environmental-sound-classification

Implementation of audio, image, and spectrogram augmentation techniques provided by the librosa, Keras and audiomentations

Replication of the Paper Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification by Salomon & Bello

The code implements the Deep CNN model described in Salamon and Bello's paper for Environmental Sound Classification on Urbansound8k dataset

Uncertainty-aware environmental sound classification using Wav2Vec2 with Bayesian Monte Carlo Dropout and calibration analysis.

AI system that analyzes urban soundscapes to optimize city planning, reduce noise pollution, and enhance acoustic environments using audio deep learning.

A novel, model-agnostic Explainable AI (XAI) framework for audio classification. Introduces RISE-SPEC, RISE-WAVE, and RISE-AUDIO, demonstrating superior interpretability over baseline methods like RISE, LIME, and Grad-CAM.

SoundSentinel is a machine learning model designed to detect harmful situations based on sound analysis. It identifies events such as screaming, glass breaking, and gunshots, with a focus on robustness against noise and background disturbances.

CRNN-based audio tagging for environmental sound classification

HTS-Audio-Transformer and BEATs for environmental sound classification

Residual CNN for Environmental Sound Classification — 84.5% accuracy on ESC-50, outperforming SVM baseline by 22.5%

This project explores various approaches for audio classification using neural networks with TensorFlow and Keras. The notebook demonstrates the complete process from data loading and preprocessing to model building, training, evaluation, and inference.

Deep Learning project for urban sound classification, comparing MLP, RNN, and Bidirectional RNN architectures with feature extraction, hyperparameter optimization, and robustness analysis.

This repository contains the implementation of Environmental Sound Classification on the ESC-50 dataset using the ACDNet.

CNN-RNN multibranch architecture for Environmental Sound Classification.

Large-scale pretrained audio neural networks (CNN14) for environmental sound classification

The aim of this project was to design and implement a Flask web application for classifying environmental sounds which uses convolutional neural network architecture.

This is the translation of our Turkish language published article to English language. For Turkish Link: https://www.set-science.com/manage/uploads/ISAS2022_0088/SETSCI_ISAS2022_0088_0011.pdf