{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T02:49:18Z","timestamp":1772592558143,"version":"3.50.1"},"reference-count":28,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9746818","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"4738-4742","source":"Crossref","is-referenced-by-count":5,"title":["Training Strategies for Automatic Song Writing: A Unified Framework Perspective"],"prefix":"10.1109","author":[{"given":"Tao","family":"Qian","sequence":"first","affiliation":[{"name":"Renmin University of China,School of Information,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiatong","family":"Shi","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuai","family":"Guo","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Information,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Wu","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qin","family":"Jin","sequence":"additional","affiliation":[{"name":"Renmin University of China,School of Information,P.R.China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref10","first-page":"5926","article-title":"Mass: Masked sequence to sequence pre-training for language generation","author":"song","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413721"},{"key":"ref12","article-title":"Tonal harmony","author":"quinn","year":"2019","journal-title":"The Oxford Handbook of Critical Concepts in Music Theory"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639674"},{"key":"ref14","first-page":"5410","article-title":"Almost unsupervised text to speech and automatic speech recognition","author":"ren","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1009"},{"key":"ref16","first-page":"820","article-title":"Dual learning for machine translation","volume":"29","author":"he","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268950"},{"key":"ref18","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref19","article-title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"lewis","year":"2019"},{"key":"ref28","first-page":"359","article-title":"Using dynamic time warping to find patterns in time series","volume":"10","author":"berndt","year":"1994","journal-title":"KDD Workshop"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32233-5_39"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220105"},{"key":"ref3","article-title":"Music transformer","author":"huang","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3424116"},{"key":"ref5","first-page":"84","article-title":"icomposer: An automatic songwriting system for chinese popular music","author":"lee","year":"2019","journal-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1015"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"13798","DOI":"10.1609\/aaai.v35i15.17626","article-title":"Songmass: Automatic song writing with pre-training and alignment constraint","volume":"35","author":"sheng","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413671"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ISM.2020.00040"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.68"},{"key":"ref20","article-title":"Giantmidi-piano: A large-scale midi dataset for classical piano music","author":"kong","year":"2020"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1609\/aaai.v35i1.16091","article-title":"Compound word transformer: Learning to compose full-song music over dynamic directed hypergraphs","volume":"35","author":"hsiao","year":"2021","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"ref21","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","author":"hawthorne","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682389"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref26","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"3rd International Conference on Learning Representations ICLR 2015"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/319463.319470"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09746818.pdf?arnumber=9746818","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T03:25:21Z","timestamp":1727061921000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9746818\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9746818","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}