{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T03:32:38Z","timestamp":1768966358295,"version":"3.49.0"},"reference-count":108,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2018,9,1]],"date-time":"2018-09-01T00:00:00Z","timestamp":1535760000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"name":"Austrian FFG","award":["858514"],"award-info":[{"award-number":["858514"]}]},{"DOI":"10.13039\/501100001659","name":"German Research Foundation","doi-asserted-by":"crossref","award":["DFG-MU 2686\/10-1"],"award-info":[{"award-number":["DFG-MU 2686\/10-1"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1109\/taslp.2018.2830113","type":"journal-article","created":{"date-parts":[[2018,4,26]],"date-time":"2018-04-26T19:27:39Z","timestamp":1524770859000},"page":"1457-1483","source":"Crossref","is-referenced-by-count":38,"title":["A Review of Automatic Drum Transcription"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9019-6515","authenticated-orcid":false,"given":"Chih-Wei","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3220-2446","authenticated-orcid":false,"given":"Christian","family":"Dittmar","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1860-158X","authenticated-orcid":false,"given":"Carl","family":"Southall","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Vogl","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3531-1282","authenticated-orcid":false,"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[]},{"given":"Jason","family":"Hockman","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6062-7524","authenticated-orcid":false,"given":"Meinard","family":"Muller","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6319-578X","authenticated-orcid":false,"given":"Alexander","family":"Lerch","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","first-page":"146","article-title":"Classification of percussive sounds using\n support vector machines","author":"steelant","year":"0","journal-title":"Proc Ann Machine Learning Conf Belgium and the Netherlands"},{"key":"ref38","first-page":"537","article-title":"Percussion\n classification in polyphonic audio recordings using localized sound models","author":"sandvold","year":"2004","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref33","first-page":"1","article-title":"Automatic\n labeling of unpitched percussion sounds","author":"herrera","year":"0","journal-title":"Proc Audio Eng Soc Convention"},{"key":"ref32","article-title":"Automatic drum transcription and source separation","author":"fitzgerald","year":"0"},{"key":"ref31","first-page":"1","article-title":"Drum\n transcription in the presence of pitched instruments using prior subspace analysis","author":"fitzgerald","year":"0","journal-title":"Proc Irish Signals Syst Conf"},{"key":"ref30","first-page":"1","article-title":"Prior\n subspace analysis for drum transcription","author":"fitzgerald","year":"0","journal-title":"Proc Audio Eng Soc Convention"},{"key":"ref37","first-page":"550","article-title":"A drum pattern retrieval method by voice\n percussion","author":"nakano","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref36","first-page":"69","article-title":"Percussion-related semantic descriptors of music audio files","author":"herrera","year":"2004","journal-title":"Proc Audio Eng Soc Conf Metadata Audio"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2004.1326815"},{"key":"ref34","first-page":"1","article-title":"Further steps towards drum transcription of polyphonic music","author":"dittmar","year":"0","journal-title":"Proc Audio Eng Soc Convention"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/WDM.2002.1176209"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45722-4_8"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPA.2003.1224833"},{"key":"ref20","article-title":"Signal processing methods for drum transcription and music\n structure analysis","author":"paulus","year":"2009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-21945-5"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1002\/9781118393550"},{"key":"ref24","article-title":"On the automatic transcription of percussive music - From acoustic\n signal to high-level analysis","author":"schloss","year":"1985"},{"key":"ref23","first-page":"246","article-title":"Harmonic \/ percussive separation using median filtering","author":"fitzgerald","year":"2010","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref101","article-title":"Lecture 6.5—rmsprop: Divide the gradient by a running average of its recent magnitude","author":"tieleman","year":"2012"},{"key":"ref26","first-page":"65","article-title":"Sub-band\n independent subspace analysis for drum transcription","author":"fitzgerald","year":"0","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref100","article-title":"Adadelta: An adaptive learning rate method","author":"zeiler","year":"2012"},{"key":"ref25","article-title":"On the use\n of zero-crossing rate for an application of classification of percussive sounds","author":"gouyon","year":"0","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref50","first-page":"1","article-title":"An\n algorithm for detecting and labeling drum events in polyphonic music","author":"tanghe","year":"0","journal-title":"Proc 1st MIREX"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2005.248626"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/1878003.1878007"},{"key":"ref58","doi-asserted-by":"crossref","DOI":"10.1186\/1687-4722-2009-497292","article-title":"Drum sound detection in polyphonic music with hidden Markov models","volume":"2009","author":"paulus","year":"2009","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"ref57","first-page":"894","article-title":"Drum\n transcription from multichannel recordings with non-negative matrix factorization","author":"alves","year":"2009","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.910783"},{"key":"ref55","first-page":"229","article-title":"Improving the\n classification of percussive sounds with analytical features: A case study","author":"roy","year":"2007","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref54","first-page":"353","article-title":"Drum transcription in polyphonic music using non-negative matrix factorisation","author":"moreau","year":"2007","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref53","first-page":"219","article-title":"Supervised and unsupervised sequence modelling for drum transcription","author":"gillet","year":"2007","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2006.1661255"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-28084-7_73"},{"key":"ref4","first-page":"1267","article-title":"Acoustic event detection in real-life\n recordings","author":"mesaros","year":"0","journal-title":"Proc Eur Signal Process Conf"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2007.4425280"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/0-387-32845-9_5"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/5.18626"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853981"},{"key":"ref49","first-page":"1","article-title":"Drum transcription with non-negative spectrogram factorisation","author":"paulus","year":"0","journal-title":"Proc 13th Eur Signal Process Conf"},{"key":"ref7","first-page":"107","article-title":"Segmentation and recognition of tabla strokes","author":"chordia","year":"0","journal-title":"Proc Int Conf Music Inf Retrieval"},{"key":"ref9","first-page":"187","article-title":"Drum\n transcription via classification of bar-level rhythmic patterns","author":"thompson","year":"2014","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref46","first-page":"92","article-title":"Drum track transcription of polyphonic music signals using noise subspace projection","author":"gillet","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref45","first-page":"482","article-title":"A simulated annealing optimization of audio features for drum\n classification","author":"sven","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1040830.1040904"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2005.1415682"},{"key":"ref42","first-page":"1","article-title":"Automatic\n drum sound description for real-world music using template adaptation and matching methods","author":"yoshii","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref41","first-page":"1","article-title":"Retrieval of percussion\n gestures using timbre classification techniques","author":"tindale","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.876754"},{"key":"ref43","first-page":"1","article-title":"Adamast:\n A drum sound recognizer based on adaptation and matching of spectrogram templates","author":"yoshii","year":"0","journal-title":"Proc Music Inf Retrieval Evaluation eXchange (MIREX)"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362590"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2015.7362739"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2015.7280342"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178002"},{"key":"ref76","first-page":"730","article-title":"Recurrent\n neural networks for drum transcription","author":"vogl","year":"2016","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952146"},{"key":"ref74","first-page":"257","article-title":"Drum transcription using partially fixed non-negative matrix factorization with template\n adaptation","author":"wu","year":"2015","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/2986416.2986453"},{"key":"ref78","first-page":"591","article-title":"Automatic\n drum transcription using bi-directional recurrent neural networks","author":"southall","year":"2016","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref79","first-page":"218","article-title":"On drum playing technique detection in polyphonic mixtures","author":"wu","year":"2016","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref60","first-page":"1","article-title":"Drum music transcription using prior\n subspace analysis and pattern recognition","author":"spich","year":"0","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref62","first-page":"1","article-title":"Live drum\n separation using probabilistic spectral clustering based on the Itakura-Saito divergence","author":"battenberg","year":"0","journal-title":"Proc Audio Eng Soc Conf Time-Frequency Process Audio"},{"key":"ref61","first-page":"1","article-title":"Real-time recognition of\n percussive sounds by a model-based method","volume":"2011","author":"?im?ekli","year":"2011","journal-title":"EURASIP J Audio Speech Music Process"},{"key":"ref63","article-title":"Techniques for machine understanding of live drum performances","author":"battenberg","year":"2012"},{"key":"ref64","first-page":"152","article-title":"Real-time drums\n transcription with characteristic bandpass filtering","author":"kaliakatsos-papakostas","year":"0","journal-title":"Proc 7th Audio Mostly Conf Conf Interact Sound"},{"key":"ref65","first-page":"1","article-title":"Drumkit\n transcription via convolutive NMF","author":"lindsay-smith","year":"2012","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6637641"},{"key":"ref67","first-page":"402","article-title":"Improving the real-time performance of a causal audio drum transcription system","author":"miron","year":"0","journal-title":"Proc Sound and Music Computing Conf"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854172"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2271648"},{"key":"ref69","first-page":"187","article-title":"Real-time transcription and separation of drum recordings based on NMF\n decomposition","author":"dittmar","year":"2014","journal-title":"Proc Int Conf Digital Audio Effects"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10844-013-0258-3"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-30110-3_63"},{"key":"ref108","first-page":"657","article-title":"Ten years of MIREX: Reflections, challenges, and opportunities","author":"downie","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref94","first-page":"556","article-title":"Algorithms for non-negative matrix factorization","author":"lee","year":"0","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref107","first-page":"1","article-title":"Learning phrase representations using\n rnn encoderdecoder for statistical machine translation","author":"cho","year":"2014","journal-title":"Proc Conf Empirical Methods Natural Lang Process"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2005.851998"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref92","first-page":"613","article-title":"Automatic drum transcription using the student-teacher learning paradigm with unlabeled music\n data","author":"wu","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-5529-2_5"},{"key":"ref91","first-page":"1","article-title":"Drum stroke Computing: Multimodal signal processing for drum stroke identification and\n performance metrics","author":"hochenbaum","year":"0","journal-title":"Proc Int Conf New Interfaces for Musical Expression"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1121\/1.427914"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/5.58337"},{"key":"ref102","first-page":"1","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref98","first-page":"543","article-title":"A method for unconstrained convex minimization problem with the\n rate of convergence o (1\/k2)","volume":"269","author":"nesterov","year":"1983","journal-title":"Doklady AN SSSR"},{"key":"ref99","first-page":"2121","article-title":"Adaptive\n subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952115"},{"key":"ref97","first-page":"823","article-title":"Two problems with backpropagation and other steepest-descent\n learning procedures for networks","author":"sutton","year":"0","journal-title":"Proc 7th Annu Conf Cogn Sci Soc"},{"key":"ref10","first-page":"1","article-title":"Towards a drum transcription system aware of bar position","author":"dzhambazov","year":"2014","journal-title":"Proc Audio Eng Soc Int Conf Semantic Audio"},{"key":"ref11","first-page":"150","article-title":"Drum transcription via joint beat and drum\n modeling using convolutional recurrent neural networks","author":"vogl","year":"2017","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref12","first-page":"1","article-title":"A new DSP tool for drum leakage\n suppression","author":"kokkinis","year":"0","journal-title":"Proc Audio Eng Soc Convention"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2567645"},{"key":"ref14","first-page":"1","article-title":"Modeling musical rhythm at scale with the music genome project","author":"prockup","year":"2015","journal-title":"Proc IEEE Workshop Appl Signal Process Audio Acoust"},{"key":"ref15","first-page":"71","article-title":"Rhythmic classification of electronic dance music","author":"leimeister","year":"2014","journal-title":"Proc Audio Eng Soc Int Conf Semantic Audio"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1525\/mp.2013.30.5.497"},{"key":"ref82","first-page":"49","article-title":"Voice drummer: A music notation interface\n of drum sounds using voice percussion input","author":"nakano","year":"0","journal-title":"Proc ACM Symp User Interface Software and Technology"},{"key":"ref17","first-page":"271","article-title":"Automated estimation of ride cymbal swing ratios in jazz recordings","author":"dittmar","year":"2015","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2011.2161264"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/09298215.2017.1367405"},{"key":"ref84","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"0","journal-title":"Proc Int Conf Artif Intell Stat"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2007.914120"},{"key":"ref83","first-page":"1","article-title":"On the futility of learning complex frame-level language models for chord recognition","author":"korzeniowski","year":"2017","journal-title":"Proc 25th Int AES Conf Semantic Audio"},{"key":"ref80","first-page":"606","article-title":"Automatic\n drum transcription for polyphonic recordings using soft attention mechanisms and convolutional neural networks","author":"southall","year":"2017","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref89","first-page":"287","article-title":"RWC music Database: Popular, classical and\n jazz music databases","volume":"2","author":"goto","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref85","article-title":"200 Drum Machines Dataset Web Presence.","year":"0"},{"key":"ref86","first-page":"1","article-title":"Toward understanding expressive percussion\n through content based analysis","author":"prockup","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref87","article-title":"Enst-drums: an extensive audio-visual database for drum signals processing","author":"gillet","year":"0","journal-title":"Proc Int Soc Music Inf Retrieval Conf"},{"key":"ref88","first-page":"1","article-title":"Study of regularizations and constraints in NMF-based drums monaural separation","author":"marxer","year":"0","journal-title":"Proc Int Conf Digital Audio Effects"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/8361959\/08350302.pdf?arnumber=8350302","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:12:19Z","timestamp":1642003939000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8350302\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,9]]},"references-count":108,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/taslp.2018.2830113","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,9]]}}}