A Unit Selection Methodology for Music Generation Using Deep Neural Networks

12/12/2016
by   Mason Bretan, et al.
0

Several methods exist for a computer to generate music based on data including Markov chains, recurrent neural networks, recombinancy, and grammars. We explore the use of unit selection and concatenation as a means of generating music using a procedure based on ranking, where, we consider a unit to be a variable length number of measures of music. We first examine whether a unit selection method, that is restricted to a finite size unit library, can be sufficient for encompassing a wide spectrum of music. We do this by developing a deep autoencoder that encodes a musical input and reconstructs the input by selecting from the library. We then describe a generative model that combines a deep structured semantic model (DSSM) with an LSTM to predict the next unit, where units consist of four, two, and one measures of music. We evaluate the generative model using objective metrics including mean rank and accuracy and with a subjective listening test in which expert musicians are asked to complete a forced-choiced ranking task. We compare our model to a note-level generative baseline that consists of a stacked LSTM trained to predict forward by one note.

READ FULL TEXT
research
01/03/2018

DeepJ: Style-Specific Music Generation

Recent advances in deep neural networks have enabled algorithms to compo...
research
09/14/2023

Comparative Assessment of Markov Models and Recurrent Neural Networks for Jazz Music Generation

As generative models have risen in popularity, a domain that has risen a...
research
03/29/2022

Iranian Modal Music (Dastgah) detection using deep neural networks

In this work, several deep neural networks are implemented to recognize ...
research
05/19/2021

Music Generation using Three-layered LSTM

This paper explores the idea of utilising Long Short-Term Memory neural ...
research
09/05/2017

Deep Learning Techniques for Music Generation - A Survey

This book is a survey and an analysis of different ways of using deep le...
research
05/15/2022

cMelGAN: An Efficient Conditional Generative Model Based on Mel Spectrograms

Analysing music in the field of machine learning is a very difficult pro...
research
02/04/2013

Beyond Markov Chains, Towards Adaptive Memristor Network-based Music Generation

We undertook a study of the use of a memristor network for music generat...

Please sign up or login with your details

Forgot password? Click here to reset