{"id":"https://openalex.org/W2164516556","doi":"https://doi.org/10.1109/icassp.2008.4518082","title":"Content-based retrieval of polyphonic music objects using pitch contour","display_name":"Content-based retrieval of polyphonic music objects using pitch contour","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2164516556","doi":"https://doi.org/10.1109/icassp.2008.4518082","mag":"2164516556"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518082","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5055788726","display_name":"Lihui Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Lihui Guo","raw_affiliation_strings":["Department of Computer Science and Technology, East China Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, East China Jiao Tong University, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051648467","display_name":"Xin He","orcid":"https://orcid.org/0000-0002-0125-4171"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin He","raw_affiliation_strings":["Motorola China Research Center, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Motorola China Research Center, Shanghai, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100736914","display_name":"Yaxin Zhang","orcid":"https://orcid.org/0000-0002-2265-3614"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaxin Zhang","raw_affiliation_strings":["Motorola China Research Center, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Motorola China Research Center, Shanghai, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031868292","display_name":"Yue Lu","orcid":"https://orcid.org/0000-0003-4062-6553"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yue Lu","raw_affiliation_strings":["Department of Computer Science and Technology, East China Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, East China Jiao Tong University, Shanghai, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5055788726"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2024,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75656325,"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":"2205","last_page":"2208"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9969000220298767,"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":0.9962999820709229,"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/polyphony","display_name":"Polyphony","score":0.9473109245300293},{"id":"https://openalex.org/keywords/singing","display_name":"Singing","score":0.7541581392288208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7412281036376953},{"id":"https://openalex.org/keywords/hum","display_name":"Hum","score":0.585003674030304},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5828101634979248},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.47486376762390137},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4701423943042755},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.41666799783706665},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33323872089385986},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.20584285259246826},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09820851683616638},{"id":"https://openalex.org/keywords/art","display_name":"Art","score":0.07807707786560059}],"concepts":[{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.9473109245300293},{"id":"https://openalex.org/C44819458","wikidata":"https://www.wikidata.org/wiki/Q27939","display_name":"Singing","level":2,"score":0.7541581392288208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7412281036376953},{"id":"https://openalex.org/C23161992","wikidata":"https://www.wikidata.org/wiki/Q2922301","display_name":"Hum","level":3,"score":0.585003674030304},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5828101634979248},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.47486376762390137},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4701423943042755},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.41666799783706665},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33323872089385986},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.20584285259246826},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09820851683616638},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.07807707786560059},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C52119013","wikidata":"https://www.wikidata.org/wiki/Q50637","display_name":"Art history","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C554144382","wikidata":"https://www.wikidata.org/wiki/Q213156","display_name":"Performance art","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518082","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518082","pdf_url":null,"source":{"id":"https://openalex.org/S4210167542","display_name":"Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"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":14,"referenced_works":["https://openalex.org/W10342353","https://openalex.org/W158998227","https://openalex.org/W1492666853","https://openalex.org/W1960041389","https://openalex.org/W1964208564","https://openalex.org/W2088632109","https://openalex.org/W2094571051","https://openalex.org/W2101119896","https://openalex.org/W2116520137","https://openalex.org/W2119599673","https://openalex.org/W2141440853","https://openalex.org/W2337437255","https://openalex.org/W6600423445","https://openalex.org/W6606489800"],"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/W2375454309","https://openalex.org/W2374135200","https://openalex.org/W2390487542"],"abstract_inverted_index":{"This":[0],"paper":[1,34],"investigates":[2],"the":[3,37,42,46,52,56,63,72,78],"retrieval":[4],"of":[5,30,80],"content-based":[6],"polyphonic":[7,60,82],"music":[8,54,83],"objects":[9,84],"in":[10,49,59],"Wav":[11],"and":[12,40,62],"MP3":[13],"format.":[14],"The":[15,74],"system":[16,39],"allows":[17],"user":[18],"to":[19],"find":[20],"an":[21],"intended":[22],"song":[23],"by":[24,85],"humming":[25],"or":[26],"singing":[27],"a":[28],"section":[29],"it.":[31],"In":[32],"this":[33],"we":[35],"introduce":[36],"baseline":[38],"describe":[41],"key":[43],"components":[44],"including":[45],"pitch":[47,57],"extraction":[48],"humming/singing":[50],"clip,":[51],"vocal/non-vocal":[53],"segmentation,":[55],"tracking":[58],"music,":[61],"DTW":[64],"based":[65],"matching":[66],"algorithm.":[67],"We":[68],"conducted":[69],"evaluations":[70],"on":[71],"system.":[73],"experimental":[75],"results":[76],"demonstrate":[77],"feasibility":[79],"retrieving":[81],"humming/singing.":[86]},"counts_by_year":[{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}