{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T15:13:08Z","timestamp":1781017988308,"version":"3.54.1"},"reference-count":56,"publisher":"Zhejiang University Press","issue":"1","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Front Inform Technol Electron Eng"],"published-print":{"date-parts":[[2024,1]]},"DOI":"10.1631\/fitee.2300359","type":"journal-article","created":{"date-parts":[[2024,2,8]],"date-time":"2024-02-08T03:04:06Z","timestamp":1707361446000},"page":"106-120","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Style-conditioned music generation with Transformer-GANs","\u57fa\u4e8eTransformer-GANs\u751f\u6210\u6709\u98ce\u683c\u8c03\u8282\u7684\u97f3\u4e50"],"prefix":"10.1631","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0589-8157","authenticated-orcid":false,"given":"Weining","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0016-9055","authenticated-orcid":false,"given":"Xiaofen","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"635","published-online":{"date-parts":[[2024,2,8]]},"reference":[{"key":"ref1","first-page":"747","article-title":"MIDI-VAE: modeling dynamics and instrumentation of music with applications to style transfer","author":"Brunner","year":"2018","journal-title":"Proc 19th Int Society for Music Information Retrieval Conf"},{"key":"ref2","first-page":"1899","article-title":"Encoding musical style with Transformer autoencoders","author":"Choi","year":"2020","journal-title":"Proc 37th Int Conf on Machine Learning"},{"key":"ref3","volume-title":"MidiBERT-Piano: large-scale pretraining for symbolic music understanding.","author":"Chou","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2008.05.028"},{"key":"ref5","first-page":"4171","article-title":"BERT: pretraining of deep bidirectional Transformers for language understanding","volume-title":"Proc Conf of the North American Chapter of the Association for Computational Linguistics","author":"Devlin","year":"2019"},{"key":"ref6","first-page":"190","article-title":"Convolutional generative adversarial networks with binary neurons for polyphonic music generation","author":"Dong","year":"2018","journal-title":"Proc 19th Int Society for Music Information Retrieval Conf"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref8","first-page":"101","article-title":"MusPy: a toolkit for symbolic music generation","author":"Dong","year":"2020","journal-title":"Proc 21st Int Society for Music Information Retrieval Conf"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"Proc 9th Int Conf on Learning Representations"},{"key":"ref10","first-page":"384","article-title":"Learning to generate music with sentiment","author":"Ferreira","year":"2021","journal-title":"Proc 20th Int Society for Music Information Retrieval Conf"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2017.2737984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16091"},{"key":"ref14","article-title":"Music Transformer: generating music with long-term structure","author":"Huang","year":"2019","journal-title":"Proc 7th Int Conf on Learning Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref16","first-page":"318","article-title":"EMOPIA: a multimodal pop piano dataset for emotion recognition and emotion-based music generation","author":"Hung","year":"2021","journal-title":"Proc 22nd Int Society for Music Information Retrieval Conf"},{"key":"ref17","article-title":"Categorical reparameterization with Gumbel-Softmax","author":"Jang","year":"2017","journal-title":"Proc 5th Int Conf on Learning Representations"},{"key":"ref18","article-title":"Modeling self-repetition in music generation using generative adversarial networks","author":"Jhamtani","year":"2019","journal-title":"Proc 36th Int Conf on Machine Learning"},{"key":"ref19","volume-title":"Stylistic melody generation with conditional variational auto-encoder.","author":"Jiang","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/icassp40776.2020.9054554"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-819714-1.00024-5"},{"key":"ref22","first-page":"5156","article-title":"Transformers are RNNs: fast autoregressive transformers with linear attention","author":"Katharopoulos","year":"2020","journal-title":"Proc 37th Int Conf on Machine Learning"},{"key":"ref23","article-title":"Rethinking positional encoding in language pretraining","author":"Ke","year":"2021","journal-title":"Proc 9th Int Conf on Learning Representations"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.2307\/3680598"},{"key":"ref25","volume-title":"MIDI-Sandwich2: RNN-based hierarchical multimodal fusion generation VAE networks for multi-track symbolic music generation.","author":"Liang","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/icmew56448.2022.9859531"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/icme46284.2020.9102870"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/icmla.2018.00114"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1162\/comj.2010.34.1.41"},{"key":"ref30","first-page":"58","article-title":"MahlerNet: unbounded orchestral music with neural networks","volume-title":"Proc Nordic Sound and Music Computing Conf and the Interactive Sonification Workshop","author":"Lousseief","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-2756-2_8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/icsc.2018.00077"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/icmew59549.2023.00057"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16117"},{"key":"ref35","article-title":"RelGAN: relational generative adversarial networks for text generation","author":"Nie","year":"2019","journal-title":"Proc 7th Int Conf on Learning Representations"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3758-9"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413721"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/app10093053"},{"key":"ref39","first-page":"4364","article-title":"A hierarchical latent vector model for learning long-term structure in music","author":"Roberts","year":"2018","journal-title":"Proc 35th Int Conf on Machine Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3161851"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/access.2022.3169744"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1162\/014892601300126106"},{"key":"ref43","article-title":"JazzGAN: improvising with generative adversarial networks","author":"Trieu","year":"2018","journal-title":"Proc 6th Int Workshop on Musical Metacreation"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref45","volume-title":"Project magenta: generating long-term structure in songs and stories.","author":"Waite","year":"2016"},{"key":"ref46","volume-title":"A review of intelligent music generation systems.","author":"Wang","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/icmew56448.2022.9859286"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref49","first-page":"142","article-title":"The jazz Transformer on the front line: exploring the shortcomings of AI-composed music through quantitative measures","author":"Wu","year":"2020","journal-title":"Proc 21st Int Society for Music Information Retrieval Conf"},{"key":"ref50","volume-title":"Transformer-XL based music generation with multiple sequences of time-valued notes.","author":"Wu","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3849-7"},{"key":"ref52","first-page":"324","article-title":"MidiNet: a convolutional generative adversarial network for symbolic-domain music generation","author":"Yang","year":"2017","journal-title":"Proc 18th Int Society for Music Information Retrieval Conf"},{"key":"ref53","first-page":"1376","article-title":"Museformer: Trans-former with fine- and coarse-grained attention for music generation","author":"Yu","year":"2022","journal-title":"Proc 36th Conf on Neural Information Processing Systems"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2020.2990746"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548084"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-23570-3_43"}],"container-title":["Frontiers of Information Technology & Electronic Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2300359.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1631\/FITEE.2300359\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1631\/FITEE.2300359.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T06:58:35Z","timestamp":1771657115000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1631\/FITEE.2300359"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":56,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["359"],"URL":"https:\/\/doi.org\/10.1631\/fitee.2300359","relation":{},"ISSN":["2095-9184","2095-9230"],"issn-type":[{"value":"2095-9184","type":"print"},{"value":"2095-9230","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"21 May 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"All the authors declare that they have no conflict of interest.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethics guidelines"}}]}}