arjunp17
PhD Researcher in AI and Audio at Queen Mary University of London
Queen Mary University of LondonLondon
Pinned Repositories
ai-audio-startups
Community list of startups working with AI in audio and music technology
All-Conv-Net-for-Bird-Activity-Detection-Significance-of-Learned-Pooling
Bird activity detection (BAD) deals with the task of predicting the presence or absence of bird vocalizations in a given audio recording. In this work, we propose an all-convolutional neural network (all-conv net) for bird activity detection. All the layers of this network including pooling and dense layers are implemented using convolution operations. The pooling operation implemented by convolution is termed as learned pooling. This learned pooling takes into account the inter featuremap correlations which are ignored in traditional max-pooling. This helps in learning a pooling function which aggregates the complementary information in various feature maps, leading to better bird activity detection. Experimental observations confirm this hypothesis. The performance of the proposed all-conv net is evaluated on the BAD Challenge 2017 dataset. The proposed all-conv net achieves state-of-art performance with a simple architecture and does not employ any data pre-processing or data augmentation techniques.
Bird-monitoring
A pre-processing technique to automatically locate bird image frames from a long video data
Bird-ROI-Detection-BROID-
Evaluation of ROI detection for bird images
custom-perceptron-model
A demo of an implementation of a custom perceptron model.
DeepLearning.AI-courses-LLM-PromptEngineering-ChatGPT
A summary of the LLM, Prompt Engineering, and ChatGPT related courses offered by DeepLearning.AI
Diffusion_Models_Course
Diffusion Models Course
MemoryControlled-MultiheadSelfAtt
Memory controlled sequential self attention for sound recognition
POLYPHONIC-SOUND-EVENT-AND-SOUND-ACTIVITY-DETECTION
POLYPHONIC SOUND EVENT AND SOUND ACTIVITY DETECTION:A MULTI-TASK APPROACH
TalkToYouTubeVideoTranscript-LLM-LangChain-Streamlit
A LangChain and Streamlit powered LLM application to talk to your YouTube video transcript
arjunp17's Repositories
arjunp17/MemoryControlled-MultiheadSelfAtt
Memory controlled sequential self attention for sound recognition
arjunp17/All-Conv-Net-for-Bird-Activity-Detection-Significance-of-Learned-Pooling
Bird activity detection (BAD) deals with the task of predicting the presence or absence of bird vocalizations in a given audio recording. In this work, we propose an all-convolutional neural network (all-conv net) for bird activity detection. All the layers of this network including pooling and dense layers are implemented using convolution operations. The pooling operation implemented by convolution is termed as learned pooling. This learned pooling takes into account the inter featuremap correlations which are ignored in traditional max-pooling. This helps in learning a pooling function which aggregates the complementary information in various feature maps, leading to better bird activity detection. Experimental observations confirm this hypothesis. The performance of the proposed all-conv net is evaluated on the BAD Challenge 2017 dataset. The proposed all-conv net achieves state-of-art performance with a simple architecture and does not employ any data pre-processing or data augmentation techniques.
arjunp17/DeepLearning.AI-courses-LLM-PromptEngineering-ChatGPT
A summary of the LLM, Prompt Engineering, and ChatGPT related courses offered by DeepLearning.AI
arjunp17/Diffusion_Models_Course
Diffusion Models Course
arjunp17/POLYPHONIC-SOUND-EVENT-AND-SOUND-ACTIVITY-DETECTION
POLYPHONIC SOUND EVENT AND SOUND ACTIVITY DETECTION:A MULTI-TASK APPROACH
arjunp17/TalkToYouTubeVideoTranscript-LLM-LangChain-Streamlit
A LangChain and Streamlit powered LLM application to talk to your YouTube video transcript
arjunp17/ai-audio-startups
Community list of startups working with AI in audio and music technology
arjunp17/Bird-monitoring
A pre-processing technique to automatically locate bird image frames from a long video data
arjunp17/Bird-ROI-Detection-BROID-
Evaluation of ROI detection for bird images
arjunp17/custom-perceptron-model
A demo of an implementation of a custom perceptron model.
arjunp17/github-final-project
arjunp17/gkpbt-css-circle
css-circle
arjunp17/jbbmo-Introduction-to-Git-and-GitHub
Introduction to Git and GitHub
arjunp17/L-CLAP
Contrastive Language-Audio Pretraining
arjunp17/minDiffusion
Self-contained, minimalistic implementation of diffusion models with Pytorch.
arjunp17/onsets-activity-events
ONSETS, ACTIVITY, AND EVENTS: A MULTI-TASK APPROACH FOR POLYPHONICSOUND EVENT MODELLING
arjunp17/Sports_Analytics_PowerBI_Dashboard
A PowerBI dashboard analysing the 2022-23 season of FC Barcelona
arjunp17/stable-diffusion
A latent text-to-image diffusion model
arjunp17/stablediffusion
High-Resolution Image Synthesis with Latent Diffusion Models
arjunp17/Talk-to-OneFootball-LLM-LangChain-Streamlit
A LangChain and Streamlit powered LLM application to talk to OneFootball!
arjunp17/TalkToYourPaper-LLM-LangChain-Streamlit
Talk to a scientific paper using the Streamlit app powered by LangChain and LLM