{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T16:39:06Z","timestamp":1773938346913,"version":"3.50.1"},"reference-count":55,"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\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62277019"],"award-info":[{"award-number":["62277019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2024.3426303","type":"journal-article","created":{"date-parts":[[2024,7,30]],"date-time":"2024-07-30T17:58:40Z","timestamp":1722362320000},"page":"3618-3630","source":"Crossref","is-referenced-by-count":1,"title":["A Two-Stage Audio-Visual Fusion Piano Transcription Model Based on the Attention Mechanism"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3621-8859","authenticated-orcid":false,"given":"Yuqing","family":"Li","sequence":"first","affiliation":[{"name":"Hubei Key Laboratory of Smart Internet Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7037-9800","authenticated-orcid":false,"given":"Xianke","family":"Wang","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Smart Internet Technology, Wuhan, China"}]},{"given":"Ruimin","family":"Wu","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Smart Internet Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4705-7189","authenticated-orcid":false,"given":"Wei","family":"Xu","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Smart Internet Technology, Wuhan, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6277-2959","authenticated-orcid":false,"given":"Wenqing","family":"Cheng","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Smart Internet Technology, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2869928"},{"key":"ref2","first-page":"23","article-title":"Onsets and frames: Dual-objective piano transcription","volume-title":"Proc. 19th Int. Soc. Music Inf. Retrieval Conf.","author":"Hawthorne","year":"2018"},{"key":"ref3","first-page":"1","article-title":"Enabling factorized piano music modeling and generation with the maestro dataset","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hawthorne","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3121991"},{"key":"ref5","first-page":"709","article-title":"HPPNET: Modeling the harmonic structure and pitch invariance in piano transcription","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Wei","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","first-page":"246","article-title":"Sequence-to-sequence piano transcription with transformers","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Hawthorne","year":"2021"},{"key":"ref8","first-page":"215","article-title":"Automatic piano transcription with hierarchical frequency-time transformer","author":"Toyama","year":"2023","journal-title":"Proc. Int. Soc. Music Inf. Retrieval Conf."},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2473702"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5803-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3409501.3409540"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053115"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMM.333-335.742"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768275"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00165"},{"key":"ref17","article-title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","author":"Bai","year":"2018"},{"key":"ref18","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2038819"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.908129"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2008.4517557"},{"key":"ref23","article-title":"Multiple fundamental frequency extraction for MIREX 2012","volume-title":"Proc. Music Inf. Retrieval Eval. Exchange","author":"Dressler","year":"2012"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2034186"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2260741"},{"key":"ref26","first-page":"584","article-title":"An attack\/decay model for piano transcription","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Cheng","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952164"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2012.6287832"},{"key":"ref29","first-page":"475","article-title":"On the potential of simple framewise approaches to piano transcription","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Kelz","year":"2016"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref31","first-page":"3325","article-title":"Audeo: Audio generation for a silent performance video","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Su","year":"2020"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2023.109134"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746789"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IVCNZ.2013.6727030"},{"key":"ref35","article-title":"Detection of piano keys pressed in video","author":"Suteparuk","year":"2014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03939-7"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/83.277898"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2015.07.027"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-021-00221-6"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0022-2836(81)90087-5"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.119491"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-25751-8_12"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref47","first-page":"3","article-title":"Constant-Q transform toolbox for music processing","volume-title":"Proc. 7th Sound Music Comput. Conf.","author":"Schrkhuber","year":"2010"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548411"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSPW59220.2023.10193618"},{"key":"ref54","first-page":"367","article-title":"MIR_EVAL: A transparent implementation of common MIR metrics","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Raffel","year":"2014"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6570655\/10304349\/10614622.pdf?arnumber=10614622","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T06:58:12Z","timestamp":1722409092000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10614622\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3426303","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}