SOTA discrete acoustic codec models with 40 tokens per second for audio language modeling

MoSQITo is a unified and modular development framework of key sound quality metrics favoring reproducible science and efficient shared scripting among engineers, teachers and researchers community.

Deep-learning iterative solver for the heterogeneous 2D Helmholtz equation

OSEkit is an open source suite of tools written in python and dedicated to the management and analysis of data in underwater passive acoustics.

A Python library for acousticians.

An Acoustic and Optical Dataset for the Perception of Underwater Unexploded Ordnance (UXO)

A Python wrapper for Tadarida-D: A Toolbox for Animal Detection on Acoustic Recordings

CNN acoustic environment classification trained on the AudioSet dataset

Weld AI Analyst software (video streaming storage)

The program will convert dBSPL to loudness (sone) and measure the dissonance level between two notes up to its 7th harmonic. Also, it can draw dissonance curve of a timbre.

This repository contains the submitted model for DCASE-2021 Task 1a, that targets on low-complexity Acoustic scene classification.

Audio Signal Processing

This is collection of voice measuring algorithms that do not rely on gender

Weld AI Analyst software

Acoustic Transformer Models for Audio Classification

StofNet: Super-resolution Time of Flight Network (ICASSP 2024)

Python tools for the Acoustic Toolbox