{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:05:13Z","timestamp":1766138713166,"version":"3.37.3"},"reference-count":86,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","award":["MOE-MOESOL2021-0005"],"award-info":[{"award-number":["MOE-MOESOL2021-0005"]}],"id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3408060","type":"journal-article","created":{"date-parts":[[2024,5,31]],"date-time":"2024-05-31T17:37:34Z","timestamp":1717177054000},"page":"10545-10558","source":"Crossref","is-referenced-by-count":1,"title":["Symbolic Music Generation From Graph-Learning-Based Preference Modeling and Textual Queries"],"prefix":"10.1109","volume":"26","author":[{"given":"Xichu","family":"Ma","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5183-1248","authenticated-orcid":false,"given":"Yuchen","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0123-1260","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5539\/elt.v6n2p113"},{"issue":"1","key":"ref2","first-page":"39","article-title":"Early language learning with and without music","volume":"42","author":"Fisher","year":"2001","journal-title":"Reading Horizons: J. Lit. Lang. Arts"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240691"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2018.01114"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1177\/0305735619878497"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.4146\/jjspopsy.2013-1222"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548169"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911489"},{"article-title":"Jukebox: A generative model for music","year":"2020","author":"Dhariwal","key":"ref9"},{"year":"2022","key":"ref10","article-title":"Mubert text-to-music"},{"article-title":"MusicLM: Generating music from text","year":"2023","author":"Agostinelli","key":"ref11"},{"article-title":"Exploring the efficacy of pre-trained checkpoints in text-to-music generation task","year":"2022","author":"Wu","key":"ref12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-37734-2_58"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450028"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350607"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3372278.3390677"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2021.102531"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/1077\/1\/012026"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-201218"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113248"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2008.22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2012.06.118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3125486.3125492"},{"key":"ref25","first-page":"2643","article-title":"Deep content-based music recommendation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"26","author":"Oord","year":"2013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2017.8335200"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654940"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.09.013"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3477314.3507099"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3340631.3394874"},{"volume-title":"This is Your Brain on Music: The Science of a Human Obsession","year":"2006","author":"Levitin","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401181"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219886"},{"key":"ref34","first-page":"324","article-title":"MidiNet: A convolutional generative adversarial network for symbolic-domain music generation","volume-title":"Int. Soc. Music Inf. Retrieval","author":"Yang","year":"2017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/SAMI50585.2021.9378654"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5539\/cis.v11n3p50"},{"key":"ref37","first-page":"48","article-title":"A first look at music composition using LSTM recurrent neural networks","volume":"103","author":"Eck","year":"2002","journal-title":"Istituto Dalle Molle Di Studi Sull Intelligenza Artificiale"},{"article-title":"Music transcription modelling and composition using deep learning","year":"2016","author":"Sturm","key":"ref38"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-65172-9_48"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11312"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461724"},{"key":"ref42","article-title":"An improved relative self-attention mechanism for transformer with application to music generation","author":"Huang","year":"2018","journal-title":"arXiv:1809.04281"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475195"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1285"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref47","first-page":"1376","article-title":"Museformer: Transformer with fine-and coarse-grained attention for music generation","volume":"35","author":"Yu","year":"2022","journal-title":"Proc. Adv. Neural Inf. Process. Syst."},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16117"},{"issue":"8","key":"ref49","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"article-title":"MuLan: A joint embedding of music audio and natural language","year":"2022","author":"Huang","key":"ref50"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ITNEC.2019.8729266"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICSC.2018.00077"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICEICT53123.2021.9531287"},{"key":"ref54","first-page":"596","article-title":"Deep music analogy via latent representation disentanglement","author":"Yang","year":"2019","journal-title":"Int. Soc. Music Inf. Retrieval"},{"key":"ref55","first-page":"384","article-title":"Learning to generate music with sentiment","author":"Ferreira","year":"2019","journal-title":"Int. Soc. Music Inf. Retrieval"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3163543"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3169744"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3113829"},{"key":"ref59","first-page":"247","article-title":"Automated music generation for visual art through emotion","volume-title":"Proc. 11th Int. Conf. Comput. Creativity","author":"Tan","year":"2020"},{"key":"ref60","first-page":"100","article-title":"YM2413-MDB: A multi-instrumental FM video game music dataset with emotion annotations","author":"Choi","year":"2022","journal-title":"Int. Soc. Music Inf. Retrieval"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aiide.v16i1.7408"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/AIMV53313.2021.9670959"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW56448.2022.9859286"},{"key":"ref64","first-page":"621","article-title":"Chord generation from symbolic melody using BLSTM networks","author":"Lim","year":"2017","journal-title":"Int. Soc. Music Inf. Retrieval"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220105"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32233-5_39"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548357"},{"key":"ref68","first-page":"84","article-title":"iComposer: An automatic songwriting system for chinese popular music","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics (Demonstrations)","author":"Lee","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3161851"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2021.1873392"},{"key":"ref71","first-page":"657","article-title":"Generating nontrivial melodies for music as a service","author":"Teng","year":"2017","journal-title":"Int. Soc. Music Inf. Retrieval"},{"key":"ref72","first-page":"90","article-title":"Functional harmony recognition of symbolic music data with multi-task recurrent neural networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval","author":"Chen","year":"2018"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/HPBDIS.2019.8735487"},{"article-title":"Inspecting and interacting with meaningful music representations using VAE","year":"2019","author":"Yang","key":"ref74"},{"article-title":"Learning-based methods for comparing sequences, with applications to audio-to-midi alignment and matching","year":"2016","author":"Raffel","key":"ref75"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref77","first-page":"318","article-title":"EMOPIA: A multi-modal pop piano dataset for emotion recognition and emotion-based music generation","author":"Hung","year":"2021","journal-title":"Int. Soc. Music Inf. Retrieval"},{"article-title":"CTRL: A conditional transformer language model for controllable generation","year":"2019","author":"Keskar","key":"ref78"},{"key":"ref79","first-page":"662","article-title":"Learning interpretable representation for controllable polyphonic music generation","author":"Wang","year":"2020","journal-title":"Int. Soc. Music Inf. Retrieval"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.5220\/0006597705010506"},{"key":"ref81","first-page":"1899","article-title":"Encoding musical style with transformer autoencoders","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Choi","year":"2020"},{"key":"ref82","first-page":"109","article-title":"Music FaderNets: Controllable music generation based on high-level features via low-level feature modelling","author":"Tan","year":"2020","journal-title":"Int. Soc. Music Inf. Retrieval"},{"article-title":"A generalization of transformer networks to graphs","year":"2020","author":"Dwivedi","key":"ref83"},{"key":"ref84","article-title":"Performance RNN: Generating music with expressive timing and dynamics","author":"Simon","year":"2017","journal-title":"Magenta Blog"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/523"},{"key":"ref86","first-page":"659","article-title":"What is missing in deep music generation? A study of repetition and structure in popular music","author":"Dai","year":"2022","journal-title":"Int. Soc. Music Inf. Retrieval"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10543064.pdf?arnumber=10543064","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:24:10Z","timestamp":1732667050000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10543064\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3408060","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2024]]}}}