spectogram

Analyze spectrograms created by rtl_power

A foobar2000 component that displays a spectrum analyzer.

Findit is a Python program which can detect audio clips from a database of stored audio files.

Javascript port of the CCWT library (Complex continuous wavelet transformation)

iOS Microphone Stethoscope to Measure Heart Rate using AudioKit and Custom FFT

Browser-based CTF toolkit. Drop a file, every check runs at once, nothing uploads. Hand-written Rust/WASM core, zero dependencies.

Web Audio high quality real-time spectogram from biquad bandpass filters

Detects AI-generated (deepfake) voices using MFCC features with CNN, Random Forest, and KNN models. Achieves ~98% accuracy using engineered audio features and the SceneFake dataset.

🌎 This repository contains unsupervised analysis of seismic data using Kmeans and Deep Embedded Clustering to identify different types of signals recorded in Seismograph 🕸️

deep_video_extraction is a powerful repository designed to extract deep feature representations from video inputs using pre-trained models. With support for both visual and aural features from videos. Additionally, you can process audio separately by converting it into spectrograms.

A command line tool that paints images (or text) on audio spectograms

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.

Web Audio high quality spectogram from biquad bandpass filters

A Node-RED node for running an impulse created by the Edge Impulse development platform.

Current research project at CSU, Chico in collaboration with the Cornell Elephant Listening Project. Developing an Elephant infrasound detector.

Southern African Bird Call Audio Identification Challenge

The data we are going to use consists of 2D spectrograms of deep space radio signals collected by the Allen Telescope Array at the SETI Institute. We will treat the spectrograms as images to train an image classification model to classify the signals into one of four classes.

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

Audio classification can be performed by converting audio streams into spectrograms, which provide visual representations of spectrums of frequencies as they vary over time, and classifying the spectrograms using convolutional neural networks (CNNs).

Snippets from learning tensorflow for audio data and models.