Skip to main content

Method For Modeling Style Of Musical Data

Potential Commercialised fa-solid fa-cart-arrow-down violet
Reg. ID : 17027
Comments

Description

A novel method for modeling musical data using deep learning is described. Musical data such as MIDI is used for training the model. A series of vector x is extracted from the musical data comprising pitch P, time difference T and duration D. Time difference T refers to the time lapse in beats between the start of preceding data and current data. Vector x is then distributed in latent space p(z). A Variational Autoencoder (VAE) distribution q(z|x) with loss function LV is constructed. The model consists of content latent space and style embedding to encode the content and style of music separately. The model is able to model and reconstruct styles of two different music styles.

Contact Person/Inventor

Name Email Contact Phone
Um Centre Of Innovation And Enterprise (Umcie) umcie@um.edu.my 013-2250151 / 03-79677351

Intellectual Property

Type of IP Registration ID
1 Patent Filed PI 2019004357

Award

Award Title Award Achievement Award Year Received
0 0 0

Comment

LOG IN or REGISTER to post comments.

Star Rating

Star Rating
No votes yet

Contact Form