Kinoshita Yuma

論文

Causal and Relaxed-Distortionless Response Beamforming for Online Target Source Extraction.

Maximization of 2D Cross-Correlation Based on Auxiliary Function Method for Image Alignment

Effectiveness of Inter- and Intra-Subarray Spatial Features for Acoustic Scene Classification

Acoustic Traffic Monitoring Based on Deep Neural Network Trained by Stereo-Recorded Sound and Sensor Data.

Automatic Call Classification of Autism Model Marmosets by Deep Learning and Analysis of Their Vocal Development.

Augmentation of Various Speed Data by Controlling Frame Overlap for Acoustic Traffic Monitoring.

Image and Model Transformation with Secret Key for Vision Transformer

Estimation of Transfer Coefficients and Signals of Sound-to-Light Conversion Device Blinky Under Saturation

Compressed Sensing of Sparse Spectrum Using Distributed Sound-to-Light Conversion Device Blinkies

Template Matching with White Balance Adjustment Under Multiple Illuminants

Missing Data Recovery Using Autoencoder for Multi-Channel Acoustic Scene Classification

N-White Balancing: White Balancing for Multiple Illuminants Including Non-Uniform Illumination

Self-Supervised Intrinsic Image Decomposition Network Considering Reflectance Consistency

Privacy-Preserving Image Classification Using Vision Transformer

An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applications.

Realizing Low Latency Time-Frequency Masking with Frame-Wise FIR Filters for Speech Enhancement

Spatially Varying White Balancing for Mixed and Non-Uniform Illuminants

Analysis on Roles of DNNs in End-to-End Acoustic Scene Analysis Framework with Distributed Sound-to-Light Conversion Devices

Causal Distortionless Response Beamforming by Alternating Direction Method of Multipliers

Real-Time Pitch Visualization with “Blinky" Sound-to-Light Conversion Device