• Context-Aware Action Recognition: Introducing a Comprehensive Dataset for Behavior Contrast
  Tatsuya Sasaki, Yoshiki Ito, Satoshi Kondo
  ECCV 2024
  [Paper][bibtex]
• Stream-based Active Learning for Streaming Anomalous Sound Detection in Machine Condition Monitoring
  Tuan Vu Ho, Kota Dohi, Yohei Kawaguchi
  INTERSPEECH 2024
  [bibtex]
• Distributed Collaborative Anomalous Sound Detection by Embedding Sharing
  Kota Dohi, Yohei Kawaguchi
  EUSIPCO 2024
  [Paper][bibtex]
• TREE-BASED APPROACH FOR VEGETATION MONITORING AND RISK ASSESSMENT ALONG POWERLINE USING HIGH RESOLUTION SATELLITE IMAGE
  Ching Man Yung, Yu Zhao, Tomonori Yamamoto, Koichiro Yawata, Shinji Matsuda, Norihiko Moriwaki
  IGARSS 2024
  [bibtex]
• Streaming Active Learning for Regression Problems Using Regression via Classification
  Shota Horiguchi, Kota Dohi, Yohei Kawaguchi
  ICASSP 2024
  [Paper][bibtex]
• CHICOT: A Developer-Assistance Toolkit for Code Search with High-Level Contextual Information
  Terufumi Morishita, Yuta Koreeda, Atsuki Yamaguchi, Gaku Morio, Osamu Imaichi, Yasuhiro Sogawa
  AAAI 2024 (demo)
  [bibtex]
• MILA: Memory-Based Instance-Level Adaptation for Cross-Domain Object Detection
  Onkar Krishna, Hiroki Ohashi, Saptarshi Sinha
  BMVC 2023
  [Paper][bibtex]
• Synthetic Data Augmentation for ASR with Domain Filtering
  Tuan Vu Ho, Shota Horiguchi, Shinji Watanabe, Paola Garcia, Takashi Sumiyoshi
  APSIPA ASC 2023
  [bibtex]
• LARCH: Large Language Model-based Automatic Readme Creation with Heuristics
  Yuta Koreeda, Terufumi Morishita, Osamu Imaichi, Yasuhiro Sogawa
  CIKM 2023
  [Paper][bibtex][Project]
• HOKEM: Human and Object Keypoint-based Extension Module for Human-Object Interaction Detection
  Yoshiki Ito
  ICIP 2023
  [Paper][bibtex]
• How Does the Task Complexity of Masked Pretraining Objectives Affect Downstream Performance?
  Atsuki Yamaguchi, Hiroaki Ozaki, Terufumi Morishita, Gaku Morio, Yasuhiro Sogawa
  ACL 2023 (Findings)
  [bibtex]
• How do different tokenizers perform on downstream tasks in scriptio continua languages?: A case study in Japanese
  Takuro Fujii, Koki Shibata, Atsuki Yamaguchi, Terufumi Morishita, Yasuhiro Sogawa
  ACL Student Research Workshop 2023
  [Paper][bibtex]
• Controling Keywords and Their Positions in Text Generation
  Yuichi Sasazawa, Terufumi Morishita, Hiroaki Ozaki, Osamu Imaichi, Yasuhiro Sogawa
  INLG 2023
  [Paper][bibtex]
• Hitachi at SemEval-2023 Task 3: Exploring Cross-lingual Multi-task Strategies for Genre and Framing Detection in Online News
  Yuta Koreeda*, Ken-ichi Yokote*, Hiroaki Ozaki, Atsuki Yamaguchi, Masaya Tsunokake, Yasuhiro Sogawa
  *Equal contribution
  SemEval 2023
  [Paper][bibtex]
• Hitachi at SemEval-2023 Task 4: Exploring Various Task Formulations Reveals the Importance of Description Texts on Human Values
  Masaya Tsunokake, Atsuki Yamaguchi, Yuta Koreeda, Hiroaki Ozaki, Yasuhiro Sogawa
  SemEval 2023
  [Paper][bibtex]
• CAPTDURE: Captioned Sound Dataset of Individual Sources
  Yuki Okamoto, Kanta Shimonishi, Keisuke Imoto, Kota Dohi, Shota Horiguchi, Yohei Kawaguchi
  INTERSPEECH 2023
  [Paper][bibtex]
• Anomalous Sound Detection Based on Sound Separation
  Kanta Shimonishi, Kota Dohi, Yohei Kawaguchi
  INTERSPEECH 2023
  [Paper][bibtex]
• Spoofing Attacker Also Benefits from Self-Supervised Pretrained Model
  Aoi Ito*, Shota Horiguchi*
  *Equal contribution
  INTERSPEECH 2023
  [Paper][bibtex]
• Learning Deductive Reasoning from Synthetic Corpus based on Formal Logic
  Terufumi Morishita, Gaku Morio, Atsuki Yamaguchi, Yasuhiro Sogawa
  ICML 2023
  [bibtex]
• Weakly-supervised crack detection
  Yuki Inoue, Hiroto Nagayoshi
  IEEE Transactions on Intelligent Transportation Systems, 2023
  [Paper][bibtex]
• Zero-Shot Domain Adaptation of Anomalous Samples for Semi-Supervised Anomaly Detection
  Tomoya Nishida, Takashi Endo, Yohei Kawaguchi
  ICASSP 2023
  [Paper][bibtex]
• Explanation Framework for Optimization-Based Scheduling: Evaluating Contributions of Constraints and Parameters by Shapley Values
  Yuta Tsuchiya, Masaki Hamamoto
  ICAPS 2023
  [Paper][bibtex]
• Mutual Learning of Single- and Multi-Channel End-to-End Neural Diarization
  Shota Horiguchi, Yuki Takashima, Shinji Watanabe, Paola Garcia
  SLT 2022
  [Paper][bibtex]
• Difficulty-Net: Learning to Predict Difficulty for Long-Tailed Recognition
  Saptarshi Sinha, Hiroki Ohashi
  WACV 2023
  [Paper][bibtex][Project]
• Online Neural Diarization of Unlimited Numbers of Speakers
  Shota Horiguchi, Shinji Watanabe, Paola Garcia, Yuki Takashima, Yohei Kawaguchi
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2023
  [Paper][bibtex]
• QUBO-inspired Molecular Fingerprint for Chemical Property Prediction
  Koichiro Yawata, Yoshihiro Osakabe, Takuya Okuyama, Akinori Asahara
  IEEE BigData 2022
  [Paper][bibtex]
• Prompter: Utilizing large language model prompting for a data efficient embodied instruction following
  Yuki Inoue, Hiroki Ohashi
  arXiv 2022
  [Paper][bibtex][Project]
• Description and Discussion on DCASE 2022 Challenge Task 2: Unsupervised Anomalous Sound Detection for Machine Condition Monitoring Applying Domain Generalization Techniques
  Kota Dohi, Keisuke Imoto, Noboru Harada, Daisuke Niizumi, Yuma Koizumi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi
  DCASE 2022
  [Paper][bibtex]
• MIMII DG: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection for Domain Generalization Task
  Kota Dohi, Tomoya Nishida, Harsh Purohit, Ryo Tanabe, Takashi Endo, Masaaki Yamamoto, Yuki Nikaido, Yohei Kawaguchi
  DCASE 2022
  [Paper][bibtex]
• Hunting Group Clues with Transformers for Social Group Activity Recognition
  Masato Tamura, Rahul Vishwakarma, Ravigopal Vennelakanti
  ECCV 2022
  [Paper][bibtex]
• Efficient and Accurate Skeleton-Based Two-Person Interaction Recognition Using Inter-and Intra-body Graphs
  Yoshiki Ito, Quan Kong, Kenichi Morita, Tomoaki Yoshinaga
  ICIP 2022
  [Paper][bibtex]
• Updating Only Encoders Prevents Catastrophic Forgetting of End-to-End ASR Models
  Yuki Takashima, Shota Horiguchi, Shinji Watanabe, Paola Garcia, Yohei Kawaguchi
  INTERSPEECH 2022
  [Paper][bibtex]
• Reducing Offensive Replies in Open Domain Dialogue System
  Naokazu Uchida, Takeshi Homma, Makoto Iwayama, Yasuhiro Sogawa
  INTERSPEECH 2022
  [Paper][bibtex]
• Unsupervised Domain Adaptation on Question-Answering System with Conversation Data
  Amalia Istiqlali Adiba, Takeshi Homma, Yasuhiro Sogawa
  SIGDIAL 2022
  [Paper][bibtex]
• Anomalous Sound Detection Based on Machine Activity Detection
  Tomoya Nishida, Kota Dohi, Takashi Endo, Masaaki Yamamoto, Yohei Kawaguchi
  EUSIPCO 2022
  [Paper][bibtex]
• Disentangling Physical Parameters for Anomalous Sound Detection Under Domain Shifts
  Kota Dohi, Takashi Endo, Yohei Kawaguchi
  EUSIPCO 2022
  [Paper][bibtex]
• Hierarchical Conditional Variational Autoencoder Based Acoustic Anomaly Detection
  Harsh Purohit, Masaaki Yamamoto, Takashi Endo, Yohei Kawaguchi
  EUSIPCO 2022
  [Paper][bibtex]
• Class-Difficulty Based Methods for Long-Tailed Visual Recognition
  Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura
  International Journal of Computer Vision (IJCV) 2022
  [Paper][bibtex][Project]
• Rethinking Fano's Inequality in Ensemble Learning
  Terufumi Morishita, Gaku Morio, Shota Horiguchi, Hiroaki Ozaki, Nobuo Nukaga
  ICML 2022
  [Paper][bibtex]
• Hierarchical Contrastive Adaptation for Cross-Domain Object Detection
  Ziwei Deng, Quan Kong, Naoto Akira, Tomoaki Yoshinaga
  Machine Vision and Applications, 2022
  [Paper][bibtex]
• Improving the Naturalness of Simulated Conversations for End-to-End Neural Diarization
  Natsuo Yamashita, Shota Horiguchi, Takeshi Homma
  Odyssey 2022
  [Paper][bibtex]
• Multi-Channel End-to-End Neural Diarization with Distributed Microphones
  Shota Horiguchi, Yuki Takashima, Paola Garcia, Shinji Watanabe, Yohei Kawaguchi
  ICASSP 2022
  [Paper][bibtex]
• Environmental Sound Extraction Using Onomatopoeic Words
  Yuki Okamoto, Shota Horiguchi, Masaaki Yamamoto, Keisuke Imoto, Yohei Kawaguchi
  ICASSP 2022
  [Paper][bibtex]
• End-to-end Argument Mining with Cross-corpora Multi-task Learning
  Gaku Morio, Hiroaki Ozaki, Terufumi Morishita, Kohsuke Yanai
  Transactions of the Association for Computational Linguistics, 2022
  [Paper][bibtex]
• Encoder-Decoder Based Attractors for End-to-End Neural Diarization
  Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Paola Garcia
  IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2022
  [Paper][bibtex]
• Towards Neural Diarization for Unlimited Numbers of Speakers Using Global and Local Attractors
  Shota Horiguchi, Shinji Watanabe, Paola Garcia, Yawen Xue, Yuki Takashima, Yohei Kawaguchi
  ASRU 2021
  [Paper][bibtex]
• Description and Discussion on DCASE 2021 Challenge Task 2
  Yohei Kawaguchi, Keisuke Imoto, Yuma Koizumi, Noboru Harada, Daisuke Niizumi, Kota Dohi, Ryo Tanabe, Harsh Purohit, Takashi Endo
  DCASE 2021
  [Paper][bibtex]
• Capturing Logical Structure of Visually Structured Documents with Multimodal Transition Parser
  Yuta Koreeda, Christopher D. Manning
  Natural Legal Language Processing Workshop 2021
  [Paper][bibtex][Project]
• ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts
  Yuta Koreeda, Christopher D. Manning
  Findings of the Association for Computational Linguistics: EMNLP 2021
  [Paper][bibtex][Dataset]
• Human-error-potential Estimation based on Wearable Biometric Sensors
  Hiroki Ohashi, Hiroto Nagayoshi
  KDIR 2021
  [Paper][bibtex]
• Sensor-Augmented Egocentric-Video Captioning with Dynamic Modal-Attention
  Katsuyuki Nakamura, Hiroki Ohashi, Mitsuhiro Okada
  ACMMM 2021
  [Paper][bibtex][Project]
• MIMII DUE: Sound Dataset for Malfunctioning Industrial Machine Investigation and inspection with Domain Shifts due to Changes in Operational and Environmental Conditions
  Ryo Tanabe, Harsh Purohit, Kota Dohi, Takashi Endo, Yuki Nikaido, Toshiki Nakamura, Yohei Kawaguchi
  WASPAA 2021
  [Paper][bibtex][Dataset]
• Emotional Speech Synthesis for Companion Robot to Imitate Professional Caregiver Speech
  Takeshi Homma, Qinghua Sun, Takuya Fujioka, Ryuta Takawaki, Eriko Ankyu, Kenji Nagamatsu, Daichi Sugawara, Etsuko T. Harada
  arXiv 2021
  [Paper][bibtex]
• Robust Unsupervised Multi-Object Tracking in Noisy Environments
  C.-H. Huck Yang, Mohit Chhabra, Y.-C. Liu, Quan Kong, Tomoaki Yoshinaga, Tomokazu Murakami
  ICIP 2021
  [Paper][bibtex]
• Online Streaming End-to-End Neural Diarization Handling Overlapping Speech and Flexible Numbers of Speakers
  Yawen Xue, Shota Horiguchi, Yusuke Fujita, Yuki Takashima, Shinji Watanabe, Paola Garcia, Kenji Nagamatsu
  INTERSPEECH 2021
  [Paper][bibtex]
• Semi-Supervised Training with Pseudo-Labeling for End-to-End Neural Diarization
  Yuki Takashima, Yusuke Fujita, Shota Horiguchi, Shinji Watanabe, Paola Garcia, Kenji Nagamatsu
  INTERSPEECH 2021
  [Paper][bibtex]
• Audio-Visual Speech Emotion Recognition by Disentangling Emotion and Identity Attributes
  Koichiro Ito, Takuya Fujioka, Qinghua Sun, Kenji Nagamatsu
  INTERSPEECH 2021
  [Paper][bibtex]
• Reproducibility Aspects of Crack Detection as a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack Detectors
  Yuki Inoue
  RRPR2021
  [Paper][bibtex][Project]
• Multi-Stream Adaptive Graph Convolutional Network Using Inter- and Intra-Body Graphs for Two-Person Interaction Recognition
  Yoshiki Ito, Kenichi Morita, Quan Kong, Tomoaki Yoshinaga
  IEEE Access, vol. 9, pp. 110670-110682, 2021
  [Paper][bibtex]
• Crack Detection as a Weakly-Supervised Problem: Towards Achieving Less Annotation-Intensive Crack Detectors
  Yuki Inoue, Hiroto Nagayoshi
  ICPR 2021
  [Paper][bibtex][Project]
• QPIC: Query-Based Pairwise Human-Object Interaction Detection with Image-Wide Contextual Information
  Masato Tamura, Hiroki Ohashi, Tomoaki Yoshinaga
  CVPR 2021
  [Paper][bibtex][Project]
• End-to-End Speaker Diarization as Post-Processing
  Shota Horiguchi, Paola Garcia, Yusuke Fujita, Shinji Watanabe, Kenji Nagamatsu
  ICASSP 2021
  [Paper][bibtex]
• Audio-Visual Speech Enhancement Method Conditioned on the Lip Motion and Speaker Discriminative Embeddings
  Koichiro Ito, Masaaki Yamamoto, Kenji Nagamatsu
  ICASSP 2021
  [Paper][bibtex]
• Flow-Based Self-Supervised Density Estimation for Anomalous Sound Detection
  Kota Dohi, Takashi Endo, Harsh Purohit, Ryo Tanabe, Yohei Kawaguchi
  ICASSP 2021
  [Paper][bibtex]
• Towards Immediate Backchannel Generation Using Attention-Based Early Prediction Model
  Amalia Istiqlali Adiba, Takeshi Homma, Toshinori Miyoshi
  ICASSP 2021
  [Paper][bibtex]
• Influence Estimation for Generative Adversarial Networks
  Naoyuki Terashita, Hiroki Ohashi, Yuichi Nonaka, Takashi Kanemaru
  ICLR 2021 (spotlight)
  [Paper][bibtex][Project]
• Project-Then-Transfer: Effective Two-Stage Cross-Lingual Transfer for Semantic Dependency Parsing
  Hiroaki Ozaki, Gaku Morio, Terufumi Morishita, Toshinori Miyoshi
  EACL 2021
  [Paper][bibtex]
• i-Parser: Interactive Parser Development Kit for Natural Language Processing
  Gaku Morio*, Hiroaki Ozaki*, Yuta Koreeda, Terufumi Morishita, Toshinori Miyoshi
  *Equal contribution
  AAAI 2021 (demo)
  [Paper][bibtex]
• The Hitachi-JHU DIHARD III System: Competitive End-to-End Neural Diarization and X-Vector Clustering Systems Combined by DOVER-Lap
  Shota Horiguchi, Nelson Yalta, Paola Garcia, Yuki Takashima, Yawen Xue, Desh Raj, Zili Huang, Yusuke Fujita, Shinji Watanabe, Sanjeev Khudanpur
  The Third DIHARD Speech Diarization Challenge, 2nd place in all the tasks
  [Paper][bibtex]
• Online End-to-End Neural Diarization with Speaker-Tracing Buffer
  Yawen Xue, Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Paola Garcia, Kenji Nagamatsu
  SLT 2021
  [Paper][bibtex]
• End-to-End Speaker Diarization Conditioned on Speech Activity and Overlap Detection
  Yuki Takashima, Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Paola Garcia, Kenji Nagamatsu
  SLT 2021
  [Paper][bibtex]
• Block-Online Guided Source Separation
  Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu
  SLT 2021
  [Paper][bibtex]
• Hitachi at SemEval-2020 Task 11: An Empirical Study of Pre-Trained Transformer Family for Propaganda Detection
  Gaku Morio*, Terufumi Morishita*, Hiroaki Ozaki, Toshinori Miyoshi
  *Equal contribution
  SemEval-2020 @COLING2020
  [Paper][bibtex]
• Hitachi at SemEval-2020 Task 10: Emphasis Distribution Fusion on Fine-Tuned Language Models
  Gaku Morio*, Terufumi Morishita*, Hiroaki Ozaki, Toshinori Miyoshi
  *Equal contribution
  SemEval-2020 @COLING2020
  [Paper][bibtex]
• Hitachi at SemEval-2020 Task 8: Simple but Effective Modality Ensemble for Meme Emotion Recognition
  Terufumi Morishita*, Gaku Morio*, Shota Horiguchi, Hiroaki Ozaki, Toshinori Miyoshi
  *Equal contribution
  SemEval-2020 @COLING2020
  [Paper][bibtex]
• Hitachi at SemEval-2020 Task 7: Stacking at Scale with Heterogeneous Language Models for Humour Recognition
  Terufumi Morishita*, Gaku Morio*, Hiroaki Ozaki, Toshinori Miyoshi
  *Equal contribution
  SemEval-2020 @COLING2020
  [Paper][bibtex]
• Hitachi at SemEval-2020 Task 3: Exploring the Representation Spaces of Transformers for Human Sense Word Similarity
  Terufumi Morishita*, Gaku Morio*, Hiroaki Ozaki, Toshinori Miyoshi
  *Equal contribution
  SemEval-2020 @COLING2020
  [Paper][bibtex]
• Machine-learning-based People-flow Simulation for Facility Layout Planning
  Satoshi Kuwamoto, Yu Kitano, Akinori Asahara
  IEEE BigData 2020
  [Paper][bibtex]
• Cycle-Contrast for Self-Supervised Video Representation Learning
  Quan Kong, Wenpeng Wei, Ziwei Deng, Tomoaki Yoshinaga, Tomokazu Murakami
  NeurIPS 2020
  [Paper][bibtex][Project]
• Class-Wise Difficulty-Balanced Loss for Solving Class-Imbalance
  Saptarshi Sinha, Hiroki Ohashi, Katsuyuki Nakamura
  ACCV 2020 (oral)
  [Paper][bibtex]
• Hitachi at MRP 2020: Text-to-Graph-Notation Transducer
  Hiroaki Ozaki*, Gaku Morio*, Yuta Koreeda, Terufumi Morishita, Toshinori Miyoshi
  *Equal contribution
  CoNLL 2020 Shared Task: Cross-Framework Meaning Representation Parsing
  [Paper][bibtex]
• Deep Autoencoding GMM-Based Unsupervised Anomaly Detection in Acoustic Signals and Its Hyper-Parameter Optimization
  Harsh Purohit, Ryo Tanabe, Takashi Endo, Kaori Suefusa, Yuki Nikaido, Yohei Kawaguchi
  DCASE 2020
  [Paper][bibtex]
• End-to-End Speaker Diarization for an Unknown Number of Speakers with Encoder-Decoder Based Attractors
  Shota Horiguchi, Yusuke Fujita, Shinji Watanabe, Yawen Xue, Kenji Nagamatsu
  INTERSPEECH 2020
  [Paper][bibtex][Project]
• Meta-Learning for Speech Emotion Recognition Considering Ambiguity of Emotional Labels
  Takuya Fujioka, Takeshi Homma, Kenji Nagamatsu
  INTERSPEECH 2020
  [Paper][bibtex]
• Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones
  Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu
  INTERSPEECH 2020
  [Paper][bibtex]
• Delay Mitigation for Backchannel Prediction in Spoken Dialog System
  Amalia Adiba, Takeshi Homma, Dario Bertero, Takashi Sumiyoshi, Kenji Nagamatsu
  IWSDS 2020
  [Paper][bibtex]
• BCaR: Beginner Classifier as Regularization Towards Generalizable Re-ID
  Masato Tamura, Tomoaki Yoshinaga
  BMVC 2020
  [Paper][bibtex][Project]
• Towards Better Non-Tree Argument Mining: Proposition-Level Biaffine Parsing with Task-Specific Parameterization
  Gaku Morio, Hiroaki Ozaki, Terufumi Morishita, Yuta Koreeda, Kohsuke Yanai
  ACL 2020
  [Paper][bibtex]
• Neural Speaker Diarization with Speaker-Wise Chain Rule
  Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Jing Shi, Kenji Nagamatsu
  arXiv 2020
  [Paper][bibtex]
• Anticipating the Start of User Interaction for Service Robot in the Wild
  Koichiro Ito, Quan Kong, Shota Horiguchi, Takashi Sumiyoshi, Kenji Nagamatsu
  ICRA 2020
  [Paper][bibtex]
• Anomalous Sound Detection Based on Interpolation Deep Neural Network
  Kaori Suefusa, Tomoya Nishida, Purohit Harsh, Ryo Tanabe, Takashi Endo, Yohei Kawaguchi
  ICASSP 2020
  [Paper][bibtex]
• End-to-End Neural Diarization: Reformulating Speaker Diarization as Simple Multi-label Classification
  Yusuke Fujita, Shinji Watanabe, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu
  arXiv 2020
  [Paper][bibtex]
• Model Ensembling of ESIM and BERT for Dialogue Response Selection
  Dario Bertero, Takeshi Homma, Kenichi Yokote, Makoto Iwayama, Kenji Nagamatsu
  The Eighth Dialog System Technology Challenge (DSTC8)
  [Paper][bibtex]
• End-to-End Neural Speaker Diarization with Self-Attention
  Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe
  ASRU 2019, Best Paper Nominee
  [Paper][bibtex][Project]
• Simultaneous Speech Recognition and Speaker Diarization for Monaural Dialogue Recordings with Target-Speaker Acoustic Models
  Naoyuki Kanda, Shota Horiguchi, Yusuke Fujita, Yawen Xue, Kenji Nagamatsu, Shinji Watanabe
  ASRU 2019
  [Paper][bibtex]
• OD-network-based Pedestrian-path Prediction for People-flow Simulation
  Yu Kitano, Satoshi Kuwamoto, Akinori Asahara
  IEEE BigData 2019
  [Paper][bibtex]
• Multimodal Deep Neural Networks Based Ensemble Learning for X-Ray Object Recognition
  Quan Kong, Naoto Akira, Bin Tong, Yuki Watanabe, Daisuke Matsubara, Tomokazu Murakami
  First International Workshop on Advanced Machine Vision for Real-Life and Industrially Relevant Applications (AMV) 2019
  [Paper][bibtex]
• Automatic Annotation Method for Document Image Binarization in Real Systems
  Ryosuke Odate
  ACPR 2019
  [Paper][bibtex]
• Hitachi at MRP 2019: Unified Encoder-to-Biaffine Network for Cross-Framework Meaning Representation Parsing
  Yuta Koreeda*, Gaku Morio*, Terufumi Morishita*, Hiroaki Ozaki*, Kohsuke Yanai
  *Equal contribution
  The Shared Task on Cross-Framework Meaning Representation Parsing (MRP 2019)
  [Paper][bibtex]
• Towards Efficient Instance Segmentation with Hierarchical Distillation
  Ziwei Deng, Quan Kong, Tomokazu Murakami
  The 6th Workshop on Transferring and Adapting Source Knowledge in Computer Vision (TASK-CV), 2019
  [Paper][bibtex]
• MMAct: A Large-Scale Dataset for Cross Modal Human Action Understanding
  Quan Kong, Ziming Wu, Ziwei Deng, Martin Klinkigt, Bin Tong, Tomokazu Murakami
  ICCV 2019
  [Paper][bibtex][Project]
• MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection
  Harsh Purohit, Ryo Tanabe, Kenji Ichige, Takashi Endo, Yuki Nikaido, Kaori Suefusa, Yohei Kawaguchi
  The Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019)
  [Paper][bibtex][Dataset]
• Location-Independent Multi-Channel Acoustic Scene Classification Using Blind Dereverberation, Blind Source Separation, and Model Ensemble
  Ryo Tanabe, Takashi Endo, Yuki Nikaido, Kenji Ichige, Phong Nguyen, Yohei Kawaguchi, Koichi Hamada
  APSIPA ASC 2019
  [Paper][bibtex]
• Split First and Then Rephrase: Hierarchical Generation for Sentence Simplification
  Mengru Wang, Hiroaki Ozaki, Yuta Koreeda, Kohsuke Yanai
  PACLING 2019, Best Paper Award
  [Paper][bibtex]
• Augmented Hard Example Mining for Generalizable Person Re-Identification
  Masato Tamura, Tomokazu Murakami
  arXiv 2019
  [Paper][bibtex]
• End-to-End Neural Speaker Diarization with Permutation-Free Objectives
  Yusuke Fujita, Naoyuki Kanda, Shota Horiguchi, Kenji Nagamatsu, Shinji Watanabe
  INTERSPEECH 2019
  [Paper][bibtex][Project]
• Multimodal Response Obligation Detection with Unsupervised Online Domain Adaptation
  Shota Horiguchi, Naoyuki Kanda, Kenji Nagamatsu
  INTERSPEECH 2019
  [Paper][bibtex]
• Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party Scenario
  Naoyuki Kanda*, Christoph Boeddeker*, Jens Heitkaemper*, Yusuke Fujita, Shota Horiguchi, Kenji Nagamatsu, Reinhold Haeb-Umbach
  *Equal contribution
  INTERSPEECH 2019
  [Paper][bibtex]
• Auxiliary Interference Speaker Loss for Target-Speaker Speech Recognition
  Naoyuki Kanda, Shota Horiguchi, Ryoichi Takashima, Yusuke Fujita, Kenji Nagamatsu, Shinji Watanabe
  INTERSPEECH 2019
  [Paper][bibtex]
• Simultaneously Determining Target Object and Transport Velocity for Manipulator and Moving Vehicle in Piece-Picking Operation
  Nobutaka Kimura, Ryo Sakai, Shinichi Katsumata, Nobuhiro Chihara
  CASE 2019
  [Paper][bibtex]
• Hierarchical Disentanglement of Discriminative Latent Features for Zero-Shot Learning
  Bin Tong, Chao Wang, Martin Klinkigt, Yoshiyuki Kobayashi, Yuuichi Nonaka
  CVPR 2019
  [Paper][bibtex]
• NAMI Question Answering System at QALab-PoliInfo
  Ken-ichi Yokote, Makoto Iwayama
  NTCIR-14
  [Paper][bibtex]
• Anomaly Detection Based on an Ensemble of Dereverberation and Anomalous Sound Extraction
  Yohei Kawaguchi, Ryo Tanabe, Takashi Endo, Kenji Ichige, Koichi Hamada
  ICASSP 2019
  [Paper][bibtex][Blog]
• Acoustic Modeling for Distant Multi-Talker Speech Recognition with Single- and Multi-Channel Branches
  Naoyuki Kanda, Yusuke Fujita, Shota Horiguchi, Rintaro Ikeshita, Kenji Nagamatsu, Shinji Watanabe
  ICASSP 2019
  [Paper][bibtex]
• Active Generative Adversarial Network for Image Classification
  Quan Kong, Bin Tong, Martin Klinkigt, Yuki Watanabe, Naoto Akira, Tomokazu Murakami
  AAAI 2019
  [Paper][bibtex]
• New Automated Guided Vehicle System Using Real-Time Holonic Scheduling for Warehouse Picking
  Hiroshi Yoshitake, Ryota Kamoshida, Yoshikazu Nagashima
  RA-L 2019 (Presented at ICRA 2019)
  [Paper][bibtex]
• Deployment Conscious Automatic Surface Crack Detection
  Yuki Inoue, Hiroto Nagayoshi
  WACV 2019
  [Paper][bibtex]
• Omnidirectional Pedestrian Detection by Rotation Invariant Training
  Masato Tamura, Shota Horiguchi, Tomokazu Murakami
  WACV 2019
  [Paper][bibtex][Dataset]
• In-Vehicle Voice Interface with Improved Utterance Classification Accuracy Using Off-the-Shelf Cloud Speech Recognizer
  Takeshi Homma, Yasunari Obuchi, Kazuaki Shima, Rintaro Ikeshita, Hiroaki Kokubo, Takuya Matsumoto
  IEICE Transactions on Information and Systems, Vol.E101-D, No.12, pp.3123-3137, 2018
  [Paper][bibtex]
• Multichannel Acoustic Scene Classification by Blind Dereverberation, Blind Source Separation, Data Augmentation, and Model Ensembling
  Ryo Tanabe, Takashi Endo, Yuki Nikaido, Takeshi Ichige, Phong Nguyen, Yohei Kawaguchi, Koichi Hamada
  The Detection and Classification of Acoustic Scenes and Events 2018 Workshop (DCASE2018), 1st prize (tied) among 13 teams in Task 5
  [Paper][bibtex]
• Autonomous Sub-Domain Modeling for Dialogue Policy with Hierarchical Deep Reinforcement Learning
  Giovanni Yoko Kristianto, Huiwen Zhang, Bin Tong, Makoto Iwayama, Yoshiyuki Kobayashi
  The 2nd Workshop on Search-Oriented Conversational AI (SCAI) 2018
  [Paper][bibtex]
• Face-Voice Matching Using Cross-Modal Embeddings
  Shota Horiguchi, Naoyuki Kanda, Kenji Nagamatsu
  ACMMM 2018
  [Paper][bibtex]
• Non-Negative Novelty Extraction: A New Non-Negativity Constraint for NMF
  Yohei Kawaguchi, Takashi Endo, Kenji Ichige, Koichi Hamada
  IWAENC 2018
  [Paper][bibtex]
• Fast Multichannel Nonnegative Matrix Factorization with Constraints on Active Source Candidates
  Rintaro Ikeshita, Yohei Kawaguchi, Kenji Nagamatsu
  IWAENC 2018
  [Paper][bibtex]
• The Hitachi/JHU CHiME-5 System: Advances in Speech Recognition for Everyday Home Environments Using Multiple Microphone Arrays
  Naoyuki Kanda, Rintaro Ikeshita, Shota Horiguchi, Yusuke Fujita, Kenji Nagamatsu, Xiaofei Wang, Vimal Manohar, Nelson Enrique Yalta Soplin, Matthew Maciejewski, Szu-Jui Chen, Aswin Shanmugam Subramanian, Ruizhi Li, Zhiqi Wang, Jason Naradowsky, L. Paola Garcia-Perera, Gregory Sell
  The 5th International Workshop on Speech Processing in Everyday Environments (CHiME) 2018, 2nd prize
  [Paper][bibtex]
• Independent Positive Semidefinite Tensor Analysis in Blind Source Separation
  Rintaro Ikeshita
  EUSIPCO 2018
  [Paper][bibtex]
• Anomaly Detection Based on Feature Reconstruction from Subsampled Audio Signals
  Yohei Kawaguchi
  EUSIPCO 2018
  [Paper][bibtex]
• Lattice-Free State-Level Minimum Bayes Risk Training of Acoustic Models
  Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu
  INTERSPEECH 2018
  [Paper][bibtex]
• Semi-Supervised Clustering Framework Based on Active Learning for Real Data
  Ryosuke Odate, Hiroshi Honjo, Yasufumi Suzuki, Masahiro Motobayashi
  Joint IAPR International Workshops on Statistical Techniques in Pattern Recognition (SPR) and Structural and Syntactic Pattern Recognition (SSPR) 2018
  [Paper][bibtex]
• Attributes' Importance for Zero-Shot Pose-Classification Based on Wearable Sensors
  Hiroki Ohashi, Mohammad Al-Naser, Sheraz Ahmed, Katsuyuki Nakamura, Takuto Sato, Andreas Dengel
  Sensors 2018, 18(8), 2485
  [Paper][bibtex][Blog]
• Maximizing SLU Performance with Minimal Training Data Using Hybrid RNN Plus Rule-Based Approach
  Takeshi Homma, Adriano S. Arantes, Maria Teresa Gonzalez Diaz, Masahito Togami
  SIGDIAL 2018
  [Paper][bibtex]
• Sequence Distillation for Purely Sequence Trained Acoustic Models
  Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu
  ICASSP 2018
  [Paper][bibtex]
• Independent Low-Rank Matrix Analysis Based on Multivariate Complex Exponential Power Distribution
  Rintaro Ikeshita, Yohei Kawaguchi
  ICASSP 2018
  [Paper][bibtex]
• Apprenticeship Learning of Ship Behavior in Crowded Area by Dimension Compression
  Yuxin Liang, Masayoshi Mase
  International Journal of Modeling and Optimization 2018
  [Paper][bibtex]
• Adversarial Zero-Shot Learning With Semantic Augmentation
  Bin Tong, Martin Klinkigt, Junwen Chen, Xiankun Cui, Quan Kong, Tomokazu Murakami, Yoshiyuki Kobayashi
  AAAI 2018
  [Paper][bibtex]
• Hierarchical Model for Zero-Shot Activity Recognition Using Wearable Sensors
  Mohammad Al-Naser*, Hiroki Ohashi*, Sheraz Ahmed, Katsuyuki Nakamura, Takayuki Akiyama, Takuto Sato, Phong Xuan Nguyen, Andreas Dengel
  *Equal contribution
  ICAART 2018
  [Paper][bibtex]
• Investigation of Lattice-Free Maximum Mutual Information-Based Acoustic Models with Sequence-Level Kullback-Leibler Divergence
  Naoyuki Kanda, Yusuke Fujita, Kenji Nagamatsu
  ASRU 2017
  [Paper][bibtex]
• An Application of Noise-Robust Speech Translation Using Asynchronous Smart Devices
  Ryoichi Takashima, Yohei Kawaguchi, Qinghua Sun, Takashi Sumiyoshi, Masahito Togami
  APSIPA ASC 2017
  [Paper][bibtex]
• Sub-Nyquist Non-Uniform Sampling for Low-Cost Sound Monitoring
  Yohei Kawaguchi, Ryoichi Takashima, Takashi Endo, Masahito Togami
  APSIPA ASC 2017
  [Paper][bibtex]
• Time-Domain Subsampling and Reconstruction for Microphone Array
  Yohei Kawaguchi, Ryoichi Takashima, Takashi Endo, Masahito Togami
  APSIPA ASC 2017
  [Paper][bibtex]
• Local Gaussian Model with Source-Set Constraints in Audio Source Separation
  Rintaro Ikeshita, Yohei Kawaguchi, Masahito Togami, Yusuke Fujita, Kenji Nagamatsu
  MLSP 2017
  [Paper][bibtex]
• How Can We Detect Anomalies from Subsampled Audio Signals?
  Yohei Kawaguchi, Takashi Endo
  MLSP 2017
  [Paper][bibtex]
• StruAP: A Tool for Bundling Linguistic Trees Through Structure-Based Abstract Pattern
  Kohsuke Yanai, Misa Sato, Toshihiko Yanase, Kenzo Kurotsuchi, Yuta Koreeda, Yoshiki Niwa
  EMNLP 2017 (demo)
  [Paper][bibtex]
• Independent Vector Analysis with Frequency Range Division and Prior Switching
  Rintaro Ikeshita, Yohei Kawaguchi, Masahito Togami, Yusuke Fujita, Kenji Nagamatsu
  EUSIPCO 2017
  [Paper][bibtex]
• Separation of Vibration-Derived Sound Signals Based on Fusion Processing of Vibration Sensors and Microphones
  Ryoichi Takashima, Yohei Kawaguchi, Masahito Togami
  EUSIPCO 2017
  [Paper][bibtex]
• ADMM-Based Audio Reconstruction for Low-Cost-Sound-Monitoring
  Sandra Ramaswami, Yohei Kawaguchi, Ryoichi Takashima, Takashi Endo, Masahito Togami
  EUSIPCO 2017
  [Paper][bibtex]
• Learning to Generate Rock Descriptions from Multivariate Well Logs with Hierarchical Attention
  Bin Tong, Martin Klinkigt, Makoto Iwayama, Toshihiko Yanase, Yoshiyuki Kobayashi, Anshuman Sahu, Ravigopal Vennelakanti
  KDD 2017
  [Paper][bibtex]
• bunji at SemEval-2017 Task 3: Combination of Neural Similarity Featuresand Comment Plausibility Features
  Yuta Koreeda, Takuya Hashito, Yoshiki Niwa, Misa Sato, Toshihiko Yanase, Kenzo Kurotsuchi, Kohsuke Yanai
  11th International Workshop on Semantic Evaluations (SemEval-2017)
  [Paper][bibtex]
• Augmenting Wearable Sensor Data with Physical Constraint for DNN-Based Human-Action Recognition
  Hiroki Ohashi, Mohammad Al-Naser, Sheraz Ahmed, Takayuki Akiyama, Takuto Sato, Phong Nguyen, Katsuyuki Nakamura, Andreas Dengel
  ICML 2017 Times Series Workshop
  [Paper][bibtex]
• Jointly Learning Energy Expenditures and Activities Using Egocentric Multimodal Signals
  Katsuyuki Nakamura, Serena Yeung, Alexandre Alahi, Li Fei-Fei
  CVPR 2017
  [Paper][bibtex]
• Adaptive Boolean Compressive Sensing by Sequential Pool-Design
  Yohei Kawaguchi, Masahito Togami
  APSIPA ASC 2016
  [Paper][bibtex]
• Robust Utterance Classification Using Multiple Classifiers in the Presence of Speech Recognition Errors
  Takeshi Homma, Kazuaki Shima, Takuya Matsumoto
  SLT 2016
  [Paper][bibtex]
• Deep Match Between Geology Reports and Well Logs Using Spatial Information
  Bin Tong, Martin Klinkigt, Makoto Iwayama, Toshihiko Yanase, Yoshiyuki Kobayashi, Anshuman Sahu, Ravigopal Vennelakanti
  CIKM 2016
  [Paper][bibtex]
• Data Augmentation Using Multi-Input Multi-Output Source Separation for Deep Neural Network Based Acoustic Modeling
  Yusuke Fujita, Ryoichi Takashima, Takeshi Homma, Masahito Togami
  INTERSPEECH 2016
  [Paper][bibtex]
• Neural Attention Model for Classification of Sentences That Support Promoting/Suppressing Relationship
  Yuta Koreeda, Toshihiko Yanase, Kohsuke Yanai, Misa Sato, Yoshiki Niwa
  Third Workshop on Argument Mining (ArgMining2016)
  [Paper][bibtex]
• bunji at SemEval-2016 Task 5: Neural and Syntactic Models of Entity-Attribute Relationship for Aspect-Based Sentiment Analysis
  Toshihiko Yanase, Kohsuke Yanai, Misa Sato, Toshinori Miyoshi, Yoshiki Niwa
  10th International Workshop on Semantic Evaluation (SemEval-2016)
  [Paper][bibtex]
• Adaptive Boolean Compressive Sensing by Using Multi-Armed Bandit
  Yohei Kawaguchi, Masahito Togami
  ICASSP 2016
  [Paper][bibtex]
• Trip-Extraction Method Based on Characteristics of Sensors and Human-Travel Behavior for Sensor-Based Travel Survey
  Hiroki Ohashi, Phong Xuan Nguyen, Takayuki Akiyama, Masaaki Yamamoto, Akiko Sato
  Journal of Information Processing 24 (1), 39-48, 2016
  [Paper][bibtex]
• Unified ASR System Using LGM-Based Source Separation, Noise-Robust Feature Extraction, and Word Hypothesis Selection
  Yusuke Fujita, Ryoichi Takashima, Takeshi Homma, Rintaro Ikeshita, Yohei Kawaguchi, Takashi Sumiyoshi, Takashi Endo, Masahito Togami
  ASRU 2015
  [Paper][bibtex]
• Production Estimation for Shale Wells with Sentiment-Based Features from Geology Reports
  Bin Tong, Hiroaki Ozaki, Makoto Iwayama, Toshihiko Yanase, Yoshiyuki Kobayashi, Anshuman Sahu, Ravigopal Vennelakanti
  ICDM Workshop 2015
  [Paper][bibtex]
• Improvement of Robustness to Change of Positive Elements in Boolean Compressive Sensing
  Yohei Kawaguchi, Tatsuhiko Osa, Hisashi Nagano, Masahito Togami
  EUSIPCO 2015
  [Paper][bibtex]
• Information Retrieval Boosted by Category for Troubleshooting Search System
  Bin Tong, Toshihiko Yanase, Hiroaki Ozaki, Makoto Iwayama
  SIGIR Workshop on Graph Search and Beyond (GSB) 2015
  [Paper][bibtex]
• End-to-End Argument Generation System in Debating
  Misa Sato, Kohsuke Yanai, Toshihiko Yanase, Toshinori Miyoshi, Makoto Iwayama, Qinghua Sun, Yoshiki Niwa
  ACL 2015 (demo)
  [Paper][bibtex]
• Learning Sentence Ordering for Opinion Generation of Debate
  Toshihiko Yanase, Toshinori Miyoshi, Kohsuke Yanai, Misa Sato, Makoto Iwayama, Yoshiki Niwa, Paul Reisert, Kentaro Inui
  2nd Workshop on Argumentation Mining (ArgMining2015)
  [Paper][bibtex]