda
First International Workshop on Audio and Multimedia Methods for Large-Scale Video Analysis (AMVA) at ACM Multimedia 2012, pp. 1-2, Oct. 29, 2012
Invited Talks & Tutorials
Mobile or Cloud-based Photo/Video Analytics?
Winston Hsu, Kunio Kashino, Keiichiro Hoashi, Koichi Shinoda, Duy-Dinh Le, Masanori Sugimoto
Greater Tokyo Area Multimedia/Vision Workshop, Aug. 30, 2012
2011
Journal Papers
Committee-Based Active Learning for Speech Recognition
yuzo hamanaka, Koichi Shinoda, Takuya Tsutaoka, SADAOKI FURUI, Tadashi Emori, Takafumi KOSHINAKA
IEICE Trans. Inf. & Syst, vol. E94-D, No. 10, pp. 2015-2023, Oct. 1, 2011
Semi-synchronous speech and pen input for mobile user interfaces
Koichi Shinoda, Yasushi Watanabe, Kenji Iwata, Yuan Liang, Ryuta Nakagawa, Sadaoki Furui
Speech Communication, Vol. 53, pp. 283-291, Mar., 2011
Conference Proceedings (peer reviewed)
Designing text corpus using phone-error distribution for acoustic modeling
Hiroko Murakami, Koichi Shinoda, Sadaoki Furui
Proc. IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) 2011, pp. 191-195, Dec. 11, 2011
Person Authentication using 3D Human Motion
Felipe Gomez-Caballero, Takahiro Shinozaki, Sadaoki Furui, Koichi Shinoda
Proc. Joint ACM Workshop on Human Gesture and Behavior Understanding 2011 (J-HGBU '11), pp. 35-40, Nov. 28, 2011
A Fast MAP Adaptation Technique for GMM-supervector-based Video Semantic Indexing Systems
Nakamasa Inoue, Koichi Shinoda
Proc. ACM Multimedia 2011, pp. 1357-1360, Nov. 28, 2011
Noise Robust Speech Recognition based on Spectral Reduction Measure
Mayumi Beppu, Koichi Shinoda, Sadaoki Furui
Proc. APSIPA ASC 2011, No. PM.PS2, Oct. 18, 2011
Acoustic Forest for SMAP-based Speaker Verification
SANGEETA BISWAS, Marc Ferras, Koichi Shinoda, SADAOKI FURUI
Proc. INTERSPEECH2011, pp. 2377-2380, Aug. 27, 2011
Structual Joint Factor Analysis for Speaker Recognition
Marc Ferras, Koichi Shinoda, SADAOKI FURUI
Proc. INTERSPEECH2011, pp. 2373-2376, Aug. 27, 2011
Generalized-Log Spectral Mean Normalization for Speech Recognition
Hilman Pardede, Koichi Shinoda
INTERSPEECH, pp. 1645-1648, Aug. 27, 2011
Structual MAP adaption in GMM-supervector based speaker recognition
Marc Ferras, Koichi Shinoda, Sadaoki Furui
Proc. ICASSP2011, pp. 5432-5435, May 22, 2011
Cross-channel spectral subtraction for meeting speech recognition
Yu Nasu, Koichi Shinoda, Sadaoki Furui
Proc. ICASSP2011, pp. 4812-4815, May 22, 2011
Conference Proceedings (non-refereed)
TokyoTech+Canon at TRECVID 2011
Nakamasa Inoue, Yusuke Kamishima, Toshiya Wada, Koichi Shinoda, Shunsuke Sato
Proc.TRECVID Workshop 2011, Dec. 5, 2011
Multimodal Interface for Error Correction in Speech Recognition
Koichi Shinoda
Microsoft Research Asia IJARC CORE6 Project Summary Booklet, Jun. 13, 2011
Domestic Conference Proceedings
Speaker verification using MMAP adaptation
Sangeeta Biswas, Johan Rohdin, Koichi Shinoda, Sadaoki Furui
IEICE Technical Report, No. SP2011-93, pp. 133-137, Dec., 2011
Speaker Adaptation for Dialogue Act Classification
Johan Rohdin, Koichi Shinoda
IPSJ SIG Technical Report, Vol. 2011-SLP-87, No. 8, Jul. 21, 2011
Nonlinear Normalization Using q-Logarithm for Robust Speech Recognition
Hilman, Koichi Shinoda, Koji IWANO
IEICE Technical Report, Vol. 111, No. 153, pp. 45-50, Jul. 21, 2011
Voting Approach in SMAP Adaptation for Speaker Verification
Sangeeta Biswas, Marc Ferras, Koichi Shinoda, Sadaoki Furui
, No. 2-5-2, pp. 45-48, Mar., 2011
Invited Talks & Tutorials
Speaker Adaptation Techniques for Automatic Speech Recognition
Koichi Shinoda
Proc. APSIPA ASC 2011, Oct., 2011
Books
Robust speech recognition in the car environment
Agnieszka Betkowska Cavalcante, Koichi Shinoda, Sadaoki Furui
LTC 2009, LNAI 6562, pp. 24-34, Jul. 11, 2011
2010
Journal Papers
(Invited Paper) Acoustic Model Adaptation for Speech Recognition
Koichi Shinoda
IEICE Transactions on Information and Systems, vol. E93-D, no. 9, pp. 2348-2362, Sep., 2010
Conference Proceedings (peer reviewed)
Dynamic Language Model Adaptation Using Keyword Category Classification
Hitoshi Yamamoto, Ken Hanazawa, Kiyokazu Miki, Koichi Shinoda
Proc. Interspeech 2010, pp. 2426-2429, Sep. 27, 2010
Robust Gait Recognition against Speed Variation
Muhammad Rasyid Aqmar, Koichi Shinoda, Sadaoki Furui
Proc. ICPR2010, pp. 2190-2193, Aug., 2010
High-Level Feature Extraction Using SIFT GMMs and Audio Models
Nakamasa Inoue, Tatsuhiko Saito, Koichi Shinoda, Sadaoki Furui
Proc. ICPR2010, pp. 3220-3223, Aug., 2010
Speech Modeling Based on Committee-Based Active Learning
Yuzo Hamanaka, Koichi Shinoda, Sadaoki Furui, Tadashi Emori, Takafumi Koshinaka
Proc. ICASP2010, pp. 4350-4353, Mar., 2010
Conference Proceedings (non-refereed)
TT+GT at TRECVID 2010 Workshop
Nakamasa Inoue, Toshiya Wada, Yusuke Kamishima, Koichi Shinoda, Ilseo Kim, Byungki Byun, Chin-Hui Lee
Proc. TRECVID Workshop 2010, Nov. 15, 2010
NIST SRE 2010:Tokyo Tech Speaker Recognition
Marc Ferras, Sangeeta Biswas, Koichi Shinoda, Sadaoki Furui
Proc. NIST 2010 Speaker Recognition Evaluation Workshop, Jun., 2010
Domestic Conference Proceedings
Optimal use of trees in structural MAP adaptation for speaker verification
Sangeeta Biswas, Marc Ferras, Koichi Shinoda, Sadaoki Furui
IPSJ Technical Report, Vol. 2010-SLP-84, No. 26, pp. 1-5, Dec., 2010
Inter-speaker weighted MAP adaptation for GMM-supervector speaker recognition
Marc Ferras, Koichi Shinoda, Sadaoki Furui
IPSJ Technical Report, Vol. 2010-SLP-84, No. 12, pp. 1-4, Dec., 2010
Gait-based Person Identification Robust against Speed Variation using CHLAC features and HMMs
Muhammad Rasyid Aqmar, Koichi Shinoda, Sadaoki Furui
, Vol. PRMU2010-92, SP2010-48, WIT2010-36, pp. 23-28, Oct., 2010
2009
Journal Papers
Automatic recognition of Indonesian declarative questions and statements using polynomial coefficients of the pitch contours
Nazrul Effendy, Koichi Shinoda, Sadaoki Furui, Somchai Jitapunkul
The Acoustical Society of Japan, Accoust. Sci. & Tech., No. 30, pp. 249-256, Apr., 2009
Conference Proceedings (peer reviewed)
Robust Speech Recognition In The Car Environment
Agnieszka Betkowska Cavalcante, Koichi Shinoda, Sadaoki Furui
the 4th Language and Technology Conference (LTC'09), pp. 39-43, Nov., 2009
Noise robust speech recognition using spectral subtraction and F0 information extracted by Hough transform
Hideki Yasui, Koichi Shinoda, Sadaoki Furui, Koji Iwano
Proc. Asia-Pacific Signal and Information Processing Association 2009 Annual Summit and Conference (APSIPA-ASC '09), pp. 631-634, Oct., 2009
Speaker Adaptation Based on Two-Step Active Learning
Koichi Shinoda, Hiroko Murakami, Sadaoki Furui
Proc. INTERSPEECH 2009, pp. 576-579, Sep., 2009
Online speaker clustering using incremental learning of an ergodic hidden markov model
Takafumi Koshinaka, Kentaro Nagatomo, Koichi Shinoda
Proc. ICASSP 2009, pp. 4093-4096, Apr., 2009
Independent component analysis for noisy speech recognition
Hsin-Lung Hsieh, Jen-Tzung Chien, Koichi Shinoda, Sadaoki Furui
Proc. ICASSP 2009, pp. 4369-4372, Apr., 2009
Conference Proceedings (non-refereed)
TITGT at TRECVID 2009 Workshop
Nakamasa Inoue, Shanshan Hao, Tatsuhiko Saito, Koichi Shinoda, Ilseo Kim, Chin-Hui Lee
Proc. TRECVID Workshop (TRECVID 2009), Nov., 2009
Multimedia Information Retrieval Using Statistical Approach
Koichi Shinoda
Microsoft Research Asia 2009 Annual Workshop of IJARC, pp. 13, Jul. 14, 2009
Domestic Conference Proceedings
Gait Recognition Using CHLAC Features and Hidden Markov Model
MUHAMMAD RASYID, Koichi Shinoda, SADAOKI FURUI
IEICT Tachnical Report, Vol. PRUM2008-224, pp. 99-103, Feb., 2009
2008
Conference Proceedings (peer reviewed)
Automatically Estimating Number of Scenes for Rushes Summarization
Koji Yamasaki, Koichi Shinoda, Sadaoki Furui
Proc. TRECVID BBC Rushes Summarization Workshop (TVS 2008) at ACM Multimedia, pp. 129-133, Oct., 2008
Time-lag Adaptation for Semi-synchronous Speech and Pen Input
Yasushi Watanabe, Koichi Shinoda, SADAOKI FURUI
Proc. INTERSPEECH2008, pp. 2675-2678, Sep., 2008
Improvement of eigenvoice-based speaker adaptation by parameter space clustering
Shutaro Tanji, Koichi Shinoda, SADAOKI FURUI, Antonio Ortega
Proc. INTERSPEECH2008, pp. 1229-1232, Sep., 2008
Robust spoken term detection using combination of phone-based and word-based recognition
Kenji Iwata, Koichi Shinoda, SADAOKI FURUI
Proc. INTERSPEECH2008, pp. 2195-2198, Sep., 2008
Conference Proceedings (non-refereed)
Tokyo Tech at TRECVID 2008
Shanshan Hao, Yusuke Yoshizawa, Koji Yamasaki, Koichi Shinoda, Sadaoki Furui
Proc. TRECVID Workshop (TRECVID 2008), Nov., 2008
Automatic score Scene Detection for Baseball Video
Koichi Shinoda, Kazuki Ishihara, Sadaoki Furui, Takahiro Mochizuki
Symposium on Large-Scale Knowledge Resources(LKR2008), pp. 226-240, Mar., 2008
Domestic Conference Proceedings
Initial Evaluation of the Drivers' Japanese Speech Corpus in a Car Environment
Kousuke Hiraki, Takahiro Shinozaki, Koji Iwano, Agnieszka Betkowska, Betkowska Agnieszka, Koichi Shinoda, SADAOKI FURUI
, Vol. SP2007-202, pp. 93-98, Mar., 2008
2007
Journal Papers
Robust Speech Recognition Using Factorial HMMs for Home Environments
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
EURASIP Journal on Advances in Signal Processing, Vol. 2007, No. 20593, May, 2007
Conference Proceedings (peer reviewed)
Home-Environment Adaptation of Phoneme Factorial Hidden Markov Models
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
Proc. EUSIPCO 2007, pp. 2380-2384, Sep., 2007
Dynamic Language Model Adaptation Using Presentation Slides for Lecture Speech Recognition
Hiroki Yamazaki, Koji Iwano, Koichi Shinoda, SADAOKI FURUI, Haruo Yokota
Proc. INTERSPEECH 2007, pp. 2349-2352, Aug., 2007
Predictive Minimum Bayes Risk Classification for Robust Speech Recognition
Jen-Tzung Chien, Koichi Shinoda, SADAOKI FURUI
Proc. INTERSPEECH2007, pp. 1062-1065, Aug., 2007
Automatic Estimation of Scaling Factors Among Probabilistic Models in Speech Recognition
Tadashi Emori, Yoshifumi Onishi, Koichi Shinoda
Proc. INTERSPEECH 2007, pp. 1453-1456, Aug., 2007
A Robust Scene Recognition System for Baseball Broadcast Using Date-Driven Approach
Ryoichi Ando, Koichi Shinoda, SADAOKI FURUI, Takahiro Mochizuki
Proc. CIVR2007, pp. 186-193, Jul., 2007
Semi-Synchronous Speech and Pen Input
Yasushi Watanabe, Kenji Iwata, Ryuta Nakagawa, Koichi Shinoda, SADAOKI FURUI
Proc. ICASSP 2007, pp. I-409-412, Apr., 2007
Speech Recognition Using FHMMs Robust against Nonstationary Noise
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
Proc. ICASSP 2007, pp. I-1029-1032, Apr., 2007
Conference Proceedings (non-refereed)
An Interface Using Semi-synchronous Speech and Pen Input
Koichi Shinoda
Proc. IJARC(Microsoft)-Tokyo Institute of Technology Joint Symposium on The forefront of the Speech Recognition Research, Dec., 2007
TokyoTech's TRECVIC2007 Notebook
Taichi Nakamura, Koichi Shinoda, Sadaoki Furui
Proc. TRECVID 2007 Workshop, Nov., 2007
Comparative Study on Robust Speech Recognition against Nonstationary Noise in the Home Environment
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
Proc. Symposium on Large-Scale Knowledge Resources(LKR2007), pp. 175-178, Mar., 2007
Robust Scene Recognition Using Scene Context Information for Video Contents
Koichi Shinoda, Ryoichi Ando, Sadaoki Furui, Takahiro Mochizuki
Proc. International Symposium on Large-Scale Knowledge Resources(LKR2007), pp. 107-112, Mar., 2007
Presentation Scene Retrieval Exploiting Features in Videos Including Pointing and Speech Information
Takashi Kobayashi, Wataru Nakano, Haruo Yokota, Koichi Shinoda, Sadaoki Furui
Proc. Symposium on Large-Scale Knowledge Resources(LKR2007)., pp. 95-100, Mar., 2007
2006
Journal Papers
Robust Scene Extraction Using Multi-Stream HMMs for Baseball Broadcast
Nguyen Huu Bach, Koichi Shinoda, Sadaoki Furui
IEICE Transactions on Information and Systems, Vol. E89-D, No. 9, pp. 2553-2561, Sep., 2006
Conference Proceedings (peer reviewed)
Robust scene Recognition Using Language Models for Scene Contexts
Ryoichi Ando, Koichi Shinoda, Sadaoki Furui, Takahiro Mochizuki
Proc. MIR2006, ACM Workshop2006, pp. 99-106, Oct., 2006
Towards Optimal Bayes Decision for Speech Recognition
Jen-Tzung Chien, Chin-Hsien Huang, Koichi Shinoda, Sadaoki Furui
Proc. ICASSP2006, pp. SLP-L2.6, May, 2006
Conference Proceedings (non-refereed)
Multimedia Information Retrieval Using Pattern Recognition Techniques
Koichi Shinoda
Proc. Microsoft Research Asia IJARC 2nd Symposium, Nov., 2006
Tokyo Tech's TRECVID2006 Notebook
Taichi Nakamura, Yuichi Miyamura, Koichi Shinoda, Sadaoki Furui
Proc. TRECVID Workshops, Nov., 2006
FHMM for Robust Speech Recognition in Home Environment
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
Proc. International Symposium on Large-Scale Knowledge Resources (LKR), pp. 129-132, Mar., 2006
Robust Scene Recognition for Baseball Broadcast
Koichi Shinoda, Sadaoki Furui
Proc. International Symposium on Large-Scale Knowledge Resources (LKR), pp. 91-94, Mar., 2006
Domestic Conference Proceedings
Family Adaptation of Factorial HMMs for Personal Robots
Betkowska Agnieszka, Koichi Shinoda, Sadaoki Furui
日本音響学会 2006年春季講演, pp. 135-136, Mar., 2006
2005
Conference Proceedings (peer reviewed)
Robust highlight extraction using multi-stream Hidden Markov Models for baseball video
Koichi Shinoda, Sadaoki Furui, Nguen Huu Bach
Proc. International Conference on Image Processing 2005 (ICIP 2005), pp. III-173-176, Sep., 2005
Conference Proceedings (non-refereed)
Scene recognition using Hidden Markov Models for video database
Koichi Shinoda, Nguyen Huu Bach, Sadaoki Furui, Naoki Kawai
Proc. Symposium on Large-Scale Knowledge Resources(LKR2005), pp. 107-110, Mar., 2005
Model optimization for noise discrimination in home environment
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
Proc. Symposium on Large-Scale Knowledge Resources (LKR2005), pp. 167-170, Mar., 2005
Domestic Conference Proceedings
Recognition of speech in non-stationary noise using Factorial HMMs
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
, No. 3-7-25, pp. 151-152, Sep., 2005
Noise discrimination using models with different structures
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
, No. 2-Q-7, pp. 111-112, Mar., 2005
Books
Speech Recognition System in NEC
Takao Watanabe, Kaichiro Hatazaki, Ken-ichi Iso, Ryosuke Isotani, Koichi Shinoda, Keizaburo Takagi
Spoken Language Systems, pp. 34-46, Sep., 2005
Speech Recognition System in NEC
Koichi Shinoda
Spoken Language Systems, Dec., 2005
2004
Domestic Conference Proceedings
A study of noise discrimination for personal robots
Agnieszka Betkowska, Koichi Shinoda, Sadaoki Furui
, No. 1-1-6, pp. 11-12, Sep., 2004
Invited Talks & Tutorials
Robust Acoustic Modeling for Speech Recognition
Koichi Shinoda
Proc. International Workshop Beyond HMM, Vol. SP2004-82, pp. 7-12, Dec., 2004