Lab41 is currently developing a new open-source project called Magnolia. Lab41 is a research firm that aims to provide a better understanding on how to work with and use data analytics. The company’s ongoing project Magnolia focuses on speech isolation using deep learning.
“Current technologies use expensive microphone arrays, are limited in the environments they can operate in, or can isolate a limited numbers of speakers. Magnolia proposes to use deep learning to break these constraints and isolate speech to work with COTS microphones in a variety of environmental conditions,” the company wrote on its website.
There are four main problems Lab41 plans to work on with Magnolia. The programs are monaural source separation, removing a source that is dynamic and loud, multiple moving sources, and standoff distance acoustic enhancement.
“This project will be primarily an analysis of cost functions (in supervised and unsupervised settings) that can be used in order to denoise and isolate signals. The resulting algorithms of interest will be a mix of cost function resembling ICA and simulated beamforming methods,” according to the project’s GitHub page.
Magnolia is just one of many project’s Lab41 is currently working on. Other projects include Pelops, which focuses on car recognition using deep learning; and Poseidon, which focus on software defined network situational awareness.
Top 5 trending GitHub projects of the week:
- tfjs: A JavaScript version of TensorFlow designed to provide a JavaScript library for training and deploying machine learning models
- tabler: An HTML dashboard UI kit built on Bootstrap 4
- awesome podcasts: A collection of awesome podcasts
- gron: A project designed to transform JSON into discrete assignments
- Interview notebook: Still trending! The project is in Chinese, but it is designed to provide basic knowledge to mastering technical interviews
