{"id":"https://openalex.org/W2800919920","doi":"https://doi.org/10.1145/3192975.3193006","title":"Combining auditory perception and visual features for regional recognition of Chinese folk songs","display_name":"Combining auditory perception and visual features for regional recognition of Chinese folk songs","publication_year":2018,"publication_date":"2018-02-24","ids":{"openalex":"https://openalex.org/W2800919920","doi":"https://doi.org/10.1145/3192975.3193006","mag":"2800919920"},"language":"en","primary_location":{"id":"doi:10.1145/3192975.3193006","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3192975.3193006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 10th International Conference on Computer and Automation Engineering","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/A5056067943","display_name":"Xinyu Yang","orcid":"https://orcid.org/0000-0001-5117-4914"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xinyu Yang","raw_affiliation_strings":["Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042350489","display_name":"Jing Luo","orcid":"https://orcid.org/0000-0001-7138-3705"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Luo","raw_affiliation_strings":["Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053345759","display_name":"Yinrui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinrui Wang","raw_affiliation_strings":["Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101700309","display_name":"Xi Zhao","orcid":"https://orcid.org/0000-0001-9108-5094"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Zhao","raw_affiliation_strings":["Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Xi'an Jiaotong University, Xi'an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100666590","display_name":"Juan Li","orcid":"https://orcid.org/0000-0002-9991-1538"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Juan Li","raw_affiliation_strings":["Center of Music Education, Xi'an Jiaotong University, Xi'an, Shannxi, China"],"affiliations":[{"raw_affiliation_string":"Center of Music Education, Xi'an Jiaotong University, Xi'an, Shannxi, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5056067943"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.03712789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"75","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9506999850273132,"subfield":{"id":"https://openalex.org/subfields/1210","display_name":"Music"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6851106286048889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6732111573219299},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.656726598739624},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5260710120201111},{"id":"https://openalex.org/keywords/texture","display_name":"Texture (cosmology)","score":0.49220386147499084},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4857342839241028},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46320095658302307},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4590557813644409},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4446639120578766},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.41234642267227173},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12654009461402893},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12322881817817688}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6851106286048889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6732111573219299},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.656726598739624},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5260710120201111},{"id":"https://openalex.org/C2781195486","wikidata":"https://www.wikidata.org/wiki/Q289436","display_name":"Texture (cosmology)","level":3,"score":0.49220386147499084},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4857342839241028},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46320095658302307},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4590557813644409},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4446639120578766},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.41234642267227173},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12654009461402893},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12322881817817688},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3192975.3193006","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3192975.3193006","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 10th International Conference on Computer and Automation Engineering","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6600000262260437,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1825426646","https://openalex.org/W1966311970","https://openalex.org/W1989639247","https://openalex.org/W2024490110","https://openalex.org/W2027035856","https://openalex.org/W2060024738","https://openalex.org/W2093373070","https://openalex.org/W2107430826","https://openalex.org/W2116684167","https://openalex.org/W2122183634","https://openalex.org/W2135294064","https://openalex.org/W2155392356","https://openalex.org/W2158275940","https://openalex.org/W2163352848","https://openalex.org/W2170895606","https://openalex.org/W2362228420","https://openalex.org/W2383028995","https://openalex.org/W2409029869","https://openalex.org/W2540121965","https://openalex.org/W2579586206","https://openalex.org/W2616039214","https://openalex.org/W2616175929","https://openalex.org/W3120620199","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2068608913","https://openalex.org/W2090763504","https://openalex.org/W3124914020","https://openalex.org/W2141033859","https://openalex.org/W2156434174","https://openalex.org/W2071701083","https://openalex.org/W2383687187","https://openalex.org/W2081517010","https://openalex.org/W148178222","https://openalex.org/W2121496884"],"abstract_inverted_index":{"The":[0],"regional":[1,16,45],"recognition":[2,46,132],"of":[3,18,47,59,147,154],"Chinese":[4,48,144],"folk":[5,21,49,145],"songs":[6,50,146],"is":[7,51,54,84],"not":[8],"only":[9],"conducive":[10],"to":[11,97,102,110],"discovering":[12],"music":[13,32],"characteristics":[14],"and":[15,41,62,107,119,138],"styles":[17],"specific":[19],"geographical":[20],"songs,":[22],"but":[23],"also":[24],"has":[25],"important":[26],"research":[27],"value":[28],"in":[29,108],"the":[30,57,71,77,81,88,91,99,113,116,120,131],"existing":[31],"information":[33,123],"retrieval":[34],"system.":[35],"In":[36],"this":[37],"paper,":[38],"an":[39,66,151],"effective":[40],"novel":[42],"approach":[43],"for":[44],"proposed,":[52],"which":[53,156],"based":[55],"on":[56],"fusion":[58],"auditory":[60,72,136],"perception":[61,73,137],"visual":[63,89,139],"features":[64,74,83,140],"using":[65],"ensemble":[67],"SVM":[68],"classifier.":[69],"When":[70],"are":[75,95,124],"extracted,":[76],"temporal":[78],"relation":[79],"among":[80],"frame":[82],"fully":[85],"considered.":[86],"For":[87],"features,":[90],"color":[92],"time-frequency":[93],"maps":[94],"used":[96],"replace":[98],"gray-scale":[100],"images":[101],"capture":[103],"more":[104],"texture":[105,117],"information,":[106],"order":[109],"better":[111],"characterize":[112],"image":[114],"texture,":[115],"patterns":[118],"corresponding":[121],"intensity":[122],"both":[125],"extracted.":[126],"Experimental":[127],"results":[128],"show":[129],"that":[130],"method":[133],"combined":[134],"with":[135,150],"can":[141],"effectively":[142],"identify":[143],"different":[148],"regions":[149],"accuracy":[152],"rate":[153],"89.29%,":[155],"outperforms":[157],"other":[158],"state-of-the-art":[159],"approaches.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}