Multi-Scale Multi-Band DenseNets for Audio Source Separation
Offered By: Launchpad via YouTube
Course Description
Overview
Explore a 24-minute presentation on Multi-scale Multi-band DenseNets for Audio Source Separation, delivered by the Fellowship.ai team. Delve into the novel network architecture that extends the densely connected convolutional network (DenseNet) to tackle the complex challenge of separating audio sources. Learn about the incorporation of up-sampling layers, block skip connections, and band-dedicated dense blocks to enhance performance in audio source separation tasks. Discover how this approach leverages long contextual information to outperform state-of-the-art results on the SiSEC 2016 competition, while requiring fewer parameters and less training time. Gain insights into the paper's methodology, problem definition, terminology, and comparisons with previous methods. Understand the intricacies of the proposed architecture, including composite layers and the multiband multiscale internet concept.
Syllabus
Introduction
Framework
Problem Definition
Terminology
Previous methods
Architecture
Composite Layers
Multiband Multiscale Internet
Taught by
Launchpad
Related Courses
Neural Networks for Machine LearningUniversity of Toronto via Coursera Good Brain, Bad Brain: Basics
University of Birmingham via FutureLearn Statistical Learning with R
Stanford University via edX Machine Learning 1—Supervised Learning
Brown University via Udacity Fundamentals of Neuroscience, Part 2: Neurons and Networks
Harvard University via edX