{"id":"https://openalex.org/W4308654477","doi":"https://doi.org/10.23919/spa53010.2022.9927877","title":"Towards searching the Holy Grail in automatic music and speech processing - examples of the correlation between human expertise and automated classification","display_name":"Towards searching the Holy Grail in automatic music and speech processing - examples of the correlation between human expertise and automated classification","publication_year":2022,"publication_date":"2022-09-21","ids":{"openalex":"https://openalex.org/W4308654477","doi":"https://doi.org/10.23919/spa53010.2022.9927877"},"language":"en","primary_location":{"id":"doi:10.23919/spa53010.2022.9927877","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa53010.2022.9927877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","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/A5033154448","display_name":"Bo\u017cena Kostek","orcid":"https://orcid.org/0000-0001-6288-2908"},"institutions":[{"id":"https://openalex.org/I169333911","display_name":"Gda\u0144sk University of Technology","ror":"https://ror.org/006x4sc24","country_code":"PL","type":"education","lineage":["https://openalex.org/I169333911"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Bo\u017cena Kostek","raw_affiliation_strings":["Gdansk University of Technology,Audio and Acoustics Laboratory, Faculty of Electronics, Telecommunications, and Informatics,Poland","Audio and Acoustics Laboratory, Faculty of Electronics, Telecommunications, and Informatics, Gdansk University of Technology, Poland"],"affiliations":[{"raw_affiliation_string":"Gdansk University of Technology,Audio and Acoustics Laboratory, Faculty of Electronics, Telecommunications, and Informatics,Poland","institution_ids":["https://openalex.org/I169333911"]},{"raw_affiliation_string":"Audio and Acoustics Laboratory, Faculty of Electronics, Telecommunications, and Informatics, Gdansk University of Technology, Poland","institution_ids":["https://openalex.org/I169333911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5033154448"],"corresponding_institution_ids":["https://openalex.org/I169333911"],"apc_list":null,"apc_paid":null,"fwci":0.1487,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41218608,"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":"16","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.9987000226974487,"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":0.9815999865531921,"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":0.9623000025749207,"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":0.7556019425392151},{"id":"https://openalex.org/keywords/parallels","display_name":"Parallels","score":0.7442294359207153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6179623603820801},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5289803743362427},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4977600872516632},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.49282315373420715},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.4285162091255188},{"id":"https://openalex.org/keywords/pop-music-automation","display_name":"Pop music automation","score":0.4216213524341583},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.41531285643577576},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3887254595756531},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3882938325405121},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16312062740325928},{"id":"https://openalex.org/keywords/music-education","display_name":"Music education","score":0.13785380125045776},{"id":"https://openalex.org/keywords/musical-composition","display_name":"Musical composition","score":0.13029026985168457},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10273131728172302},{"id":"https://openalex.org/keywords/politics","display_name":"Politics","score":0.08115094900131226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7556019425392151},{"id":"https://openalex.org/C2775922551","wikidata":"https://www.wikidata.org/wiki/Q7135033","display_name":"Parallels","level":2,"score":0.7442294359207153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6179623603820801},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5289803743362427},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4977600872516632},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.49282315373420715},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.4285162091255188},{"id":"https://openalex.org/C73520026","wikidata":"https://www.wikidata.org/wiki/Q7229091","display_name":"Pop music automation","level":4,"score":0.4216213524341583},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.41531285643577576},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3887254595756531},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3882938325405121},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16312062740325928},{"id":"https://openalex.org/C13553968","wikidata":"https://www.wikidata.org/wiki/Q27908","display_name":"Music education","level":2,"score":0.13785380125045776},{"id":"https://openalex.org/C109568592","wikidata":"https://www.wikidata.org/wiki/Q207628","display_name":"Musical composition","level":3,"score":0.13029026985168457},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10273131728172302},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.08115094900131226},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"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/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/spa53010.2022.9927877","is_oa":false,"landing_page_url":"https://doi.org/10.23919/spa53010.2022.9927877","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Signal Processing: Algorithms, Architectures, Arrangements, and Applications (SPA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8399999737739563,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3107474891","https://openalex.org/W2676493621","https://openalex.org/W2160136308","https://openalex.org/W178932670","https://openalex.org/W2189603775","https://openalex.org/W2742078559","https://openalex.org/W2890285072","https://openalex.org/W2406972062","https://openalex.org/W2176890384","https://openalex.org/W4308654477"],"abstract_inverted_index":{"This":[0],"tutorial":[1],"lecture":[2],"is":[3,151],"dedicated":[4],"to":[5,61,78,109,134,168],"addressing":[6],"the":[7,103,139,155,179],"still":[8],"not":[9],"fully":[10],"achieved":[11],"potential":[12],"in":[13,35,52,66,69,92,102,141,154,164,178],"automatic":[14,42,128],"music":[15,23,43,93,129,158],"and":[16,24,45,54,63,89,94,130,147,159],"speech":[17,25,95,131,160],"processing.":[18,161],"There":[19],"are":[20,28,41,49,133,171,182],"parallels":[21,40],"between":[22],"as":[26],"both":[27,48,145],"audio":[29],"signals;":[30],"however,":[31],"they":[32],"differ":[33],"much":[34],"detail.":[36],"One":[37],"of":[38,127,157,175],"such":[39,169],"transcription":[44],"text-to-speech":[46],"technology;":[47],"very":[50],"advanced":[51],"research":[53,176],"technology":[55,166],"but":[56],"suffer":[57],"from":[58],"challenges":[59,100],"related":[60,167],"polyphony":[62],"differentiated":[64,71],"articulation":[65],"music,":[67],"whereas":[68],"speech:":[70],"accents,":[72],"L2":[73],"speakers'":[74],"pronunciations,":[75],"diarization,":[76],"just":[77],"name":[79],"a":[80],"few,":[81],"cause":[82],"problems.":[83],"Another":[84],"challenge":[85],"concerns":[86],"affective":[87],"computation":[88],"predicting":[90],"emotions":[91],"with":[96,113],"sufficient":[97],"accuracy.":[98],"These":[99],"lie":[101],"notion":[104],"that":[105],"we":[106],"would":[107],"like":[108],"get":[110],"better":[111],"results":[112],"machine":[114,142],"learning-based":[115],"classification":[116],"than":[117],"human":[118],"expertise":[119],"could":[120],"deliver.":[121],"In":[122],"this":[123],"lecture,":[124],"first,":[125],"bases":[126],"processing":[132],"be":[135],"shortly":[136],"reviewed.":[137],"Then,":[138],"state-of-the-art":[140],"learning,":[143],"including":[144],"baseline":[146],"deep":[148],"learning":[149],"methods,":[150],"briefly":[152],"examined":[153],"context":[156],"Also,":[162],"advances":[163],"available":[165],"issues":[170],"presented.":[172],"Finally,":[173],"examples":[174],"performed":[177],"discussed":[180],"areas":[181],"shown.":[183]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}