Picture for Kazuhiro Nakadai

Kazuhiro Nakadai

Honda Research Institute Japan Co., Ltd., Saitama, Japan

SLAM-based Joint Calibration of Multiple Asynchronous Microphone Arrays and Sound Source Localization

Add code
May 30, 2024
Viaarxiv icon

From Blurry to Brilliant Detection: YOLOv5-Based Aerial Object Detection with Super Resolution

Jan 26, 2024
Viaarxiv icon

Is the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers

Add code
Sep 21, 2023
Figure 1 for Is the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers
Figure 2 for Is the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers
Figure 3 for Is the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers
Figure 4 for Is the Ideal Ratio Mask Really the Best? -- Exploring the Best Extraction Performance and Optimal Mask of Mask-based Beamformers
Viaarxiv icon

Retraining-free Customized ASR for Enharmonic Words Based on a Named-Entity-Aware Model and Phoneme Similarity Estimation

May 29, 2023
Viaarxiv icon

Observability Analysis of Graph SLAM-Based Joint Calibration of Multiple Microphone Arrays and Sound Source Localization

Oct 11, 2022
Figure 1 for Observability Analysis of Graph SLAM-Based Joint Calibration of Multiple Microphone Arrays and Sound Source Localization
Figure 2 for Observability Analysis of Graph SLAM-Based Joint Calibration of Multiple Microphone Arrays and Sound Source Localization
Figure 3 for Observability Analysis of Graph SLAM-Based Joint Calibration of Multiple Microphone Arrays and Sound Source Localization
Figure 4 for Observability Analysis of Graph SLAM-Based Joint Calibration of Multiple Microphone Arrays and Sound Source Localization
Viaarxiv icon

Metric-based multimodal meta-learning for human movement identification via footstep recognition

Nov 15, 2021
Figure 1 for Metric-based multimodal meta-learning for human movement identification via footstep recognition
Figure 2 for Metric-based multimodal meta-learning for human movement identification via footstep recognition
Figure 3 for Metric-based multimodal meta-learning for human movement identification via footstep recognition
Figure 4 for Metric-based multimodal meta-learning for human movement identification via footstep recognition
Viaarxiv icon

CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments

Add code
Nov 07, 2018
Figure 1 for CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments
Figure 2 for CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments
Figure 3 for CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments
Figure 4 for CNN-based MultiChannel End-to-End Speech Recognition for everyday home environments
Viaarxiv icon

Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation

Add code
Jul 03, 2018
Figure 1 for Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
Figure 2 for Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
Figure 3 for Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
Figure 4 for Weakly Supervised Deep Recurrent Neural Networks for Basic Dance Step Generation
Viaarxiv icon

Robust Recognition of Simultaneous Speech By a Mobile Robot

Add code
Feb 20, 2016
Figure 1 for Robust Recognition of Simultaneous Speech By a Mobile Robot
Figure 2 for Robust Recognition of Simultaneous Speech By a Mobile Robot
Figure 3 for Robust Recognition of Simultaneous Speech By a Mobile Robot
Figure 4 for Robust Recognition of Simultaneous Speech By a Mobile Robot
Viaarxiv icon