Section: New Software and Platforms

dnnsep

Multichannel audio source separation with deep neural networks

Keywords: Audio - Source Separation - Deep learning

Scientific Description: dnnsep is the only source separation software relying on multichannel Wiener filtering based on deep learning. Deep neural networks are used to initialize and reestimate the power spectrum of the sources at every iteration of an expectation-maximization (EM) algorithm. This results in state-of-the-art separation quality for both speech and music.

Functional Description: Combines deep neural networks and multichannel signal processing for speech enhancement and separation of musical recordings.

News Of The Year: In 2017, we changed the type of multichannel filter used and modified the software so that it runs online in real time.

• Participants: Aditya Nugraha, Laurent Pierron, Emmanuel Vincent, Antoine Liutkus, Romain Serizel and Floris Fournier

• Contact: Emmanuel Vincent