Deep Learning, Wavelet Analysis and Fourier Transforms for identification of abnormal EEG in Epilepsy patients

Genre Classification using Convolutional Neural Networks

🏃‍♀️ Process, Visualize, and Analyze Actigraphy Data

This repository contains an end-to-end pipeline to train a convolutional neural network (CNN) for environmental sound classification on ESC-50. Serve the model for inference using Modal + a FastAPI endpoint. - Visualize model outputs (top predictions, input mel-spectrogram, waveform, and CNN feature maps).

Three in one. capture audio with mobile mic and then play, play songs from internal download directly, displaying spectogram (frequency) of an audio in Flutter.

HackOnHills project : Pronuncuation correction game which takes in voice input of the pronunciation of words from the user and compares it with the correct pronunciation of the word.

Audio Studio Pro is a comprehensive, AI-powered application for professional audio production.

An implementation of trigger word detection using keras, for detecting digits spoken in an audio

This is a project on ML, Music Genre Classification using Mel-spectogram for audio preprocessing and Convolutional Neural Network(CNN) for the model training. Built CNN kinda scratch with no ml libraries but only using low-level tf operations.

Project for the Signal Processing course @acs, UPB 2021

Developed a deep learning system to identify and isolate human voice from single waveform audio signals. Leveraging neural networks for sound source separation, this project filters background noise and non-human sounds, enhancing clarity in real-time audio processing.

Bronze medal solution for the kaggle competition HMS-Harmful Brain Activity Classification

Utility to create audio captchas using gTTS and decode it to text