MUSIC Tribe's perspective and challenges on edge-oriented machine learning
By T. Arvanitidis

Thomas Arvanitidis talks to ADASP about MUSIC Tribe’s perspectives and challenges arisen from deploying ML-driven audio applications on edge.

Abstract

Thomas will give a talk on edge-oriented machine learning and the challenges that come from having deployment on edge as a requirement. He will briefly discuss MUSIC Tribe’s view on platforms in general and bring some platforms as examples for consideration, list the key challenges of ML on edge, and share some industry approaches and insights on MUSIC Tribe’s approach.

Bio

Thomas Arvanitidis works as a Machine Learning Team Leader in the Research Department of MUSIC Tribe. One of the key projects that he has worked on is the Channel AI feature that is available in the newest flagship of the Midas Consoles, Midas HD 96. With his team, they are focusing on incorporating innovative ML technologies to make the company’s products more intelligent. During his academic career, Thomas focused on digital signal processing, spectral processing in particular, and he graduated with a MSc (by research) in Electronic Engineering and a BEng in Electronic Engineering with Music Technology Systems from the University of York.