{"id":"https://openalex.org/W2938353296","doi":"https://doi.org/10.1109/icassp.2019.8683609","title":"Evaluating Salience Representations for Cross-modal Retrieval of Western Classical Music Recordings","display_name":"Evaluating Salience Representations for Cross-modal Retrieval of Western Classical Music Recordings","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2938353296","doi":"https://doi.org/10.1109/icassp.2019.8683609","mag":"2938353296"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5019894297","display_name":"Frank Zalkow","orcid":"https://orcid.org/0000-0003-1383-4541"},"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":"Frank Zalkow","raw_affiliation_strings":["International Audio Laboratories Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","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, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","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 M\u00fcller","raw_affiliation_strings":["International Audio Laboratories Erlangen, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Audio Laboratories Erlangen, Germany","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":0.3823,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.47369092,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"331","last_page":"335"},"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":0.9930999875068665,"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/melody","display_name":"Melody","score":0.8008593320846558},{"id":"https://openalex.org/keywords/salience","display_name":"Salience (neuroscience)","score":0.7154991626739502},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7080379128456116},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.6682236790657043},{"id":"https://openalex.org/keywords/music-information-retrieval","display_name":"Music information retrieval","score":0.6215918064117432},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5743040442466736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4784139096736908},{"id":"https://openalex.org/keywords/musical","display_name":"Musical","score":0.44439053535461426},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.44230055809020996},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35931146144866943},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29276490211486816},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20174196362495422},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10693761706352234}],"concepts":[{"id":"https://openalex.org/C43803900","wikidata":"https://www.wikidata.org/wiki/Q170412","display_name":"Melody","level":3,"score":0.8008593320846558},{"id":"https://openalex.org/C108154423","wikidata":"https://www.wikidata.org/wiki/Q1469792","display_name":"Salience (neuroscience)","level":2,"score":0.7154991626739502},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080379128456116},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.6682236790657043},{"id":"https://openalex.org/C2777946086","wikidata":"https://www.wikidata.org/wiki/Q1163335","display_name":"Music information retrieval","level":3,"score":0.6215918064117432},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5743040442466736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4784139096736908},{"id":"https://openalex.org/C558565934","wikidata":"https://www.wikidata.org/wiki/Q2743","display_name":"Musical","level":2,"score":0.44439053535461426},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.44230055809020996},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35931146144866943},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29276490211486816},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20174196362495422},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10693761706352234},{"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/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683609","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683609","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W20529463","https://openalex.org/W170732776","https://openalex.org/W1515150410","https://openalex.org/W1518164296","https://openalex.org/W1540613698","https://openalex.org/W1554104313","https://openalex.org/W1576578512","https://openalex.org/W1976069042","https://openalex.org/W1988749582","https://openalex.org/W2038678505","https://openalex.org/W2101722322","https://openalex.org/W2111956167","https://openalex.org/W2116244429","https://openalex.org/W2139107403","https://openalex.org/W2142669986","https://openalex.org/W2153331925","https://openalex.org/W2161632835","https://openalex.org/W2191779130","https://openalex.org/W2398141343","https://openalex.org/W2399349471","https://openalex.org/W2406682741","https://openalex.org/W2407410673","https://openalex.org/W2478051194","https://openalex.org/W2528613928","https://openalex.org/W2673758101","https://openalex.org/W6600865812","https://openalex.org/W6633146083","https://openalex.org/W6634496701","https://openalex.org/W6682222477","https://openalex.org/W6712658070","https://openalex.org/W6714029020","https://openalex.org/W6950485904"],"related_works":["https://openalex.org/W2031608562","https://openalex.org/W2070348439","https://openalex.org/W1472467890","https://openalex.org/W1908769745","https://openalex.org/W2144131839","https://openalex.org/W3012755723","https://openalex.org/W2039049596","https://openalex.org/W2092287538","https://openalex.org/W2291136386","https://openalex.org/W2023541445"],"abstract_inverted_index":{"In":[0],"this":[1,39,65,85,128],"paper,":[2,129],"we":[3,130],"consider":[4],"a":[5,14,33,94,152],"cross-modal":[6,70,113,139],"retrieval":[7,40,140],"scenario":[8],"of":[9,38,49,93,102,119,127,163],"Western":[10,81],"classical":[11,82],"music.":[12],"Given":[13],"short":[15],"monophonic":[16,53],"musical":[17,158],"theme":[18],"in":[19,32,46],"symbolic":[20],"notation":[21],"as":[22],"query,":[23],"the":[24,43,47,52,56,69,78,90,104,112,117,124],"objective":[25],"is":[26,42,87,98,109],"to":[27,110],"find":[28],"relevant":[29],"audio":[30,164],"recordings":[31],"database.":[34],"A":[35],"major":[36],"challenge":[37],"task":[41],"possible":[44],"difference":[45],"degree":[48],"polyphony":[50],"between":[51],"query":[54],"and":[55,160],"music":[57,63],"recordings.":[58,79,165],"Previous":[59],"studies":[60],"for":[61,137],"popular":[62],"addressed":[64],"issue":[66],"by":[67],"performing":[68],"comparison":[71,114],"based":[72],"on":[73,116,151],"predominant":[74],"melodies":[75],"extracted":[76],"from":[77],"For":[80],"music,":[83],"however,":[84],"approach":[86],"problematic":[88],"since":[89],"underlying":[91],"assumption":[92],"single":[95],"pre-dominant":[96],"melody":[97,105],"often":[99],"violated.":[100],"Instead":[101],"extracting":[103],"explicitly,":[106],"another":[107],"strategy":[108],"perform":[111],"directly":[115],"basis":[118],"melody-enhanced":[120],"salience":[121,135],"representations.":[122],"As":[123],"main":[125],"contribution":[126],"evaluate":[131],"several":[132],"conceptually":[133],"different":[134],"representations":[136],"our":[138],"scenario.":[141],"Our":[142],"extensive":[143],"experimental":[144],"results,":[145],"which":[146],"have":[147],"been":[148],"made":[149],"available":[150],"website,":[153],"comprise":[154],"more":[155],"than":[156],"2000":[157],"themes":[159],"100":[161],"hours":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
