{"id":"https://openalex.org/W2673758101","doi":"https://doi.org/10.1109/icassp.2017.7952145","title":"Data-driven solo voice enhancement for jazz music retrieval","display_name":"Data-driven solo voice enhancement for jazz music retrieval","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2673758101","doi":"https://doi.org/10.1109/icassp.2017.7952145","mag":"2673758101"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2017.7952145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5078080260","display_name":"Stefan Balke","orcid":"https://orcid.org/0000-0003-1306-3548"},"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":"Stefan Balke","raw_affiliation_strings":["International Audio Laboratories Erlangen, Friedrich-Alexander-Universit\u00e4t (FAU), Germany","International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat (FAU), Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universit\u00e4t (FAU), Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat (FAU), Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009881719","display_name":"Christian Dittmar","orcid":"https://orcid.org/0000-0002-3220-2446"},"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":"Christian Dittmar","raw_affiliation_strings":["International Audio Laboratories Erlangen, Friedrich-Alexander-Universit\u00e4t (FAU), Germany","International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat (FAU), Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universit\u00e4t (FAU), Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat (FAU), Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047532715","display_name":"Jakob Abe\u00dfer","orcid":"https://orcid.org/0000-0003-4689-7944"},"institutions":[{"id":"https://openalex.org/I4210138578","display_name":"Fraunhofer Institute for Digital Media Technology","ror":"https://ror.org/04gp0yb49","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210138578","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jakob Abesser","raw_affiliation_strings":["Semantic Music Technologies Group, Fraunhofer IDMT, Ilmenau, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Semantic Music Technologies Group, Fraunhofer IDMT, Ilmenau, Germany","institution_ids":["https://openalex.org/I4210138578"]}]},{"author_position":"last","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 Muller","raw_affiliation_strings":["International Audio Laboratories Erlangen, Friedrich-Alexander-Universit\u00e4t (FAU), Germany","International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat (FAU), Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universit\u00e4t (FAU), Germany","institution_ids":["https://openalex.org/I4210123192"]},{"raw_affiliation_string":"International Audio Laboratories Erlangen, Friedrich-Alexander-Universitat (FAU), Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1205,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.78906783,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"12","issue":null,"first_page":"196","last_page":"200"},"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":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.995199978351593,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.843575119972229},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7646166086196899},{"id":"https://openalex.org/keywords/jazz","display_name":"Jazz","score":0.6692548394203186},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.5928698778152466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5817980766296387},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5741475820541382},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4386548697948456},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4232403635978699},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4118085503578186},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2817758321762085},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08776253461837769}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.843575119972229},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7646166086196899},{"id":"https://openalex.org/C2980749","wikidata":"https://www.wikidata.org/wiki/Q8341","display_name":"Jazz","level":2,"score":0.6692548394203186},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.5928698778152466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5817980766296387},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5741475820541382},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4386548697948456},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4232403635978699},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4118085503578186},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2817758321762085},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08776253461837769},{"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/icassp.2017.7952145","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952145","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/397488","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/397488","pdf_url":null,"source":{"id":"https://openalex.org/S4306400318","display_name":"Fraunhofer-Publica (Fraunhofer-Gesellschaft)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4923324","host_organization_name":"Fraunhofer-Gesellschaft","host_organization_lineage":["https://openalex.org/I4923324"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference paper"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1554104313","https://openalex.org/W1576578512","https://openalex.org/W1594771616","https://openalex.org/W1976069042","https://openalex.org/W1986602091","https://openalex.org/W2025768430","https://openalex.org/W2038678505","https://openalex.org/W2101234009","https://openalex.org/W2101722322","https://openalex.org/W2110798204","https://openalex.org/W2111956167","https://openalex.org/W2142669986","https://openalex.org/W2170142018","https://openalex.org/W2295104115","https://openalex.org/W2296463171","https://openalex.org/W2396684454","https://openalex.org/W2398141343","https://openalex.org/W2399349471","https://openalex.org/W2406682741","https://openalex.org/W2407410673","https://openalex.org/W2478051194","https://openalex.org/W2522234776","https://openalex.org/W2577202280","https://openalex.org/W6633146083","https://openalex.org/W6634496701","https://openalex.org/W6675354045","https://openalex.org/W6696888253","https://openalex.org/W6697479953","https://openalex.org/W6712557957","https://openalex.org/W6712658070","https://openalex.org/W6714029020","https://openalex.org/W6727014285"],"related_works":["https://openalex.org/W2494884022","https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W600619470","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2132597408","https://openalex.org/W2340483794","https://openalex.org/W126167045","https://openalex.org/W4298140471"],"abstract_inverted_index":{"Retrieving":[0],"short":[1],"monophonic":[2,72],"queries":[3],"in":[4,12,35,88],"music":[5,37,99],"recordings":[6,100],"is":[7,27],"a":[8,21,36,79,109,114,118,123,133,144,153],"challenging":[9],"research":[10],"problem":[11],"Music":[13],"Information":[14],"Retrieval":[15],"(MIR).":[16],"In":[17,74],"jazz":[18,145],"music,":[19],"given":[20],"solo":[22,105,136,146],"transcription,":[23],"one":[24],"retrieval":[25,44,147],"task":[26],"to":[28,60,70,112,152],"find":[29],"the":[30,49,53,57,66,71,84],"corresponding":[31],"(potentially":[32],"polyphonic)":[33],"recording":[34],"collection.":[38],"Many":[39],"conventional":[40,89],"systems":[41],"approach":[42,81,111,142],"such":[43],"tasks":[45],"by":[46],"first":[47],"extracting":[48],"predominant":[50,157],"F0-trajectory":[51],"from":[52],"recording,":[54],"then":[55],"quantizing":[56],"extracted":[58],"trajectory":[59],"musical":[61],"pitches":[62],"and":[63,101,149],"finally":[64],"comparing":[65],"resulting":[67],"pitch":[68],"sequence":[69],"query.":[73],"this":[75],"paper,":[76],"we":[77,107],"introduce":[78],"data-driven":[80],"that":[82],"avoids":[83],"hard":[85],"decisions":[86],"involved":[87],"approaches:":[90],"Given":[91],"pairs":[92],"of":[93,97,104,135],"time-frequency":[94],"(TF)":[95],"representations":[96,103],"full":[98],"TF":[102,120,125],"transcriptions,":[106],"use":[108],"DNN-based":[110],"learn":[113],"mapping":[115],"for":[116,156],"transforming":[117],"\u201cpolyphonic\u201d":[119],"representation":[121],"into":[122],"\u201cmonophonic\u201d":[124],"representation.":[126],"This":[127],"transform":[128],"can":[129],"be":[130],"considered":[131],"as":[132],"kind":[134],"voice":[137],"enhancement.":[138],"We":[139],"evaluate":[140],"our":[141],"within":[143],"scenario":[148],"compare":[150],"it":[151],"state-of-the-art":[154],"method":[155],"melody":[158],"extraction.":[159]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
