{"id":"https://openalex.org/W4372260329","doi":"https://doi.org/10.1109/icassp49357.2023.10096762","title":"TAPE: An End-to-End Timbre-Aware Pitch Estimator","display_name":"TAPE: An End-to-End Timbre-Aware Pitch Estimator","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260329","doi":"https://doi.org/10.1109/icassp49357.2023.10096762"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://repositori.upf.edu/bitstream/10230/56565/1/Tamer_mtg_tape.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041283771","display_name":"Nazif Can Tamer","orcid":"https://orcid.org/0000-0003-3903-7428"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Nazif Can Tamer","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030848563","display_name":"Yigitcan \u00d6zer","orcid":"https://orcid.org/0000-0003-2235-8655"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Yigitcan \u00d6zer","raw_affiliation_strings":["International Audio Laboratories,Erlangen,Germany","International Audio Laboratories, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109881851","display_name":"Meinard M\u00fcller","orcid":null},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Meinard M\u00fcller","raw_affiliation_strings":["International Audio Laboratories,Erlangen,Germany","International Audio Laboratories, Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories,Erlangen,Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006479715","display_name":"Xavier Serra","orcid":"https://orcid.org/0000-0003-1395-2345"},"institutions":[{"id":"https://openalex.org/I170486558","display_name":"Universitat Pompeu Fabra","ror":"https://ror.org/04n0g0b29","country_code":"ES","type":"education","lineage":["https://openalex.org/I170486558"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Xavier Serra","raw_affiliation_strings":["Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Pompeu Fabra,Music Technology Group,Barcelona,Spain","institution_ids":["https://openalex.org/I170486558"]},{"raw_affiliation_string":"Music Technology Group, Universitat Pompeu Fabra, Barcelona, Spain","institution_ids":["https://openalex.org/I170486558"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9667,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74414246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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":0.9983999729156494,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.8576024770736694},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.7591167688369751},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.743645191192627},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6390697956085205},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6312263011932373},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5572133660316467},{"id":"https://openalex.org/keywords/pitch-detection-algorithm","display_name":"Pitch detection algorithm","score":0.5377727746963501},{"id":"https://openalex.org/keywords/piano","display_name":"Piano","score":0.4792056977748871},{"id":"https://openalex.org/keywords/pitch","display_name":"Pitch (Music)","score":0.4738602638244629},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.3677094280719757},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2148931324481964},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.19723239541053772},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15959858894348145}],"concepts":[{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.8576024770736694},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.7591167688369751},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.743645191192627},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6390697956085205},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6312263011932373},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5572133660316467},{"id":"https://openalex.org/C135622632","wikidata":"https://www.wikidata.org/wiki/Q7198851","display_name":"Pitch detection algorithm","level":3,"score":0.5377727746963501},{"id":"https://openalex.org/C124086623","wikidata":"https://www.wikidata.org/wiki/Q5994","display_name":"Piano","level":2,"score":0.4792056977748871},{"id":"https://openalex.org/C153405242","wikidata":"https://www.wikidata.org/wiki/Q118819","display_name":"Pitch (Music)","level":3,"score":0.4738602638244629},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3677094280719757},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2148931324481964},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.19723239541053772},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15959858894348145},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","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/icassp49357.2023.10096762","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096762","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repositori.upf.edu:10230/56565","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/56565","pdf_url":"http://repositori.upf.edu/bitstream/10230/56565/1/Tamer_mtg_tape.pdf","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"}],"best_oa_location":{"id":"pmh:oai:repositori.upf.edu:10230/56565","is_oa":true,"landing_page_url":"http://hdl.handle.net/10230/56565","pdf_url":"http://repositori.upf.edu/bitstream/10230/56565/1/Tamer_mtg_tape.pdf","source":{"id":"https://openalex.org/S4306402615","display_name":"Repositori digital de la UPF (Universitat Pompeu Fabra)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I170486558","host_organization_name":"Universitat Pompeu Fabra","host_organization_lineage":["https://openalex.org/I170486558"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"},"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/1","display_name":"No poverty"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335598","display_name":"Agencia Estatal de Investigaci\u00f3n","ror":null}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4372260329.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1529883046","https://openalex.org/W1875231349","https://openalex.org/W1975079546","https://openalex.org/W1976069042","https://openalex.org/W2054139811","https://openalex.org/W2067265757","https://openalex.org/W2091425152","https://openalex.org/W2118774185","https://openalex.org/W2130770109","https://openalex.org/W2166209411","https://openalex.org/W2296724634","https://openalex.org/W2559688696","https://openalex.org/W2799452163","https://openalex.org/W2950547518","https://openalex.org/W2962866891","https://openalex.org/W2972411915","https://openalex.org/W2986673441","https://openalex.org/W2997938083","https://openalex.org/W3012391395","https://openalex.org/W3037149862","https://openalex.org/W3095303521","https://openalex.org/W3115488976","https://openalex.org/W3171087525","https://openalex.org/W3191088441","https://openalex.org/W4235907194","https://openalex.org/W4283388885","https://openalex.org/W4308859910","https://openalex.org/W4308860703","https://openalex.org/W4322615164","https://openalex.org/W4385245566","https://openalex.org/W6639350448","https://openalex.org/W6697040288","https://openalex.org/W6730401039","https://openalex.org/W6739901393","https://openalex.org/W6755182157","https://openalex.org/W6796931752","https://openalex.org/W6799492392","https://openalex.org/W6803088475","https://openalex.org/W6846893220"],"related_works":["https://openalex.org/W2171508519","https://openalex.org/W4253022192","https://openalex.org/W2037916898","https://openalex.org/W55541205","https://openalex.org/W1985268485","https://openalex.org/W2946308721","https://openalex.org/W1969330155","https://openalex.org/W1982918643","https://openalex.org/W2564416932","https://openalex.org/W2031573710"],"abstract_inverted_index":{"Pitch":[0],"estimation":[1,142],"of":[2,13,27,42,74,99,137],"a":[3,8,28,65,75,100],"target":[4,29,76,149],"musical":[5],"source":[6,30,35,77,88,138,150],"within":[7],"multi-source":[9],"polyphonic":[10],"signal":[11],"is":[12,31,151],"great":[14],"interest":[15],"for":[16,23,85],"music":[17],"performance":[18],"analysis.":[19],"One":[20],"possible":[21],"approach":[22,104],"extracting":[24],"the":[25,40,43,72,83,97,113,134,148],"pitch":[26,41,67,73,141],"to":[32,54,60,92],"first":[33],"perform":[34],"separation":[36,89,139],"and":[37,140],"then":[38],"estimate":[39],"separated":[44],"track.":[45],"However,":[46],"as":[47],"we":[48,63],"will":[49],"show,":[50],"this":[51,61],"typically":[52],"leads":[53],"poor":[55],"results.":[56],"As":[57],"an":[58,79,86],"alternative":[59],"approach,":[62],"introduce":[64],"timbre-aware":[66],"estimator":[68],"(TAPE),":[69],"which":[70],"estimates":[71],"in":[78],"end-to-end":[80],"manner":[81],"without":[82,124],"need":[84],"explicit":[87],"step.":[90],"Opposed":[91],"existing":[93],"approaches":[94],"that":[95,109],"assume":[96],"predominance":[98],"lead":[101],"voice,":[102],"our":[103],"builds":[105],"upon":[106],"other":[107],"cues":[108],"only":[110],"rely":[111],"on":[112,118,130],"timbral":[114],"characteristics.":[115],"Our":[116],"results":[117],"real":[119],"violin\u2013piano":[120],"duets":[121],"show":[122],"that,":[123],"any":[125],"pre-processing":[126],"step,":[127],"TAPE":[128],"trained":[129],"synthetic":[131],"mixes":[132],"outperforms":[133],"sequential":[135],"procedure":[136],"under":[143],"many":[144],"settings,":[145],"even":[146],"if":[147],"not":[152],"predominant.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
