{"id":"https://openalex.org/W3015783972","doi":"https://doi.org/10.1109/icassp40776.2020.9054642","title":"Local Key Estimation In Classical Music Recordings: A Cross-Version Study on Schubert\u2019s Winterreise","display_name":"Local Key Estimation In Classical Music Recordings: A Cross-Version Study on Schubert\u2019s Winterreise","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015783972","doi":"https://doi.org/10.1109/icassp40776.2020.9054642","mag":"3015783972"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5082386697","display_name":"Hendrik Schreiber","orcid":"https://orcid.org/0000-0002-3033-1703"},"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":true,"raw_author_name":"Hendrik Schreiber","raw_affiliation_strings":["International Audio Laborator"],"affiliations":[{"raw_affiliation_string":"International Audio Laborator","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110931910","display_name":"Christof Weis","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":"Christof Weis","raw_affiliation_strings":["International Audio Laborator"],"affiliations":[{"raw_affiliation_string":"International Audio Laborator","institution_ids":["https://openalex.org/I4210123192"]}]},{"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 Laborator"],"affiliations":[{"raw_affiliation_string":"International Audio Laborator","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082386697"],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":0.9151,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73421362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"501","last_page":"505"},"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":0.9952999949455261,"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":0.9950000047683716,"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/key","display_name":"Key (lock)","score":0.770484209060669},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7099504470825195},{"id":"https://openalex.org/keywords/chord","display_name":"Chord (peer-to-peer)","score":0.6434555053710938},{"id":"https://openalex.org/keywords/hyperparameter","display_name":"Hyperparameter","score":0.5823952555656433},{"id":"https://openalex.org/keywords/ambiguity","display_name":"Ambiguity","score":0.5494992136955261},{"id":"https://openalex.org/keywords/timbre","display_name":"Timbre","score":0.506735622882843},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4966781735420227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4961129128932953},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4674191474914551},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46187806129455566},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.413490355014801},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3963378369808197},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10621321201324463}],"concepts":[{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.770484209060669},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7099504470825195},{"id":"https://openalex.org/C194147245","wikidata":"https://www.wikidata.org/wiki/Q1076368","display_name":"Chord (peer-to-peer)","level":2,"score":0.6434555053710938},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.5823952555656433},{"id":"https://openalex.org/C2780522230","wikidata":"https://www.wikidata.org/wiki/Q1140419","display_name":"Ambiguity","level":2,"score":0.5494992136955261},{"id":"https://openalex.org/C2776539107","wikidata":"https://www.wikidata.org/wiki/Q176501","display_name":"Timbre","level":3,"score":0.506735622882843},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4966781735420227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4961129128932953},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4674191474914551},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46187806129455566},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.413490355014801},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3963378369808197},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10621321201324463},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054642","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":51,"referenced_works":["https://openalex.org/W62934727","https://openalex.org/W172772501","https://openalex.org/W424637349","https://openalex.org/W1504032994","https://openalex.org/W1522301498","https://openalex.org/W1562529351","https://openalex.org/W1686810756","https://openalex.org/W1836465849","https://openalex.org/W1955976719","https://openalex.org/W1989216934","https://openalex.org/W2016916928","https://openalex.org/W2066174107","https://openalex.org/W2076811432","https://openalex.org/W2097720264","https://openalex.org/W2165911145","https://openalex.org/W2170142018","https://openalex.org/W2294376557","https://openalex.org/W2398597216","https://openalex.org/W2401859649","https://openalex.org/W2403620556","https://openalex.org/W2408689217","https://openalex.org/W2739987151","https://openalex.org/W2771265026","https://openalex.org/W2886422331","https://openalex.org/W2922872820","https://openalex.org/W2949117887","https://openalex.org/W2963765091","https://openalex.org/W2964051853","https://openalex.org/W2964121744","https://openalex.org/W3014089027","https://openalex.org/W3211469364","https://openalex.org/W4214907486","https://openalex.org/W4288407552","https://openalex.org/W6607028437","https://openalex.org/W6614607778","https://openalex.org/W6630250213","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638667902","https://openalex.org/W6641127812","https://openalex.org/W6696995126","https://openalex.org/W6712497386","https://openalex.org/W6713061376","https://openalex.org/W6713219380","https://openalex.org/W6714206803","https://openalex.org/W6742154312","https://openalex.org/W6746411809","https://openalex.org/W6753689128","https://openalex.org/W6760571136","https://openalex.org/W6775063858","https://openalex.org/W6803187181"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2360603947","https://openalex.org/W2371528275","https://openalex.org/W2769570009","https://openalex.org/W2964089573","https://openalex.org/W2700782391"],"abstract_inverted_index":{"While":[0],"global":[1],"key":[2,28,38,100],"and":[3,9,60,95,157],"chord":[4],"estimation":[5,39],"for":[6,29,99,140],"both":[7,72,124],"popular":[8],"classical":[10,30],"music":[11],"recordings":[12],"have":[13],"received":[14],"a":[15,41,68,76,86],"lot":[16],"of":[17,49,56,83,151],"attention,":[18],"little":[19],"research":[20],"has":[21],"been":[22],"devoted":[23],"to":[24,135,145,160],"estimating":[25],"the":[26,81,92,113,118,131,141,148,152],"local":[27,37],"music.":[31],"In":[32],"this":[33],"work,":[34],"we":[35,74,106,121],"approach":[36],"on":[40,85],"unique":[42],"cross-version":[43],"dataset":[44],"comprising":[45],"nine":[46],"performances":[47],"(versions)":[48],"Schubert's":[50],"song":[51,119,155],"cycle":[52],"Winterreise-a":[53],"challenging":[54],"scenario":[55],"high":[57],"musical":[58,97],"ambiguity":[59],"subjectivity.":[61],"We":[62,89],"compare":[63],"an":[64],"HMM-based":[65],"system":[66],"with":[67],"CNN-based":[69],"approach.":[70],"For":[71],"models,":[73],"employ":[75],"similar":[77],"training":[78],"procedure":[79],"including":[80],"optimization":[82],"hyperparameters":[84],"validation":[87],"split.":[88],"systematically":[90],"evaluate":[91],"model":[93],"predictions":[94],"provide":[96],"explanations":[98],"confusions.":[101],"As":[102],"our":[103],"main":[104],"contribution,":[105],"explore":[107],"how":[108],"different":[109],"training-test":[110],"splits":[111],"affect":[112],"models'":[114],"efficacy.":[115],"Splitting":[116,129],"along":[117,130],"axis,":[120],"find":[122],"that":[123],"methods":[125],"perform":[126],"similarly":[127],"well.":[128],"version":[132],"axis":[133],"leads":[134],"clearly":[136],"higher":[137],"results,":[138],"especially":[139],"CNN,":[142],"which":[143],"seems":[144],"effectively":[146],"learn":[147],"harmonic":[149],"progressions":[150],"songs":[153],"(\"cover":[154],"effect\")":[156],"successfully":[158],"generalizes":[159],"unseen":[161],"versions.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}