The Jazz Transformer on the Front Line: Exploring the Shortcomings of
AI-composed Music through Quantitative Measures
S. Wu, and Y. Yang. (2020)cite arxiv:2008.01307Comment: Accepted to the 21st International Society for Music Information Retrieval Conference (ISMIR 2020).
Abstract
This paper presents the Jazz Transformer, a generative model that utilizes a
neural sequence model called the Transformer-XL for modeling lead sheets of
Jazz music. Moreover, the model endeavors to incorporate structural events
present in the Weimar Jazz Database (WJazzD) for inducing structures in the
generated music. While we are able to reduce the training loss to a low value,
our listening test suggests however a clear gap between the average ratings of
the generated and real compositions. We therefore go one step further and
conduct a series of computational analysis of the generated compositions from
different perspectives. This includes analyzing the statistics of the pitch
class, grooving, and chord progression, assessing the structureness of the
music with the help of the fitness scape plot, and evaluating the model's
understanding of Jazz music through a MIREX-like continuation prediction task.
Our work presents in an analytical manner why machine-generated music to date
still falls short of the artwork of humanity, and sets some goals for future
work on automatic composition to further pursue.
Description
[2008.01307] The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures
%0 Generic
%1 wu2020transformer
%A Wu, Shih-Lun
%A Yang, Yi-Hsuan
%D 2020
%K evaluation
%T The Jazz Transformer on the Front Line: Exploring the Shortcomings of
AI-composed Music through Quantitative Measures
%U http://arxiv.org/abs/2008.01307
%X This paper presents the Jazz Transformer, a generative model that utilizes a
neural sequence model called the Transformer-XL for modeling lead sheets of
Jazz music. Moreover, the model endeavors to incorporate structural events
present in the Weimar Jazz Database (WJazzD) for inducing structures in the
generated music. While we are able to reduce the training loss to a low value,
our listening test suggests however a clear gap between the average ratings of
the generated and real compositions. We therefore go one step further and
conduct a series of computational analysis of the generated compositions from
different perspectives. This includes analyzing the statistics of the pitch
class, grooving, and chord progression, assessing the structureness of the
music with the help of the fitness scape plot, and evaluating the model's
understanding of Jazz music through a MIREX-like continuation prediction task.
Our work presents in an analytical manner why machine-generated music to date
still falls short of the artwork of humanity, and sets some goals for future
work on automatic composition to further pursue.
@misc{wu2020transformer,
abstract = {This paper presents the Jazz Transformer, a generative model that utilizes a
neural sequence model called the Transformer-XL for modeling lead sheets of
Jazz music. Moreover, the model endeavors to incorporate structural events
present in the Weimar Jazz Database (WJazzD) for inducing structures in the
generated music. While we are able to reduce the training loss to a low value,
our listening test suggests however a clear gap between the average ratings of
the generated and real compositions. We therefore go one step further and
conduct a series of computational analysis of the generated compositions from
different perspectives. This includes analyzing the statistics of the pitch
class, grooving, and chord progression, assessing the structureness of the
music with the help of the fitness scape plot, and evaluating the model's
understanding of Jazz music through a MIREX-like continuation prediction task.
Our work presents in an analytical manner why machine-generated music to date
still falls short of the artwork of humanity, and sets some goals for future
work on automatic composition to further pursue.},
added-at = {2023-05-09T18:49:36.000+0200},
author = {Wu, Shih-Lun and Yang, Yi-Hsuan},
biburl = {https://www.bibsonomy.org/bibtex/2be96af498e5ab6d00348b8ddddf64d5a/alex_h},
description = {[2008.01307] The Jazz Transformer on the Front Line: Exploring the Shortcomings of AI-composed Music through Quantitative Measures},
interhash = {50a2cca1eed8f778105647b30dd66149},
intrahash = {be96af498e5ab6d00348b8ddddf64d5a},
keywords = {evaluation},
note = {cite arxiv:2008.01307Comment: Accepted to the 21st International Society for Music Information Retrieval Conference (ISMIR 2020)},
timestamp = {2023-05-09T18:49:36.000+0200},
title = {The Jazz Transformer on the Front Line: Exploring the Shortcomings of
AI-composed Music through Quantitative Measures},
url = {http://arxiv.org/abs/2008.01307},
year = 2020
}