Evaluating an Analysis-by-Synthesis Model for Jazz Improvisation

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Standard

Evaluating an Analysis-by-Synthesis Model for Jazz Improvisation. / Frieler, Klaus; Zaddach, Wolf-Georg.
in: Transactions of the International Society for Music Information Retrieval, Jahrgang 5, Nr. 1, 03.02.2022, S. 20-34.

Publikation: Beiträge in ZeitschriftenZeitschriftenaufsätzeForschungbegutachtet

Harvard

APA

Vancouver

Bibtex

@article{f0b6121557a84c58ac2d63faea77a885,
title = "Evaluating an Analysis-by-Synthesis Model for Jazz Improvisation",
abstract = "This paper pursues two goals. First, we present a generative model for (monophonic) jazz improvisation whose main purpose is testing hypotheses on creative processes during jazz improvisation. It uses a hierarchical Markov model based on mid-level units and the Weimar Bebop Alphabet, with statistics taken from the Weimar Jazz Database. A further ingredient is chord-scale theory to select pitches. Second, as there are several issues with Turing-like evaluation processes for generative models of jazz improvisation, we decided to conduct an exploratory online study to gain further insight while testing our algorithm in the context of a variety of human generated solos by eminent masters, jazz students, and non-professionals in various performance renditions. Results show that jazz experts (64.4% accuracy) but not non-experts (41.7% accuracy) are able to distinguish the computer-generated solos amongst a set of real solos, but with a large margin of error. The type of rendition is crucial when assessing artificial jazz solos because expressive and performative aspects (timbre, articulation, micro-timing and band-soloist interaction) seem to be equally if not more important than the syntactical (tone) content. Furthermore, the level of expertise of the solo performer does matter, as solos by non-professional humans were on average rated worse than the algorithmic ones. Accordingly, we found indications that assessments of origin of a solo are partly driven by aesthetic judgments. We propose three possible strategies to install a reliable evaluation process to mitigate some of the inherent problems.",
keywords = "Music education, Generative Models, analysis by synthesis, jazz, improvisation, assessment, performance",
author = "Klaus Frieler and Wolf-Georg Zaddach",
note = "Publisher Copyright: {\textcopyright} Vascular and Endovascular Review 2021.",
year = "2022",
month = feb,
day = "3",
doi = "10.5334/tismir.87",
language = "English",
volume = "5",
pages = "20--34",
journal = "Transactions of the International Society for Music Information Retrieval",
issn = "2514-3298",
publisher = "Ubiquity Press Ltd",
number = "1",

}

RIS

TY - JOUR

T1 - Evaluating an Analysis-by-Synthesis Model for Jazz Improvisation

AU - Frieler, Klaus

AU - Zaddach, Wolf-Georg

N1 - Publisher Copyright: © Vascular and Endovascular Review 2021.

PY - 2022/2/3

Y1 - 2022/2/3

N2 - This paper pursues two goals. First, we present a generative model for (monophonic) jazz improvisation whose main purpose is testing hypotheses on creative processes during jazz improvisation. It uses a hierarchical Markov model based on mid-level units and the Weimar Bebop Alphabet, with statistics taken from the Weimar Jazz Database. A further ingredient is chord-scale theory to select pitches. Second, as there are several issues with Turing-like evaluation processes for generative models of jazz improvisation, we decided to conduct an exploratory online study to gain further insight while testing our algorithm in the context of a variety of human generated solos by eminent masters, jazz students, and non-professionals in various performance renditions. Results show that jazz experts (64.4% accuracy) but not non-experts (41.7% accuracy) are able to distinguish the computer-generated solos amongst a set of real solos, but with a large margin of error. The type of rendition is crucial when assessing artificial jazz solos because expressive and performative aspects (timbre, articulation, micro-timing and band-soloist interaction) seem to be equally if not more important than the syntactical (tone) content. Furthermore, the level of expertise of the solo performer does matter, as solos by non-professional humans were on average rated worse than the algorithmic ones. Accordingly, we found indications that assessments of origin of a solo are partly driven by aesthetic judgments. We propose three possible strategies to install a reliable evaluation process to mitigate some of the inherent problems.

AB - This paper pursues two goals. First, we present a generative model for (monophonic) jazz improvisation whose main purpose is testing hypotheses on creative processes during jazz improvisation. It uses a hierarchical Markov model based on mid-level units and the Weimar Bebop Alphabet, with statistics taken from the Weimar Jazz Database. A further ingredient is chord-scale theory to select pitches. Second, as there are several issues with Turing-like evaluation processes for generative models of jazz improvisation, we decided to conduct an exploratory online study to gain further insight while testing our algorithm in the context of a variety of human generated solos by eminent masters, jazz students, and non-professionals in various performance renditions. Results show that jazz experts (64.4% accuracy) but not non-experts (41.7% accuracy) are able to distinguish the computer-generated solos amongst a set of real solos, but with a large margin of error. The type of rendition is crucial when assessing artificial jazz solos because expressive and performative aspects (timbre, articulation, micro-timing and band-soloist interaction) seem to be equally if not more important than the syntactical (tone) content. Furthermore, the level of expertise of the solo performer does matter, as solos by non-professional humans were on average rated worse than the algorithmic ones. Accordingly, we found indications that assessments of origin of a solo are partly driven by aesthetic judgments. We propose three possible strategies to install a reliable evaluation process to mitigate some of the inherent problems.

KW - Music education

KW - Generative Models

KW - analysis by synthesis

KW - jazz

KW - improvisation

KW - assessment

KW - performance

UR - http://www.scopus.com/inward/record.url?scp=85132038592&partnerID=8YFLogxK

U2 - 10.5334/tismir.87

DO - 10.5334/tismir.87

M3 - Journal articles

VL - 5

SP - 20

EP - 34

JO - Transactions of the International Society for Music Information Retrieval

JF - Transactions of the International Society for Music Information Retrieval

SN - 2514-3298

IS - 1

ER -

Dokumente

DOI