{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,19]],"date-time":"2026-04-19T08:05:12Z","timestamp":1776585912998,"version":"3.51.2"},"reference-count":47,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/access.2024.3476998","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T17:52:26Z","timestamp":1728496346000},"page":"169247-169262","source":"Crossref","is-referenced-by-count":2,"title":["CPTGZ: Generating Chinese Guzheng Music From Chinese Paintings Based on Diffusion Model"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9643-0757","authenticated-orcid":false,"given":"Enji","family":"Zhao","sequence":"first","affiliation":[{"name":"Department of Global Cultural Convergence, Graduate School, Kangwon National University, Chuncheon, Gangwon-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1407-8894","authenticated-orcid":false,"given":"Jiaxiang","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Global Cultural Convergence, Graduate School, Kangwon National University, Chuncheon, Gangwon-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2769-2316","authenticated-orcid":false,"given":"Moxi","family":"Cao","sequence":"additional","affiliation":[{"name":"Department of Global Cultural Convergence, Graduate School, Kangwon National University, Chuncheon, Gangwon-do, South Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref2","volume-title":"Suno: Ai-Powered Music and Lyrics Generator","author":"Ai","year":"2024"},{"key":"ref3","volume-title":"Chatgpt (Gpt-4) [large Language Model]","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/SSW.2016"},{"key":"ref5","first-page":"3918","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Oord"},{"key":"ref6","first-page":"17022","article-title":"HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kong"},{"key":"ref7","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv:2005.00341"},{"key":"ref8","article-title":"AudioGen: Textually guided audio generation","author":"Kreuk","year":"2022","journal-title":"arXiv:2209.15352"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref10","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"arXiv:2301.12503"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2023.3288409"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref13","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1109\/TASLP.2021.3129994","article-title":"SoundStream: An end-to-end neural audio codec","volume":"30","author":"Zeghidour","year":"2022","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang., Process."},{"key":"ref14","article-title":"Text-to-audio generation using instruction-tuned LLM and latent diffusion model","author":"Ghosal","year":"2023","journal-title":"arXiv:2304.13731"},{"issue":"70","key":"ref15","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref16","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023","journal-title":"arXiv:2312.15821"},{"key":"ref17","first-page":"579","article-title":"Crash: Raw audio score-based generative modeling for controllable high-resolution drum sound synthesis","volume-title":"Proc. Int. Soc. Music Inf. Retr. Conf. (ISMIR)","author":"Rouard"},{"key":"ref18","volume-title":"Riffusion\u2013stable Diffusion for Real-time Music Generation","author":"Forsgren","year":"2022"},{"key":"ref19","article-title":"Multi-instrument music synthesis with spectrogram diffusion","author":"Hawthorne","year":"2022","journal-title":"arXiv:2206.05408"},{"key":"ref20","article-title":"MuLan: A joint embedding of music audio and natural language","author":"Huang","year":"2022","journal-title":"arXiv:2208.12415"},{"key":"ref21","article-title":"MusicLM: Generating music from text","author":"Agostinelli","year":"2023","journal-title":"arXiv:2301.11325"},{"key":"ref22","article-title":"Noise2Music: Text-conditioned music generation with diffusion models","author":"Huang","year":"2023","journal-title":"arXiv:2302.03917"},{"key":"ref23","article-title":"VampNet: Music generation via masked acoustic token modeling","author":"Flores Garcia","year":"2023","journal-title":"arXiv:2307.04686"},{"key":"ref24","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023","journal-title":"arXiv:2301.11757"},{"key":"ref25","article-title":"AudioLDM 2: Learning holistic audio generation with self-supervised pretraining","author":"Liu","year":"2023","journal-title":"arXiv:2308.05734"},{"key":"ref26","article-title":"JEN-1: Text-guided universal music generation with omnidirectional diffusion models","author":"Li","year":"2023","journal-title":"arXiv:2308.04729"},{"key":"ref27","article-title":"Multi-source diffusion models for simultaneous music generation and separation","author":"Mariani","year":"2023","journal-title":"arXiv:2302.02257"},{"key":"ref28","article-title":"Adversarial audio synthesis","author":"Donahue","year":"2018","journal-title":"arXiv:1802.04208"},{"key":"ref29","article-title":"StemGen: A music generation model that listens","author":"Parker","year":"2023","journal-title":"arXiv:2312.08723"},{"key":"ref30","article-title":"Masked audio generation using a single non-autoregressive transformer","author":"Ziv","year":"2024","journal-title":"arXiv:2401.04577"},{"key":"ref31","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024","journal-title":"arXiv:2402.04825"},{"key":"ref32","volume-title":"Mubert: Ai-driven Music Generation Platform","author":"Inc","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICSP51882.2021.9408813"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IMCEC55388.2022.10019796"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-023-05195-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-19786-1"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-2756-2_8"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.visinf.2020.04.003"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3390\/app12189309"},{"key":"ref40","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref41","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref42","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"arXiv:1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3108242"},{"issue":"2","key":"ref44","first-page":"205","article-title":"The value of traditional music in the age of globalization","volume":"36","author":"Yang","year":"2018","journal-title":"Int. J. Music Educ."},{"issue":"2","key":"ref45","first-page":"292","article-title":"Intercultural understanding in music: A study on the effects of cultural background on music perception","volume":"47","author":"Futre","year":"2019","journal-title":"Psychol. Music"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"issue":"3","key":"ref47","first-page":"395","article-title":"The evolution of authorship: Work made by code","volume":"39","author":"Bridy","year":"2021","journal-title":"Columbia J. Law Arts"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10380310\/10711246.pdf?arnumber=10711246","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:48:33Z","timestamp":1732668513000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10711246\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3476998","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}