國立虎尾科技大學 |

Choral Music Generation: A Deep Hybrid Learning Approach /

Record Type:	Language materials, printed : Monograph/item
Title/Author:	Choral Music Generation: A Deep Hybrid Learning Approach // Daniel James Szelogowski.
Author:	Szelogowski, Daniel James,
Description:	1 electronic resource (301 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
Contained By:	Dissertations Abstracts International85-12B.
Subject:	Music. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31296228
ISBN:	9798382798271

Choral Music Generation: A Deep Hybrid Learning Approach /
Szelogowski, Daniel James,

Choral Music Generation: A Deep Hybrid Learning Approach /Daniel James Szelogowski. - 1 electronic resource (301 pages)

Source: Dissertations Abstracts International, Volume: 85-12, Section: B.

Despite advancements in AI and machine learning, the creation of AI-generated music that captures the complexity and nuance of classical choral arrangements has remained largely unexplored. This gap is significant, considering the intricate compositional techniques and sophisticated music theory knowledge required for classical choral music. My research is motivated by the quest to bridge this gap, aiming to develop an AI model capable of producing realistic choral compositions that adhere to the rich traditions of classical music. Additionally, I explore how AI-generated music is perceived across different listener groups, contributing insights into the intersection of AI and human perception in the arts. This study seeks to address three primary research questions: the feasibility of current machine learning architectures in generating SATB choral music, the ability of a hybrid AI model to produce compositions indistinguishable from human-created music by the general public, and the varying perception of AI-generated classical music among individuals with varying musical backgrounds. This dissertation presents the "Choral-GTN" system: a novel architecture combining a Generative Transformer Network with a rule-based post-processing system, alongside the curated "CHORAL" dataset to address the challenge of generating realistic four-part (SATB) choral music. My comprehensive approach integrates advanced deep learning techniques with sophisticated musical theory insights to produce compositions that closely mimic those created by human composers. Through a meticulously designed survey and rigorous statistical analysis, I evaluate the realism and indistinguishability of my AI-generated music across varied listener groups. The findings demonstrate that this model successfully created music that was largely indistinguishable from human compositions, achieving a significant milestone in AI-assisted music composition and music perception.

English

ISBN: 9798382798271Subjects--Topical Terms:

649088
Music.
Subjects--Index Terms:

Choral music

Choral Music Generation: A Deep Hybrid Learning Approach /
LDR:03504nam a22004573i 4500 001 1157794
005 20250603111416.5
006 m o d
007 cr|nu||||||||
008 250804s2024 miu||||||m |||||||eng d
020 $a 9798382798271
035 $a (MiAaPQD)AAI31296228
035 $a AAI31296228
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Szelogowski, Daniel James, $e author. $3 1484068
245 1 0 $a Choral Music Generation: A Deep Hybrid Learning Approach / $c Daniel James Szelogowski.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2024
300 $a 1 electronic resource (301 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-12, Section: B.
500 $a Advisors: Goodwin, Susan; McAndrew, Ian Committee members: Bodily, Paul; Noir, Sophia.
502 $b Ph.D. $c Capitol Technology University $d 2024.
520 $a Despite advancements in AI and machine learning, the creation of AI-generated music that captures the complexity and nuance of classical choral arrangements has remained largely unexplored. This gap is significant, considering the intricate compositional techniques and sophisticated music theory knowledge required for classical choral music. My research is motivated by the quest to bridge this gap, aiming to develop an AI model capable of producing realistic choral compositions that adhere to the rich traditions of classical music. Additionally, I explore how AI-generated music is perceived across different listener groups, contributing insights into the intersection of AI and human perception in the arts. This study seeks to address three primary research questions: the feasibility of current machine learning architectures in generating SATB choral music, the ability of a hybrid AI model to produce compositions indistinguishable from human-created music by the general public, and the varying perception of AI-generated classical music among individuals with varying musical backgrounds. This dissertation presents the "Choral-GTN" system: a novel architecture combining a Generative Transformer Network with a rule-based post-processing system, alongside the curated "CHORAL" dataset to address the challenge of generating realistic four-part (SATB) choral music. My comprehensive approach integrates advanced deep learning techniques with sophisticated musical theory insights to produce compositions that closely mimic those created by human composers. Through a meticulously designed survey and rigorous statistical analysis, I evaluate the realism and indistinguishability of my AI-generated music across varied listener groups. The findings demonstrate that this model successfully created music that was largely indistinguishable from human compositions, achieving a significant milestone in AI-assisted music composition and music perception.
546 $a English
590 $a School code: 1847
650 4 $a Music. $3 649088
650 4 $a Computer science. $3 573171
650 4 $a Musical composition. $3 1185732
653 $a Choral music
653 $a Computational musicology
653 $a Deep learning
653 $a Music generation
653 $a Music perception
690 $a 0800
690 $a 0413
690 $a 0984
690 $a 0214
710 2 $a Capitol Technology University. $b Technology (PhD). $3 1467163
720 1 $a Goodwin, Susan $e degree supervisor.
720 1 $a McAndrew, Ian $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 85-12B.
790 $a 1847
791 $a Ph.D.
792 $a 2024
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=31296228