An automatic music generation and evaluation method based on transfer learning
Copyright: © 2023 Guo et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited..
In recent years, deep learning has seen remarkable progress in many fields, especially with many excellent pre-training models emerged in Natural Language Processing(NLP). However, these pre-training models can not be used directly in music generation tasks due to the different representations between music symbols and text. Compared with the traditional presentation method of music melody that only includes the pitch relationship between single notes, the text-like representation method proposed in this paper contains more melody information, including pitch, rhythm and pauses, which expresses the melody in a form similar to text and makes it possible to use existing pre-training models in symbolic melody generation. In this paper, based on the generative pre-training-2(GPT-2) text generation model and transfer learning we propose MT-GPT-2(music textual GPT-2) model that is used in music melody generation. Then, a symbolic music evaluation method(MEM) is proposed through the combination of mathematical statistics, music theory knowledge and signal processing methods, which is more objective than the manual evaluation method. Based on this evaluation method and music theories, the music generation model in this paper are compared with other models (such as long short-term memory (LSTM) model,Leak-GAN model and Music SketchNet). The results show that the melody generated by the proposed model is closer to real music.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:18 |
---|---|
Enthalten in: |
PloS one - 18(2023), 5 vom: 25., Seite e0283103 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Guo, Yi [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Completed 12.05.2023 Date Revised 05.06.2023 published: Electronic-eCollection Citation Status MEDLINE |
---|
doi: |
10.1371/journal.pone.0283103 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM356663876 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM356663876 | ||
003 | DE-627 | ||
005 | 20231226070935.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1371/journal.pone.0283103 |2 doi | |
028 | 5 | 2 | |a pubmed24n1188.xml |
035 | |a (DE-627)NLM356663876 | ||
035 | |a (NLM)37163469 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Guo, Yi |e verfasserin |4 aut | |
245 | 1 | 3 | |a An automatic music generation and evaluation method based on transfer learning |
264 | 1 | |c 2023 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 12.05.2023 | ||
500 | |a Date Revised 05.06.2023 | ||
500 | |a published: Electronic-eCollection | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Copyright: © 2023 Guo et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. | ||
520 | |a In recent years, deep learning has seen remarkable progress in many fields, especially with many excellent pre-training models emerged in Natural Language Processing(NLP). However, these pre-training models can not be used directly in music generation tasks due to the different representations between music symbols and text. Compared with the traditional presentation method of music melody that only includes the pitch relationship between single notes, the text-like representation method proposed in this paper contains more melody information, including pitch, rhythm and pauses, which expresses the melody in a form similar to text and makes it possible to use existing pre-training models in symbolic melody generation. In this paper, based on the generative pre-training-2(GPT-2) text generation model and transfer learning we propose MT-GPT-2(music textual GPT-2) model that is used in music melody generation. Then, a symbolic music evaluation method(MEM) is proposed through the combination of mathematical statistics, music theory knowledge and signal processing methods, which is more objective than the manual evaluation method. Based on this evaluation method and music theories, the music generation model in this paper are compared with other models (such as long short-term memory (LSTM) model,Leak-GAN model and Music SketchNet). The results show that the melody generated by the proposed model is closer to real music | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Research Support, Non-U.S. Gov't | |
700 | 1 | |a Liu, Yangcheng |e verfasserin |4 aut | |
700 | 1 | |a Zhou, Ting |e verfasserin |4 aut | |
700 | 1 | |a Xu, Liang |e verfasserin |4 aut | |
700 | 1 | |a Zhang, Qianxue |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t PloS one |d 2006 |g 18(2023), 5 vom: 25., Seite e0283103 |w (DE-627)NLM167327399 |x 1932-6203 |7 nnns |
773 | 1 | 8 | |g volume:18 |g year:2023 |g number:5 |g day:25 |g pages:e0283103 |
856 | 4 | 0 | |u http://dx.doi.org/10.1371/journal.pone.0283103 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 18 |j 2023 |e 5 |b 25 |h e0283103 |