Jazz Bass Transcription Using a U-Net Architecture

Jazz Bass Transcription Using a U-Net Architecture

In this paper, we adapt a recently proposed U-net deep neural network architecture from melody to bass transcription. We investigate pitch shifting and random equalization as data augmentation techniques. In a parameter importance study, we study the influence of the skip connection strategy between...

Full description

Bibliographic Details
Main Authors: Jakob Abeßer, Meinard Müller
Format: Article
Language:English
Published: MDPI AG 2021-03-01
Series:Electronics
Subjects:
bass transcription
convolutional neural networks
U-net architecture
data augmentation
skip connections
Online Access:https://www.mdpi.com/2079-9292/10/6/670

Internet

https://www.mdpi.com/2079-9292/10/6/670

Similar Items