東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Differential Music : = Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Differential Music :/
Reminder of title:	Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals.
Author:	Rafraf, Hooman.
Description:	1 online resource (90 pages)
Notes:	Source: Dissertations Abstracts International, Volume: 83-12, Section: B.
Contained By:	Dissertations Abstracts International83-12B.
Subject:	Musical composition. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29066282click for full text (PQDT)
ISBN:	9798802704806

Differential Music : = Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals.
Rafraf, Hooman.

Differential Music :Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals. - 1 online resource (90 pages)

Source: Dissertations Abstracts International, Volume: 83-12, Section: B.

Thesis (Ph.D.)--University of Florida, 2022.

Includes bibliographical references

To be able to teach music to an artificial-intelligence (AI) model, regardless of its functionality, the music has to be encoded in a way that is understandable for a computer program. Examples of such "representations" of music include MIDI, piano-roll, MP3, MusicXML, etc. In the AI field, the representations are normally in the form of matrices of numbers. This research introduces a generative AI model for automated music composition with LSTM networks that uses a novel representation of music that is based on melodic and harmonic intervals in music rather than absolute pitch. Melodies are encoded as a series of intervals rather than a series of pitches, and chords are encoded as the set of intervals that each chord note makes with the melody at each moment. We will first introduce some of the suitable AI models as well as the literature on the use of artificial intelligence and machine learning in musical creativity. We will then focus on LSTM-based models and how they have been used for automated music generation. The existing representations are introduced and discussed. We will then build a model using LSTM networks and use our novel representation to train the model to write music. The resulting compositions are included and discussed as well.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2023

Mode of access: World Wide Web

ISBN: 9798802704806Subjects--Topical Terms:

3289630
Musical composition.
Subjects--Index Terms:

Automated music generationIndex Terms--Genre/Form:

542853
Electronic books.

Differential Music : = Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals.
LDR:02704nmm a2200397K 4500 001 2363743
005 20231127094546.5
006 m o d
007 cr mn ---uuuuu
008 241011s2022 xx obm 000 0 eng d
020 $a 9798802704806
035 $a (MiAaPQ)AAI29066282
035 $a AAI29066282
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Rafraf, Hooman. $3 3704520
245 1 0 $a Differential Music : $b Automated Music Generation Using LSTM Networks with Representation Based on Melodic and Harmonic Intervals.
264 0 $c 2022
300 $a 1 online resource (90 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: 83-12, Section: B.
500 $a Advisor: Sain, James Paul.
502 $a Thesis (Ph.D.)--University of Florida, 2022.
504 $a Includes bibliographical references
520 $a To be able to teach music to an artificial-intelligence (AI) model, regardless of its functionality, the music has to be encoded in a way that is understandable for a computer program. Examples of such "representations" of music include MIDI, piano-roll, MP3, MusicXML, etc. In the AI field, the representations are normally in the form of matrices of numbers. This research introduces a generative AI model for automated music composition with LSTM networks that uses a novel representation of music that is based on melodic and harmonic intervals in music rather than absolute pitch. Melodies are encoded as a series of intervals rather than a series of pitches, and chords are encoded as the set of intervals that each chord note makes with the melody at each moment. We will first introduce some of the suitable AI models as well as the literature on the use of artificial intelligence and machine learning in musical creativity. We will then focus on LSTM-based models and how they have been used for automated music generation. The existing representations are introduced and discussed. We will then build a model using LSTM networks and use our novel representation to train the model to write music. The resulting compositions are included and discussed as well.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2023
538 $a Mode of access: World Wide Web
650 4 $a Musical composition. $3 3289630
650 4 $a Artificial intelligence. $3 516317
650 4 $a Music. $3 516178
650 4 $a Computer science. $3 523869
653 $a Automated music generation
653 $a Long short-term memory
653 $a Melodic intervals
653 $a Harmonic intervals
655 7 $a Electronic books. $2 lcsh $3 542853
690 $a 0214
690 $a 0800
690 $a 0984
690 $a 0413
710 2 $a ProQuest Information and Learning Co. $3 783688
710 2 $a University of Florida. $b Music. $3 3551813
773 0 $t Dissertations Abstracts International $g 83-12B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29066282 $z click for full text (PQDT)