This is a project on Audio Classification using Deep Learning. I am using the Google-audioset dataset for this project and Tensorflow and Keras on Jupyter Notebook.
Initially, I solved a simple problem of classifying Clapping from non-clapping human examples. I used a single-label dataset for this classification and the results of the various classifications can be found in the file uploaded on this repository.
Then, I moved on to solve the classification problem on multi-label datasets using multi-label classification algorithms like label powerset,binary relevance,and Classifier chain methods.
Further progress in the project will be updated soon!!!