Free

Profiling Audio Effects with Deep Neural Networks with Dr. Scott Hawley

Event Information

Share this event

Date and Time

Location

Location

ArtsOne Lecture Theatre

Queen Mary University of London

Mile End Road

London

E1 4PA

United Kingdom

View Map

Event description

Description

Come join the AES at Queen Mary's with a fascinating talk by Dr. Scott Hawley as he guides us through his work profiling compressors using neural networks and deep learning.


Abstract:
One traditional method of modeling audio effects, amplifiers, analog gear, microphones, etc. is to build a detailed model which emulates the physical processes involved. An alternate approach is a 'data-driven', 'model-agnostic' approach, in which a large amount of audio inputs and outputs and a machine learning
system such a neural network is used to approximate the same mapping of inputs to outputs in a "black box" manner. Such methods have been applied
to reverberation, tube amplifiers, source separation, and a host of other applications. I'll present some recent success in 'profiling' dynamic range compressors, whose
combination of nonlinearity and time-dependence has made them difficult to capture. The result is still a bit noisy and slow, so we won't be replacing traditional plugins
just yet, but this method also allows for some easy creation of 'inverse' effects such as de-noising and de-compression, allowing the engineer to create new effects if sufficient input-output recordings are present. For a web demo and a link to the recent paper on this, see http://www.signaltrain.ml


Bio:
Scott Hawley is a computational physicist who has been developing apps to assist and inspire his Audio Engineering Technology (AET) students at Belmont University since 2006. After speaking at his first AES conference in 2013, he was inspired to learn about machine learning (ML) techniques to assist in the audio production pipeline. In 2017 he started the ASPIRE Research Co-op to unite academics, engineers and hobbyists in the Nashville area to collaborate on innovative audio projects. Last summer he won the Incubator Lab contest of Art+Logic, Inc. for his project consisting of a ML system to help producers and composers to personalize their index of samples and loops. His free iOS acoustics measurement app, "Polar Pattern Plotter," was featured on the cover of the February 2018 issue of The Physics Teacher.
Share with friends

Date and Time

Location

ArtsOne Lecture Theatre

Queen Mary University of London

Mile End Road

London

E1 4PA

United Kingdom

View Map

Save This Event

Event Saved