{"id":"https://openalex.org/W3197988356","doi":"https://doi.org/10.1109/taslp.2021.3110137","title":"CTC-Based Learning of Chroma Features for Score\u2013Audio Music Retrieval","display_name":"CTC-Based Learning of Chroma Features for Score\u2013Audio Music Retrieval","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3197988356","doi":"https://doi.org/10.1109/taslp.2021.3110137","mag":"3197988356"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3110137","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3110137","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09531521.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"oa_status":"hybrid","oa_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09531521.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019894297","display_name":"Frank Zalkow","orcid":"https://orcid.org/0000-0003-1383-4541"},"institutions":[{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["https://openalex.org/I4210124274","https://openalex.org/I4923324"]},{"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":"Frank Zalkow","raw_affiliation_strings":["International Audio Laboratories Erlangen, a joint institution of the Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, a joint institution of the Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]},{"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"]},{"id":"https://openalex.org/I4210124274","display_name":"Fraunhofer Institute for Integrated Circuits","ror":"https://ror.org/024ape423","country_code":"DE","type":"facility","lineage":["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, a joint institution of the Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany"],"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, a joint institution of the Friedrich-Alexander-Universit&#x00E4;t Erlangen-N&#x00FC;rnberg (FAU) and Fraunhofer Institute for Integrated Circuits IIS, Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5019894297"],"corresponding_institution_ids":["https://openalex.org/I4210123192","https://openalex.org/I4210124274"],"apc_list":null,"apc_paid":null,"fwci":1.676,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.8464503,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":"29","issue":null,"first_page":"2957","last_page":"2971"},"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":0.9970999956130981,"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":0.9962000250816345,"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/computer-science","display_name":"Computer science","score":0.7511729001998901},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6608635187149048},{"id":"https://openalex.org/keywords/melody","display_name":"Melody","score":0.6414192914962769},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6145114898681641},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.49674278497695923},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4789319932460785},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4751843512058258},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4655293822288513},{"id":"https://openalex.org/keywords/musical-notation","display_name":"Musical notation","score":0.46025145053863525},{"id":"https://openalex.org/keywords/theme","display_name":"Theme (computing)","score":0.44965246319770813},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43469446897506714},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4258127510547638},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.2394690215587616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7511729001998901},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6608635187149048},{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.6414192914962769},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6145114898681641},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.49674278497695923},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4789319932460785},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4751843512058258},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4655293822288513},{"id":"https://openalex.org/C88639978","wikidata":"https://www.wikidata.org/wiki/Q233861","display_name":"Musical notation","level":3,"score":0.46025145053863525},{"id":"https://openalex.org/C33566652","wikidata":"https://www.wikidata.org/wiki/Q1065927","display_name":"Theme (computing)","level":2,"score":0.44965246319770813},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43469446897506714},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4258127510547638},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.2394690215587616},{"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2021.3110137","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3110137","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09531521.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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:fraunhofer.de:N-642034","is_oa":true,"landing_page_url":"http://publica.fraunhofer.de/documents/N-642034.html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400801","display_name":"Publikationsdatenbank der Fraunhofer-Gesellschaft (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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Fraunhofer IIS","raw_type":"Journal Article"},{"id":"pmh:oai:publica.fraunhofer.de:publica/270262","is_oa":false,"landing_page_url":"https://publica.fraunhofer.de/handle/publica/270262","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":"journal article"}],"best_oa_location":{"id":"doi:10.1109/taslp.2021.3110137","is_oa":true,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3110137","pdf_url":"https://ieeexplore.ieee.org/ielx7/6570655/6633080/09531521.pdf","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.7200000286102295}],"awards":[{"id":"https://openalex.org/G3988372918","display_name":null,"funder_award_id":"DFG-MU 2686/11-1","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"},{"id":"https://openalex.org/G7378671776","display_name":null,"funder_award_id":"MU 2686/12-1","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3197988356.pdf","grobid_xml":"https://content.openalex.org/works/W3197988356.grobid-xml"},"referenced_works_count":77,"referenced_works":["https://openalex.org/W1518164296","https://openalex.org/W1522301498","https://openalex.org/W1901129140","https://openalex.org/W1988749582","https://openalex.org/W2024475670","https://openalex.org/W2111956167","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2139107403","https://openalex.org/W2153331925","https://openalex.org/W2161632835","https://openalex.org/W2296610835","https://openalex.org/W2296724634","https://openalex.org/W2398360960","https://openalex.org/W2399349471","https://openalex.org/W2407410673","https://openalex.org/W2478051194","https://openalex.org/W2528613928","https://openalex.org/W2552400013","https://openalex.org/W2577760017","https://openalex.org/W2673758101","https://openalex.org/W2771265026","https://openalex.org/W2774938731","https://openalex.org/W2796517058","https://openalex.org/W2885570506","https://openalex.org/W2890559714","https://openalex.org/W2900365452","https://openalex.org/W2902303903","https://openalex.org/W2902437809","https://openalex.org/W2906259846","https://openalex.org/W2906658932","https://openalex.org/W2917340025","https://openalex.org/W2920796904","https://openalex.org/W2922301133","https://openalex.org/W2938353296","https://openalex.org/W2939957001","https://openalex.org/W2964111193","https://openalex.org/W2964121744","https://openalex.org/W2964177567","https://openalex.org/W2983598429","https://openalex.org/W2990244497","https://openalex.org/W2990946792","https://openalex.org/W2991402284","https://openalex.org/W2991512180","https://openalex.org/W2996266053","https://openalex.org/W3015271757","https://openalex.org/W3015315843","https://openalex.org/W3023043375","https://openalex.org/W3083833517","https://openalex.org/W3094268961","https://openalex.org/W3099037078","https://openalex.org/W3099271704","https://openalex.org/W3101398262","https://openalex.org/W3103403347","https://openalex.org/W3106476516","https://openalex.org/W3125766201","https://openalex.org/W3130926914","https://openalex.org/W3151955268","https://openalex.org/W3186528344","https://openalex.org/W6631190155","https://openalex.org/W6682222477","https://openalex.org/W6697040288","https://openalex.org/W6697451111","https://openalex.org/W6712324461","https://openalex.org/W6732858653","https://openalex.org/W6746411809","https://openalex.org/W6753544557","https://openalex.org/W6756599191","https://openalex.org/W6764992649","https://openalex.org/W6770476880","https://openalex.org/W6770607572","https://openalex.org/W6770833027","https://openalex.org/W6777041185","https://openalex.org/W6782889728","https://openalex.org/W6786603260","https://openalex.org/W6798836799","https://openalex.org/W6950485904"],"related_works":["https://openalex.org/W3186129571","https://openalex.org/W971076770","https://openalex.org/W2140924349","https://openalex.org/W1908769745","https://openalex.org/W2039049596","https://openalex.org/W2144131839","https://openalex.org/W2092287538","https://openalex.org/W3012755723","https://openalex.org/W2005811360","https://openalex.org/W2023541445"],"abstract_inverted_index":{"This":[0],"paper":[1],"deals":[2],"with":[3,199,216],"a":[4,23,32,45,142,154,193],"scoreaudio":[5,79],"music":[6],"retrieval":[7,177],"task":[8],"where":[9,81],"the":[10,62,86,91,96,123,130,145,149,171,184,187,200,242,251],"aim":[11],"is":[12,103],"to":[13,90,105,121],"find":[14],"relevant":[15],"audio":[16,39,97,161],"recordings":[17],"of":[18,64,85,95,115,148,153,186,244,247],"Western":[19],"classical":[20],"music,":[21],"given":[22],"short":[24],"monophonic":[25],"musical":[26,248],"theme":[27,155,176],"in":[28,100,129,159,174,226],"symbolic":[29],"notation":[30],"as":[31,50,213,215,235],"query.":[33],"Strategies":[34],"for":[35,189],"comparing":[36],"score":[37,87],"and":[38,56,151,179,239],"data":[40],"are":[41,88,157],"often":[42],"based":[43],"on":[44,250],"common":[46],"mid-level":[47,71],"representation,":[48],"such":[49,74,107,141],"chroma":[51,224],"features,":[52],"which":[53,133],"capture":[54],"melodic":[55],"harmonic":[57],"properties.":[58],"Recent":[59],"studies":[60],"demonstrated":[61],"effectiveness":[63],"deep":[65],"neural":[66],"networks":[67],"that":[68,181,198],"learn":[69],"task-specific":[70],"representations.":[72],"Usually,":[73],"supervised":[75],"learning":[76],"approaches":[77],"require":[78],"pairs":[80],"individual":[82],"note":[83],"events":[84],"aligned":[89,109,137],"corresponding":[92],"time":[93,146],"positions":[94,147],"excerpt.":[98],"However,":[99],"practice,":[101],"it":[102],"tedious":[104],"generate":[106],"strongly":[108,217],"training":[110,131,138,202],"pairs.":[111,139],"As":[112,192],"one":[113],"contribution":[114],"this":[116,190],"paper,":[117],"we":[118,196,208,221],"show":[119,180],"how":[120],"apply":[122],"Connectionist":[124],"Temporal":[125],"Classification":[126],"(CTC)":[127],"loss":[128],"procedure,":[132],"only":[134,144],"uses":[135],"weakly":[136,205],"In":[140],"pair,":[143],"beginning":[150],"end":[152],"occurrence":[156],"annotated":[158,206,218],"an":[160,236],"recording,":[162],"rather":[163],"than":[164],"requiring":[165],"local":[166],"alignment":[167],"annotations.":[168],"We":[169],"evaluate":[170],"resulting":[172],"features":[173,225],"our":[175,223],"scenario":[178],"they":[182],"improve":[183],"state":[185],"art":[188],"task.":[191],"main":[194],"result,":[195],"demonstrate":[197],"CTC-based":[201],"procedure":[203],"using":[204],"data,":[207],"can":[209],"achieve":[210],"results":[211],"almost":[212],"good":[214],"data.":[219],"Furthermore,":[220],"assess":[222],"depth":[227],"by":[228,240],"inspecting":[229],"their":[230],"temporal":[231],"smoothness":[232],"or":[233],"granularity":[234],"important":[237],"property":[238],"analyzing":[241],"impact":[243],"different":[245],"degrees":[246],"complexity":[249],"features.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
