Yagya Raj Pandeya

An enthusiastic and adaptive person with a broad and acute interest in the discovery of new innovative information technologies. I particularly enjoy collaborating with tech exports from different disciplines of computer science to develop new skills and solve new challenges.

• Sound event detection (SED) of Cow in a restriced environment.
• A synthetic cow sound event dataset preparation using the events from a cowshed and Internet.
• Visual object detection model implented for sound event detection.
• State-of-art result.
• Under pulication.

• Semi-supervised Sound Event Annotation Tool using audio and video as input.
• Automatic event detector is used to detect the audio event.
• Based on the automatic detector result, an human annotation have to refine the annotation boundary.
• Easy to use, better audio visualization, python based and output in easy CSV data file.
• Diversified annotation tool for any rare sound event.
• Under pulication.

• Article title:Deep Learning-Based Late Fusion of Multimodal Information for Emotion Classification of Music Video
• Music-Video emotion classification using audio and video multimodal network architecture.
• Use pretrained CNN for audio and 3D video model (I3D and C3D).
• The network learned features ate late fused and comparision the impact of network feature fusion.
• Cross validation and network feature fusion.
• Puplished on Multimedia Tools and Applications in March 2020

• Article title:Music Onset Detection Using Convolutional Neural Network
• Onset detection on Nepali folk music.
• One dimensional Convolutional Neural Network architecture.
• Training dataset preparation.
• Sliding window is used to identify the presence or absence of onset.
• Puplished on Springer RICE 2019 Conference in 2019

• Article title:Music-Video Emotion Analysis Using Late Fusion of Multimodal
• Music video emotion dataset of six class category.
• Audio-video multimodal architecture.
• C3D pretrained network and CNN pretrained audio network feature fusion.
• Emotion representation in 2D emotion space.
• Puplished on ITEEE 2019 Conference in 2019

• Article title:Domestic Cat Sound Classification Using Learned Features from Deep Neural Nets
• CNN and CDBN network architecture.
• Cat sound dataset preparation of 10 class categories.
• Frequency division average pooling (FDAP) technique instead of global average pooling (GAP) to make a robust prediction using various frequency band features.
• Audio augmentation and learned feature visualization.
• Puplished on Applied Science in Sep 2018

• Article title:Domestic Cat Sound Classification Using Transfer Learning
• Cat sound dataset with 10 class categories.
• Use pretrained CNN for feature extraction and make feature classification.
• Machine learning classifier and deep learning classifier comparision.
• Ensemble and data augmentation.
• Puplished on International Journal of Fuzzy Logic and Intelligent Systems in June 2018