{"id":"https://openalex.org/W4292826157","doi":"https://doi.org/10.1109/taslp.2022.3200547","title":"Comparing Deep Models and Evaluation Strategies for Multi-Pitch Estimation in Music Recordings","display_name":"Comparing Deep Models and Evaluation Strategies for Multi-Pitch Estimation in Music Recordings","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4292826157","doi":"https://doi.org/10.1109/taslp.2022.3200547"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3200547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3200547","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5110931910","display_name":"Christof Weis","orcid":null},"institutions":[{"id":"https://openalex.org/I2802330208","display_name":"Statistics Belgium","ror":"https://ror.org/0246a9012","country_code":"BE","type":"government","lineage":["https://openalex.org/I2802330208","https://openalex.org/I4210095879"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["BE","FR"],"is_corresponding":false,"raw_author_name":"Christof Weis","raw_affiliation_strings":["LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","Signal, Statistique et Apprentissage","Laboratoire Traitement et Communication de l'Information"],"raw_orcid":"https://orcid.org/0000-0003-2143-4679","affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Signal, Statistique et Apprentissage","institution_ids":["https://openalex.org/I2802330208"]},{"raw_affiliation_string":"Laboratoire Traitement et Communication de l'Information","institution_ids":["https://openalex.org/I4210165912"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063097936","display_name":"Geoffroy Peeters","orcid":"https://orcid.org/0000-0001-5255-3019"},"institutions":[{"id":"https://openalex.org/I2802330208","display_name":"Statistics Belgium","ror":"https://ror.org/0246a9012","country_code":"BE","type":"government","lineage":["https://openalex.org/I2802330208","https://openalex.org/I4210095879"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["BE","FR"],"is_corresponding":false,"raw_author_name":"Geoffroy Peeters","raw_affiliation_strings":["LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","Laboratoire Traitement et Communication de l'Information","Signal, Statistique et Apprentissage"],"raw_orcid":"https://orcid.org/0000-0001-5255-3019","affiliations":[{"raw_affiliation_string":"LTCI, Télécom Paris, Institut Polytechnique de Paris, Palaiseau, France","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Laboratoire Traitement et Communication de l'Information","institution_ids":["https://openalex.org/I4210165912"]},{"raw_affiliation_string":"Signal, Statistique et Apprentissage","institution_ids":["https://openalex.org/I2802330208"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2726,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.78694733,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"2814","last_page":"2827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11349","display_name":"Music Technology and Sound Studies","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10788","display_name":"Neuroscience and Music Perception","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8252537250518799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8061099052429199},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6237692832946777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5317560434341431},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5119189023971558},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4852742850780487},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.44854044914245605},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.42756757140159607},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3879323899745941},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3336130380630493}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8252537250518799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8061099052429199},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6237692832946777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5317560434341431},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5119189023971558},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4852742850780487},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.44854044914245605},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.42756757140159607},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3879323899745941},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3336130380630493},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/taslp.2022.3200547","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3200547","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:HAL:hal-03860460v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-03860460","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech and Language Processing, 2022, 30, pp.2814-2827. ⟨10.1109/TASLP.2022.3200547⟩","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2159595415","display_name":null,"funder_award_id":"DFG WE 6611/1-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":64,"referenced_works":["https://openalex.org/W16345605","https://openalex.org/W1878565453","https://openalex.org/W1901129140","https://openalex.org/W1979654135","https://openalex.org/W2017416504","https://openalex.org/W2096482524","https://openalex.org/W2100816929","https://openalex.org/W2107328928","https://openalex.org/W2110007838","https://openalex.org/W2110644015","https://openalex.org/W2144414181","https://openalex.org/W2155195660","https://openalex.org/W2194775991","https://openalex.org/W2198584637","https://openalex.org/W2296724634","https://openalex.org/W2400969690","https://openalex.org/W2523056285","https://openalex.org/W2559688696","https://openalex.org/W2560254426","https://openalex.org/W2587248453","https://openalex.org/W2902303903","https://openalex.org/W2906214917","https://openalex.org/W2908510526","https://openalex.org/W2915654580","https://openalex.org/W2921083967","https://openalex.org/W2939988664","https://openalex.org/W2950335938","https://openalex.org/W2950547518","https://openalex.org/W2963045359","https://openalex.org/W2963452667","https://openalex.org/W2963535133","https://openalex.org/W3015247127","https://openalex.org/W3095303521","https://openalex.org/W3096508889","https://openalex.org/W3098226019","https://openalex.org/W3137158725","https://openalex.org/W3146994612","https://openalex.org/W3160787318","https://openalex.org/W3162528130","https://openalex.org/W3200791433","https://openalex.org/W3206146520","https://openalex.org/W4225281045","https://openalex.org/W4287072584","https://openalex.org/W4293775315","https://openalex.org/W4322615164","https://openalex.org/W4385245566","https://openalex.org/W6600679824","https://openalex.org/W6639824700","https://openalex.org/W6676956424","https://openalex.org/W6681236507","https://openalex.org/W6682891771","https://openalex.org/W6697040288","https://openalex.org/W6713219328","https://openalex.org/W6730401039","https://openalex.org/W6733434541","https://openalex.org/W6733936739","https://openalex.org/W6739901393","https://openalex.org/W6745851314","https://openalex.org/W6751512325","https://openalex.org/W6755182157","https://openalex.org/W6757817989","https://openalex.org/W6759107158","https://openalex.org/W6798855526","https://openalex.org/W6803088475"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W3099765033","https://openalex.org/W4226493464","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3103566983"],"abstract_inverted_index":{"Extracting":[0],"pitch":[1],"information":[2],"from":[3],"music":[4,13,31,115,256],"recordings":[5,32],"is":[6],"a":[7,44,88,192,199],"challenging":[8],"but":[9],"important":[10],"problem":[11],"in":[12,29,105,185,249,255],"signal":[14],"processing.":[15],"Frame-wise":[16],"transcription":[17,257],"or":[18],"multi-pitch":[19,109,247],"estimation":[20],"aims":[21],"for":[22,78,108,170,203,244],"detecting":[23],"the":[24,62,85,95,117,121,157,161,166,180,186,207,242],"simultaneous":[25,92],"activity":[26],"of":[27,46,94,97,102,160,168,182,188,191,209],"pitches":[28],"polyphonic":[30],"and":[33,65,87,123,136,156,197,213,219],"has":[34],"recently":[35],"seen":[36],"major":[37],"improvements":[38,228],"thanks":[39],"to":[40,72,83,142,216,237,251],"deep-learning":[41],"techniques,":[42],"with":[43,91],"variety":[45],"proposed":[47],"model":[48,139],"architectures.":[49],"In":[50],"this":[51],"paper,":[52],"we":[53,146],"compare":[54,100],"different":[55,106],"architectures":[56,74,104,132,172],"based":[57],"on":[58,112,153,229],"convolutional":[59],"neural":[60],"networks,":[61],"U-net":[63],"structure,":[64],"self-attention":[66,76],"components.":[67],"We":[68,99,177],"propose":[69,198],"several":[70,189],"modifications":[71],"these":[73,103,149],"including":[75],"modules":[77],"skip":[79],"connections,":[80],"recurrent":[81],"layers":[82],"replace":[84],"self-attention,":[86],"multi-task":[89],"strategy":[90,202],"prediction":[93],"degree":[96],"polyphony.":[98],"variants":[101,140],"sizes":[107],"estimation,":[110],"focusing":[111],"Western":[113],"classical":[114],"beyond":[116],"piano-solo":[118],"scenario":[119],"using":[120],"MusicNet":[122],"Schubert":[124],"Winterreise":[125],"datasets.":[126],"Our":[127],"experiments":[128],"indicate":[129],"that":[130,137,148,227],"most":[131],"yield":[133],"competitive":[134],"results":[135,150],"larger":[138],"seem":[141],"be":[143],"beneficial.":[144],"However,":[145],"find":[147],"substantially":[151],"depend":[152],"randomization":[154],"effects":[155],"particular":[158,171],"choice":[159],"training–test":[162],"split,":[163],"which":[164,205],"questions":[165],"claim":[167],"superiority":[169],"given":[173],"only":[174],"small":[175],"improvements.":[176],"therefore":[178],"investigate":[179],"influence":[181,208],"dataset":[183,232],"splits":[184],"presence":[187],"movements":[190],"work":[193],"cycle":[194],"(cross-version":[195],"evaluation)":[196],"best-practice":[200],"evaluation":[201,225],"MusicNet,":[204],"weakens":[206],"individual":[210],"test":[211],"tracks":[212],"suppresses":[214],"overfitting":[215],"specific":[217,231],"works":[218],"recording":[220],"conditions.":[221],"A":[222],"final":[223],"cross-dataset":[224],"suggests":[226],"one":[230],"do":[233],"not":[234],"necessarily":[235],"generalize":[236],"other":[238],"scenarios,":[239],"thus":[240],"emphasizing":[241],"need":[243],"further":[245],"high-quality":[246],"datasets":[248],"order":[250],"reliably":[252],"measure":[253],"progress":[254],"tasks.":[258]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}