VISHNU VARDHAN BATTU's Projects
Created with StackBlitz ā”ļø
Created with StackBlitz ā”ļø
We'll look into audio categorization using deep learning principles like Artificial Neural Networks (ANN), 1D Convolutional Neural Networks (CNN1D), and CNN2D in this repository. We undertake some basic data preprocessing and feature extraction on audio sources before developing models. As a result, the accuracy, training time, and prediction time of each model are compared. This is explained by model deployment, which allows users to load the desired sound output for each model that is successfully deployed, as will be addressed in more depth later.
Multi class audio classification using Deep Learning (MLP, CNN): The objective of this project is to build a multi class classifier to identify sound of a bee, cricket or noise.
A series of Jupyter notebooks and python files which stream audio from a microphone using pyaudio, then processes it.
Tensorflow 2.0 implementation of the paper: A Fully Convolutional Neural Network for Speech Enhancement
Lecture materials for Cornell CS5785 Applied Machine Learning (Fall 2022)
Data repository of Project Coswara
The projects and the materials that accompany the Flutter Apprentice book
Contains all Assignments of Python from Infosys Generic Training
PyTorch, Android application code for lung sound classification
Implementation of IEEE Access paper - Lung Sound Recognition Algorithm Based on VGGish-BiGRU
Keras implementation of Noise Masking RNN for respiratory sound classification
č®ŗęåä½äøčµęåäŗ«
This codebase is focused on predicting lung diseases from a breathing sounds dataset. 8 experiments were conducted on 5 different machine learning models. In addition, a novel data augmentation algorithm was performed and tested.
Respiratory Sound Classification
This is the official implementation of the work RespireNet.
experiments with RETURNN
Using the ICS43432 MEMS microphone on a Raspberry Pi with i2s
A collection of tutorials and examples for the Raspberry Pi
Encounter Queue and viewer module for OpenMRS
Using Convolutional Neural Networks in speech emotion recognition on the RAVDESS Audio Dataset.
Think DSP: Digital Signal Processing in Python, by Allen B. Downey.
Config files for my GitHub profile.