Subjective Evaluation of Deep Learning Models for Symbolic Music Composition

03/28/2022
by   Carlos Hernandez-Olivan, et al.
0

Deep learning models are typically evaluated to measure and compare their performance on a given task. The metrics that are commonly used to evaluate these models are standard metrics that are used for different tasks. In the field of music composition or generation, the standard metrics used in other fields have no clear meaning in terms of music theory. In this paper, we propose a subjective method to evaluate AI-based music composition systems by asking questions related to basic music principles to different levels of users based on their musical experience and knowledge. We use this method to compare state-of-the-art models for music composition with deep learning. We give the results of this evaluation method and we compare the responses of each user level for each evaluated model.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
08/27/2021

Music Composition with Deep Learning: A Review

Generating a complex work of art such as a musical composition requires ...
research
07/12/2022

ReLyMe: Improving Lyric-to-Melody Generation by Incorporating Lyric-Melody Relationships

Lyric-to-melody generation, which generates melody according to given ly...
research
09/26/2017

Learning a Predictive Model for Music Using PULSE

Predictive models for music are studied by researchers of algorithmic co...
research
07/25/2020

Adaptive music: Automated music composition and distribution

Creativity, or the ability to produce new useful ideas, is commonly asso...
research
04/10/2022

Towards Evaluation of Autonomously Generated Musical Compositions: A Comprehensive Survey

There are many applications that aim to create a complete model for an a...
research
08/26/2023

A Comprehensive Survey for Evaluation Methodologies of AI-Generated Music

In recent years, AI-generated music has made significant progress, with ...
research
06/03/2019

MUSICNTWRK: data tools for music theory, analysis and composition

We present the API for MUSICNTWRK, a python library for pitch class set ...

Please sign up or login with your details

Forgot password? Click here to reset