The code for the MaD TwinNet. Demo page:

DCASE2020 Challenge Task 2 baseline system

Python code for handling the Clotho dataset.

a python library for speech enhancement

Control mechanisms to the U-Net architecture for doing multiple source separation instruments

Sound event detection with depthwise separable and dilated convolutions.

Audio captioning baseline system for DCASE 2020 challenge.

Autoencoder-based baseline system for DCASE2021 Challenge Task 2.

Python audio signal processing library

MobileNetV2-based baseline system for DCASE2021 Challenge Task 2.

Language modelling for sound event detection

A small tool to calculate the distribution of audio durations in a directory

Unsupervised Domain Adaptation for Acoustic Scene Classification with Wasserstein Distance

A convolutional neural network for blind audio source separation.

Detection of events described by hidden (semi-)Markov models in an audio stream

This project implements the functionalities of a virtual radio broadcasting station. It includes features such as sound file manipulation, amplitude modulation, frequency modulation, spectral analysis, filter design, noise removal, and music composition using given notes.

An intelligent music playlist generator that analyzes your personal music library and creates playlists based on acoustic similarity. This project implements advanced audio signal processing techniques using Mel-Frequency Cepstral Coefficients (MFCCs) to understand music at a fundamental level and provides comprehensive library management.

python discord bot that converts pcm (analog audio signals) from calls into mp3 audio

Signal Processing Audio to create an Auditory Enviroment - Based on Schroeders Reverb Theory

Emotion Analysis from Video: A Multi-Model Machine Learning Approach