{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T01:18:02Z","timestamp":1740100682460,"version":"3.37.3"},"reference-count":29,"publisher":"IEEE","license":[{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T00:00:00Z","timestamp":1631059200000},"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","award":["61877060"],"award-info":[{"award-number":["61877060"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,9,8]]},"DOI":"10.23919\/dafx51585.2021.9768275","type":"proceedings-article","created":{"date-parts":[[2022,5,11]],"date-time":"2022-05-11T20:33:41Z","timestamp":1652301221000},"page":"308-315","source":"Crossref","is-referenced-by-count":2,"title":["An Audio-Visual Fusion Piano Transcription Approach Based on Strategy"],"prefix":"10.23919","author":[{"given":"Xianke","family":"Wang","sequence":"first","affiliation":[{"name":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"}]},{"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"}]},{"given":"Juanting","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"}]},{"given":"Weiming","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"}]},{"given":"Wenqing","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications Huazhong University of Science and Technology,Smart Internet Technology Lab,Wuhan,China,430074"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref2","article-title":"Enabling fac-torized piano music modeling and generation with the MAESTRO dataset","volume-title":"Proceedings of International Conference on Learning Representations","author":"Hawthorne","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3409501.3409540"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2015.07.027"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00165"},{"key":"ref6","first-page":"291","article-title":"Polyphonic piano note transcription with non-negative matrix factorization of dif-ferential spectrogram","volume-title":"Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing","author":"Gao","year":"2017"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2666183"},{"key":"ref8","first-page":"584","article-title":"An attack\/decay model for piano transcription","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference","author":"Cheng","year":"2016"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3390\/app7090901"},{"key":"ref10","first-page":"391","article-title":"A parallel fusion approach to piano music transcription based on convolutional neural network","volume-title":"Proceedings of IEEE International Con-ference on Acoustics, Speech and Signal Processing","author":"Liu","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MMRP.2019.00023"},{"key":"ref12","article-title":"High-resolution piano tran-scription with pedals by regressing onsets and offsets times","author":"Kong","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"470","article-title":"A comparative study of neural models for polyphonic music sequence transduction","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference","author":"Ycart","year":"2019"},{"key":"ref14","first-page":"670","article-title":"Adversarial learning for improved onsets and frames music transcription","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference","author":"Kim","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178333"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref17","first-page":"454","article-title":"Blending acoustic and language model predictions for automatic music tran-scription","volume-title":"Proceedings of the International Society for Music Information Retrieval Conference","author":"Ycart","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2013.6727030"},{"key":"ref19","article-title":"Detection of piano keys pressed in video","volume-title":"Dept. of Comput. Sci., Stanford Univ","author":"Suteparuk","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5803-1"},{"volume-title":"claVision: visual automatic piano music tran-scription","year":"2014","author":"Akbari","key":"ref21"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2473702"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053115"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCE.2014.6775884"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768276"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref29","first-page":"367","article-title":"mir_eval: A transparent implementation of common mir metrics","volume-title":"Pro-ceedings of the International Society for Music Information Retrieval Conference","author":"Raffel","year":"2014"}],"event":{"name":"2021 24th International Conference on Digital Audio Effects (DAFx)","start":{"date-parts":[[2021,9,8]]},"location":"Vienna, Austria","end":{"date-parts":[[2021,9,10]]}},"container-title":["2021 24th International Conference on Digital Audio Effects (DAFx)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9768159\/9768211\/09768275.pdf?arnumber=9768275","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T01:52:35Z","timestamp":1706061155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9768275\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,8]]},"references-count":29,"URL":"https:\/\/doi.org\/10.23919\/dafx51585.2021.9768275","relation":{},"subject":[],"published":{"date-parts":[[2021,9,8]]}}}