{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:31:19Z","timestamp":1770834679341,"version":"3.50.1"},"reference-count":79,"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\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["328416299"],"award-info":[{"award-number":["328416299"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"publisher","award":["DFG MU 2686\/10-2"],"award-info":[{"award-number":["DFG MU 2686\/10-2"]}],"id":[{"id":"10.13039\/501100001659","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.2024.3356980","type":"journal-article","created":{"date-parts":[[2024,1,24]],"date-time":"2024-01-24T18:44:17Z","timestamp":1706121857000},"page":"1214-1225","source":"Crossref","is-referenced-by-count":10,"title":["Source Separation of Piano Concertos Using Musically Motivated Augmentation Techniques"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2235-8655","authenticated-orcid":false,"given":"Yigitcan","family":"\u00d6zer","sequence":"first","affiliation":[{"name":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6062-7524","authenticated-orcid":false,"given":"Meinard","family":"M\u00fcller","sequence":"additional","affiliation":[{"name":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat Erlangen-Nurnberg, Erlangen, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9780511582721.006"},{"key":"ref2","first-page":"493","article-title":"Source separation of piano concertos with test-time adaptation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"zer","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2874719"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21105\/joss.01667"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21105\/joss.02154"},{"key":"ref6","first-page":"745","article-title":"Singing voice separation with deep U-net convolutional networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Jansson","year":"2017"},{"key":"ref7","first-page":"334","article-title":"Wave-U-Net: A multi-scale neural network for end-to-end audio source separation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Stoller","year":"2018"},{"key":"ref8","article-title":"Music source separation in the waveform domain","author":"Dfossez","year":"2021"},{"key":"ref9","first-page":"1","article-title":"Hybrid spectrogram and waveform source separation","volume-title":"Proc. ISMIR Workshop Music Source Separation","author":"Dfossez","year":"2021"},{"key":"ref10","article-title":"CatNet: Music source separation system with mix-audio augmentation","author":"Song","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096956"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3271145"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93764-9_28"},{"key":"ref14","article-title":"The MUSDB18 corpus for music separation","author":"Rafii","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.3389\/frsip.2021.808395"},{"key":"ref16","first-page":"55","article-title":"Monaural score-informed source separation for classical music using convolutional neural networks","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Miron","year":"2017"},{"key":"ref17","first-page":"231","article-title":"Score-informed source separation of choral music","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Gover","year":"2020"},{"key":"ref18","first-page":"733","article-title":"Deep learning based source separation applied to choir ensembles","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Petermann","year":"2020"},{"key":"ref19","first-page":"726","article-title":"Improving choral music separation through expressive synthesized data from sampled instruments","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Chen","year":"2022"},{"key":"ref20","first-page":"155","article-title":"MedleyDB: A multitrack dataset for annotation-intensive MIR research","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Bittner","year":"2014"},{"key":"ref21","first-page":"551","article-title":"Freischtz digitalwhen computer science meets musicology","volume-title":"Proc. Festschrift frJoachimVeitzum Geburtstag","author":"Mller","year":"2016"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CBMI.2016.7500240"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2856090"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.48"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.17743\/jaes.2020.0056"},{"key":"ref26","first-page":"625","article-title":"EnsembleSet: A new high quality dataset for chamber ensemble separation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Sarkar","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP48831.2020.9287146"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.5334\/tismir.160"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.858005"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3069302"},{"key":"ref32","article-title":"Method for the subjective assessment of intermediate quality level of audio systems","volume-title":"Proc. Int. Telecommun. Union Radiocommunication Assem.","author":"Series","year":"2015"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7177973"},{"key":"ref34","first-page":"1","article-title":"Phase-aware speech enhancement with deep complex U-Net","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Choi","year":"2018"},{"key":"ref35","first-page":"1","article-title":"Deep complex networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Trabelsi","year":"2018"},{"key":"ref36","first-page":"1","article-title":"CWS-PResUNet: Music source separation with channel-wise subband phase-aware ResUNet","volume-title":"Proc. ISMIR Workshop Music Source Separation","author":"Liu","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094992"},{"key":"ref38","first-page":"192","article-title":"Investigating U-Nets with various intermediate blocks for spectrogram-based singing voice separation","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Choi","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASSP.1984.1164317"},{"key":"ref40","first-page":"17","article-title":"Real-time spectrogram inversion using phase gradient heap integration","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Prua","year":"2016"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2915167"},{"key":"ref42","first-page":"1","article-title":"KUIELab-MDX-Net: A two-stream neural network for music demixing","volume-title":"Proc. ISMIR Workshop Music Source Separation","author":"Kim","year":"2021"},{"key":"ref43","article-title":"From sparse models to timbre learning: New methods for musical source separation","author":"Burred","year":"2009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952158"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746530"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414044"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref49","first-page":"159","article-title":"Conditioned-U-Net: Introducing a control mechanism in the U-Net for multiple source separations","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Meseguer-Brocal","year":"2019"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2019.8902810"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2050716"},{"key":"ref52","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":"ref53","first-page":"446","article-title":"ATEPP: A dataset of automatically transcribed expressive piano performance","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Zhang","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2159701"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2016.1182191"},{"key":"ref56","first-page":"229","article-title":"RWC music database: Music genre database and musical instrument sound database","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Goto","year":"2003"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747612"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095061"},{"key":"ref59","first-page":"235","article-title":"Unison source separation","volume-title":"Proc. Int. Conf. Digit. Audio Effects","author":"Stter","year":"2014"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471650"},{"key":"ref61","article-title":"Fast","volume-title":"Proc. KDD Workshop Mining Temporal Sequential Data","author":"Salvador","year":"2004"},{"key":"ref62","first-page":"492","article-title":"MATCH: A music alignment tool chest","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"Dixon","year":"2005"},{"key":"ref63","first-page":"27","article-title":"Polyphonic audio matching for score following and intelligent audio editors","volume-title":"Proc. Int. Comput. Music Conf.","author":"Dannenberg","year":"2003"},{"key":"ref64","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-69808-9","volume-title":"Fundamentals of Music ProcessingUsing Python and Jupyter Notebooks","author":"Mller","year":"2021"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959972"},{"key":"ref66","first-page":"749","article-title":"Using activation functions for improving measure-level audio synchronization","volume-title":"Proc. Int. Soc. Music Inf. Retrieval Conf.","author":"zer","year":"2022"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2973795"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.21105\/joss.03434"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7471739"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2013.2294023"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1966.tb01706.x"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1993.319366"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195104806.001.0001"},{"key":"ref74","first-page":"9229","article-title":"Test-time training with self-supervision for generalization under distribution shifts","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sun","year":"2020"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937266"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095153"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760550"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2109381"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10413592.pdf?arnumber=10413592","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,6]],"date-time":"2024-02-06T22:16:01Z","timestamp":1707257761000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10413592\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/taslp.2024.3356980","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}