Hiromitsu Nishizaki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Hiromitsu Nishizaki has a total of 88 co-authors. Here are the top co-authors by number of shared publications:
- Xiaoyang Mao
University of Yamanashi
9 shared publications - Chee Siang Leow
University of Yamanashi
8 shared publications - Latifah Munirah Kamarudin
Universiti Malaysia Perlis
8 shared publications Chee Siang Leow
Integrated Graduate School of Medicine, Engineering, and Agricultural Sciences, University of Yamanashi
6 shared publications- Ammar Zakaria
Universiti Malaysia Perlis (UniMAP)
5 shared publications - Akio Kobayashi
日本大学理工学部海洋建築工学
4 shared publications
Latest Publications
- 14 September 2026
- Published by Springer Nature
- p. 623-634
Harmonic and Entropy Neural Modeling with Demographic Fusion for Speech-Based Depression Detection
- 14 September 2026
- Published by Springer Nature
- p. 623-634
Harmonic and Entropy Neural Modeling with Demographic Fusion for Speech-Based Depression Detection
- 7 September 2026
- Published by Springer Nature
- p. 177-194
Difficulty-Aware Curriculum and Token-Weighted Rationale Distillation from LLM for Sequential Recommendation
- 7 September 2026
- Published by Springer Nature
- p. 177-194
Difficulty-Aware Curriculum and Token-Weighted Rationale Distillation from LLM for Sequential Recommendation
- 1 September 2026
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 160 (3) , 2272-2287
A dual-stream spectral network for versatile full-band speech enhancement
Full-band speech restoration aims to recover high-fidelity speech from signals degraded by noise, reverberation, bandwidth limitation, or their combinations. Existing methods are typically designed for a specific type of degradation, which limits their flexibility when multiple distortions coexist. To address this problem, this paper proposes a dual-stream versatile speech enhancement network (DSVN)—a unified task-conditioned system for full-band speech restoration. The model introduces a dual-stream spectral block to jointly model frequency-wise spectral structures and temporal dynamics. A band-refill decoder is further designed to recover missing or degraded high-frequency components. Task-conditioned modulation is introduced to enable the same network to adapt to different objectives. Evaluation results demonstrate that DSVN improves restoration quality under both single- and mixed-degradation scenarios. The model shows clear advantages in non-intrusive quality assessment, spectral distance, and automatic speech recognition evaluation, indicating that the enhanced speech is not only cleaner but also more useful for downstream systems. Additional analysis of internal responses and ablation studies provides evidence that the proposed modules contribute to different aspects of restoration.
- 1 September 2026
- Published by Acoustical Society of America (ASA) in The Journal of the Acoustical Society of America
- Vol. 160 (3) , 2272-2287
A dual-stream spectral network for versatile full-band speech enhancement
Full-band speech restoration aims to recover high-fidelity speech from signals degraded by noise, reverberation, bandwidth limitation, or their combinations. Existing methods are typically designed for a specific type of degradation, which limits their flexibility when multiple distortions coexist. To address this problem, this paper proposes a dual-stream versatile speech enhancement network (DSVN)—a unified task-conditioned system for full-band speech restoration. The model introduces a dual-stream spectral block to jointly model frequency-wise spectral structures and temporal dynamics. A band-refill decoder is further designed to recover missing or degraded high-frequency components. Task-conditioned modulation is introduced to enable the same network to adapt to different objectives. Evaluation results demonstrate that DSVN improves restoration quality under both single- and mixed-degradation scenarios. The model shows clear advantages in non-intrusive quality assessment, spectral distance, and automatic speech recognition evaluation, indicating that the enhanced speech is not only cleaner but also more useful for downstream systems. Additional analysis of internal responses and ablation studies provides evidence that the proposed modules contribute to different aspects of restoration.
- 24 August 2026
- Published by Springer Nature
- p. 3-19
Reference-Free Handwritten Japanese Character Generation via CLIP-Conditioned Diffusion Models
- 24 August 2026
- Published by Springer Nature
- p. 3-19
Reference-Free Handwritten Japanese Character Generation via CLIP-Conditioned Diffusion Models
- Open Access
- 28 July 2026
- Published by Elsevier in Internet of Things
- Vol. 39
Lightweight streaming speech enhancement for AIoT-enabled wearable hearing aids using parallel spiking mamba
- 28 July 2026
- Published by Elsevier in Internet of Things
- Vol. 39
Open AccessLightweight streaming speech enhancement for AIoT-enabled wearable hearing aids using parallel spiking mamba
- 20 April 2026
- Published by Fuji Technology Press Ltd. in Journal of Robotics and Mechatronics
- Vol. 38 (2) , 513-524
End-to-End Position Prediction for Robotic Grape Berry Thinning
Berry thinning is essential for producing high-quality grape varieties such as Shine Muscat because it directly impacts fruit size and quality. To address the labor-intensive nature of this task, this study presents an autonomous robotic arm system that integrates depth sensing with a learning-based transformation method and is implemented using a ResNet-18 convolutional neural network to predict berry coordinates and execute cutting actions. Its performance was compared with a geometric transformation method based on Robot Operating System 2 (ROS2) coordinate transformations in both indoor and outdoor environments. In indoor trials, the learning-based transformation approach achieved an approach accuracy of 96.8% and cutting accuracy of 78.5%, outperforming the geometric transformation approach, which achieved 94.6% for approach and 69.6% for cutting. On outdoor slopes, environmental challenges degraded the performance of both the approaches; however, the learning-based transformation method maintained higher accuracies, achieving 75.6% for approach and 60.3% for cutting, compared with the geometric transformation approach, which achieved 63.1% approach accuracy and 44.1% cutting accuracy. The complete thinning cycle required an average of 3.67 min to process 10 berries, confirming its feasibility for practical use. Limitations in the curved scissor end-effector reduced cutting effectiveness, highlighting the need for improved blade design. This study demonstrates the potential of combining geometric and learning-based transformation methods for artificial intelligence-driven robotic thinning to achieve efficient vineyard management.
- 20 April 2026
- Published by Fuji Technology Press Ltd. in Journal of Robotics and Mechatronics
- Vol. 38 (2) , 513-524
End-to-End Position Prediction for Robotic Grape Berry Thinning
Berry thinning is essential for producing high-quality grape varieties such as Shine Muscat because it directly impacts fruit size and quality. To address the labor-intensive nature of this task, this study presents an autonomous robotic arm system that integrates depth sensing with a learning-based transformation method and is implemented using a ResNet-18 convolutional neural network to predict berry coordinates and execute cutting actions. Its performance was compared with a geometric transformation method based on Robot Operating System 2 (ROS2) coordinate transformations in both indoor and outdoor environments. In indoor trials, the learning-based transformation approach achieved an approach accuracy of 96.8% and cutting accuracy of 78.5%, outperforming the geometric transformation approach, which achieved 94.6% for approach and 69.6% for cutting. On outdoor slopes, environmental challenges degraded the performance of both the approaches; however, the learning-based transformation method maintained higher accuracies, achieving 75.6% for approach and 60.3% for cutting, compared with the geometric transformation approach, which achieved 63.1% approach accuracy and 44.1% cutting accuracy. The complete thinning cycle required an average of 3.67 min to process 10 berries, confirming its feasibility for practical use. Limitations in the curved scissor end-effector reduced cutting effectiveness, highlighting the need for improved blade design. This study demonstrates the potential of combining geometric and learning-based transformation methods for artificial intelligence-driven robotic thinning to achieve efficient vineyard management.
- Open Access
- 11 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 168-175
Geometry-Driven Triangulation and Differentiable Semantic Gaussian Refinement for 3D Grape Bunch Model Reconstruction in the Field
- 11 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 168-175
Open AccessGeometry-Driven Triangulation and Differentiable Semantic Gaussian Refinement for 3D Grape Bunch Model Reconstruction in the Field
- Open Access
- 1 December 2025
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E108.D (12) , 1594-1604
Enhancing the Robustness of Speech Anti-Spoofing Countermeasures through Joint Optimization and Transfer Learning
Currently, research in deepfake speech detection focuses on the generalization of detection systems towards different spoofing methods, mainly for noise-free clean speech. However, the performance of speech anti-spoofing countermeasure (CM) systems often does not work well in more complicated scenarios, such as those involving noise and reverberation. To address the problem of enhancing the robustness of CM systems, we propose a transfer learning-based hybrid approach with Speech Enhancement front-end and Counter Measure back-end Joint optimization (SECM-Joint), investigating its effectiveness in improving robustness against noise and reverberation. Experimental results show that our SECM-Joint method reduces EER by 19.11% to 64.05% relatively in most noisy conditions and 23.23% to 30.67% relatively in reverberant environments compared to a Conformer-based CM baseline system without pre-training. Additionally, our dual-path U-Net (DUMENet) further enhances the robustness for real-world applications. These results demonstrate that the proposed method effectively enhances the robustness of CM systems in noisy and reverberant conditions. Codes and experimental data supporting this work are publicly available at: https://github.com/ikou-austin/SECM-Joint
- 1 December 2025
- Published by Institute of Electronics, Information and Communications Engineers (IEICE) in IEICE Transactions on Information and Systems
- Vol. E108.D (12) , 1594-1604
Open AccessEnhancing the Robustness of Speech Anti-Spoofing Countermeasures through Joint Optimization and Transfer Learning
Currently, research in deepfake speech detection focuses on the generalization of detection systems towards different spoofing methods, mainly for noise-free clean speech. However, the performance of speech anti-spoofing countermeasure (CM) systems often does not work well in more complicated scenarios, such as those involving noise and reverberation. To address the problem of enhancing the robustness of CM systems, we propose a transfer learning-based hybrid approach with Speech Enhancement front-end and Counter Measure back-end Joint optimization (SECM-Joint), investigating its effectiveness in improving robustness against noise and reverberation. Experimental results show that our SECM-Joint method reduces EER by 19.11% to 64.05% relatively in most noisy conditions and 23.23% to 30.67% relatively in reverberant environments compared to a Conformer-based CM baseline system without pre-training. Additionally, our dual-path U-Net (DUMENet) further enhances the robustness for real-world applications. These results demonstrate that the proposed method effectively enhances the robustness of CM systems in noisy and reverberant conditions. Codes and experimental data supporting this work are publicly available at: https://github.com/ikou-austin/SECM-Joint
- Open Access
- 15 July 2025
- Published by American Chemical Society (ACS) in ChemRxiv
ColabReaction: Accelerating Transition State Searches with Machine Learning Potentials on Google Colaboratory
We have developed a rapid and automated transition state (TS) search method for chemical reactions by combining the double-ended method, Direct MaxFlux (DMF), with machine learning (ML) potentials. Compared to conventional quantum mechanical (QM) scan-based approaches, this method achieves approximately two orders of magnitude speedup, typically locating TS structures within several minutes. To promote broad accessibility, this method is implemented on Google Colaboratory (Colab), leveraging its cloud-based GPU environment to eliminate the need for local computational resources. We named this implementation ColabReaction. A modified Panel-based graphical user interface is also provided, allowing users to perform TS searches through a web-based interface without writing code. This platform offers a cost-free, user-friendly solution for reaction pathway exploration and mechanistic analysis, particularly for experimental researchers and students without prior experience in computational chemistry. ColabReaction is open-source and freely available at https://ColabReaction.net and https://github.com/BILAB/ColabReaction.
- 15 July 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessColabReaction: Accelerating Transition State Searches with Machine Learning Potentials on Google Colaboratory
We have developed a rapid and automated transition state (TS) search method for chemical reactions by combining the double-ended method, Direct MaxFlux (DMF), with machine learning (ML) potentials. Compared to conventional quantum mechanical (QM) scan-based approaches, this method achieves approximately two orders of magnitude speedup, typically locating TS structures within several minutes. To promote broad accessibility, this method is implemented on Google Colaboratory (Colab), leveraging its cloud-based GPU environment to eliminate the need for local computational resources. We named this implementation ColabReaction. A modified Panel-based graphical user interface is also provided, allowing users to perform TS searches through a web-based interface without writing code. This platform offers a cost-free, user-friendly solution for reaction pathway exploration and mechanistic analysis, particularly for experimental researchers and students without prior experience in computational chemistry. ColabReaction is open-source and freely available at https://ColabReaction.net and https://github.com/BILAB/ColabReaction.
- Open Access
- 26 May 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (14) , 11705-11720
Non-invasive estimation of Shine Muscat grape color and sensory evaluation from standard camera images
This study proposes a non-invasive method to estimate both color and sensory attributes of Shine Muscat grapes from standard camera images. First, we focus on color estimation by integrating a Vision Transformer (ViT) feature extractor with interquartile range (IQR)-based outlier removal. Experimental results show that our approach achieves 97.2% accuracy, significantly outperforming Convolutional Neural Network (CNN) models. This improvement underscores the importance of capturing global contextual information to differentiate subtle color variations in grape ripeness. Second, we address human sensory evaluation by collecting questionnaire responses on 13 attributes (e.g., “Sweetness,” “Overall taste rating”), each rated on a five-point scale. Because these ratings tend to cluster around midrange values (labels “2,” “3,” and “4”), we initially limit the dataset to the extreme labels “1” (“lowest grade”) and “5” (“highest grade”) for binary classification. Three attributes—“Overall color,” “Sweetness,” and “Overall taste rating”—exhibit relatively high classification accuracies of 79.9%, 75.1%, and 75.7%, respectively. By contrast, the other 10 attributes reach only 50%–66%, suggesting that subjective variations and limited visual cues pose significant challenges. Overall, the proposed approach demonstrates the feasibility of an image-based system that integrates color estimation and sensory evaluation to support more objective, data-driven harvest timing decisions for Shine Muscat grapes.
- 26 May 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (14) , 11705-11720
Open AccessNon-invasive estimation of Shine Muscat grape color and sensory evaluation from standard camera images
This study proposes a non-invasive method to estimate both color and sensory attributes of Shine Muscat grapes from standard camera images. First, we focus on color estimation by integrating a Vision Transformer (ViT) feature extractor with interquartile range (IQR)-based outlier removal. Experimental results show that our approach achieves 97.2% accuracy, significantly outperforming Convolutional Neural Network (CNN) models. This improvement underscores the importance of capturing global contextual information to differentiate subtle color variations in grape ripeness. Second, we address human sensory evaluation by collecting questionnaire responses on 13 attributes (e.g., “Sweetness,” “Overall taste rating”), each rated on a five-point scale. Because these ratings tend to cluster around midrange values (labels “2,” “3,” and “4”), we initially limit the dataset to the extreme labels “1” (“lowest grade”) and “5” (“highest grade”) for binary classification. Three attributes—“Overall color,” “Sweetness,” and “Overall taste rating”—exhibit relatively high classification accuracies of 79.9%, 75.1%, and 75.7%, respectively. By contrast, the other 10 attributes reach only 50%–66%, suggesting that subjective variations and limited visual cues pose significant challenges. Overall, the proposed approach demonstrates the feasibility of an image-based system that integrates color estimation and sensory evaluation to support more objective, data-driven harvest timing decisions for Shine Muscat grapes.