OpenL3: Open-source deep audio and image embeddings
-
Updated
Jun 17, 2023 - Jupyter Notebook
OpenL3: Open-source deep audio and image embeddings
A library for soundscape synthesis and augmentation
DCASE2020 Challenge Task 2 baseline system
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.
Code for the paper "Self-Supervised Learning for Anomalous Sound Detection"
MobileNetV2-based baseline system for DCASE2021 Challenge Task 2.
Corpus-based concatenative synthesizer in Max for Live
Unsupervised Domain Adaptation for Acoustic Scene Classification with Wasserstein Distance
Submission for task 2 "First-Shot Unsupervised Anomalous Sound Detection for Machine Condition Monitoring" of the DCASE challenge 2023 (https://dcase.community/challenge2023/task-first-shot-unsupervised-anomalous-sound-detection-for-machine-condition-monitoring)
Accompanying code for the paper Design Choices for Learning Embeddings from Auxiliary Tasks for Domain Generalization in Anomalous Sound Detection.
Deep neural network model combining audio signal processing and pre-trained audio CNN achieved 90.1% adjusted accuracy (27.6% improvement) for classifying audio recording environment.
Codes related to DCASE2021 Task 1 - Acoustic Scene Classification
Code for using with the Clotho dataset
Codes related to acoustic scene classification task for DCASE 2022
Capstone Project
Accompanying code for the paper On Using Pre-Trained Embeddings for Detecting Anomalous Sounds with Limited Training Data.
Code for task 2 of the DCASE2024 Challenge
Code for the paper "AdaProj: Adaptively Scaled Angular Margin Subspace Projections for Anomalous Sound Detection with Auxiliary Classification Tasks"
Add a description, image, and links to the machine-listening topic page so that developers can more easily learn about it.
To associate your repository with the machine-listening topic, visit your repo's landing page and select "manage topics."