{"id":"https://openalex.org/W2113613324","doi":"https://doi.org/10.1145/1631272.1631320","title":"Local summarization and multi-level LSH for retrieving multi-variant audio tracks","display_name":"Local summarization and multi-level LSH for retrieving multi-variant audio tracks","publication_year":2009,"publication_date":"2009-10-19","ids":{"openalex":"https://openalex.org/W2113613324","doi":"https://doi.org/10.1145/1631272.1631320","mag":"2113613324"},"language":"en","primary_location":{"id":"doi:10.1145/1631272.1631320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","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/A5100745222","display_name":"Yi Yu","orcid":"https://orcid.org/0000-0002-0294-6620"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yi Yu","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ, USA",", New Jersey Institute of Technology, Newark, NJ, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]},{"raw_affiliation_string":", New Jersey Institute of Technology, Newark, NJ, USA#TAB#","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028132236","display_name":"Michel Crucianu","orcid":"https://orcid.org/0000-0001-8204-6843"},"institutions":[{"id":"https://openalex.org/I124158823","display_name":"Conservatoire National des Arts et M\u00e9tiers","ror":"https://ror.org/0175hh227","country_code":"FR","type":"education","lineage":["https://openalex.org/I124158823","https://openalex.org/I4210134562"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Michel Crucianu","raw_affiliation_strings":["Conservatoire National des Arts et M\u00e9tiers, Paris, France"],"affiliations":[{"raw_affiliation_string":"Conservatoire National des Arts et M\u00e9tiers, Paris, France","institution_ids":["https://openalex.org/I124158823"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081226122","display_name":"Vincent Oria","orcid":"https://orcid.org/0000-0003-4345-243X"},"institutions":[{"id":"https://openalex.org/I118118575","display_name":"New Jersey Institute of Technology","ror":"https://ror.org/05e74xb87","country_code":"US","type":"education","lineage":["https://openalex.org/I118118575"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vincent Oria","raw_affiliation_strings":["New Jersey Institute of Technology, Newark, NJ, USA",", New Jersey Institute of Technology, Newark, NJ, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"New Jersey Institute of Technology, Newark, NJ, USA","institution_ids":["https://openalex.org/I118118575"]},{"raw_affiliation_string":", New Jersey Institute of Technology, Newark, NJ, USA#TAB#","institution_ids":["https://openalex.org/I118118575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100333516","display_name":"Lei Chen","orcid":"https://orcid.org/0000-0002-8257-5806"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lei Chen","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100745222"],"corresponding_institution_ids":["https://openalex.org/I118118575"],"apc_list":null,"apc_paid":null,"fwci":2.08710451,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.87069723,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"341","last_page":"350"},"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/T11439","display_name":"Video Analysis and Summarization","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/automatic-summarization","display_name":"Automatic summarization","score":0.8253213763237},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8041846752166748},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.7317332029342651},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.586167573928833},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.5365701913833618},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.5288226008415222},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.38614773750305176},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37663745880126953},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37440285086631775},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3704126477241516},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.18520405888557434},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.10731974244117737}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8253213763237},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8041846752166748},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.7317332029342651},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.586167573928833},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.5365701913833618},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.5288226008415222},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.38614773750305176},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37663745880126953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37440285086631775},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3704126477241516},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.18520405888557434},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10731974244117737},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1631272.1631320","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1631272.1631320","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-27455","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-27455","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W41713251","https://openalex.org/W82645835","https://openalex.org/W158861595","https://openalex.org/W179305498","https://openalex.org/W216397362","https://openalex.org/W1970360159","https://openalex.org/W1971877806","https://openalex.org/W1989859754","https://openalex.org/W2011645100","https://openalex.org/W2083540857","https://openalex.org/W2117939210","https://openalex.org/W2137319814","https://openalex.org/W2138679406","https://openalex.org/W2139107403","https://openalex.org/W2154473523","https://openalex.org/W2164523872","https://openalex.org/W2164693078","https://openalex.org/W2170037597","https://openalex.org/W2340480757","https://openalex.org/W2407147481","https://openalex.org/W6704190477"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W4389760904","https://openalex.org/W2000601968","https://openalex.org/W2144265691","https://openalex.org/W2033383639","https://openalex.org/W3108918257","https://openalex.org/W3016124764"],"abstract_inverted_index":{"In":[0],"this":[1,20],"paper":[2],"we":[3,59],"study":[4],"the":[5,145],"problem":[6],"of":[7,35,86,115,177],"detecting":[8],"and":[9,24,57,68,174],"grouping":[10],"multi-variant":[11,165],"audio":[12,16,36,47,76,166,178],"tracks":[13],"in":[14],"large":[15,46],"datasets.":[17],"To":[18,49],"address":[19],"issue,":[21],"a":[22,45,51,113,127,141,155,163],"fast":[23,40,173],"reliable":[25,175],"retrieval":[26,41,55,176],"method":[27],"is":[28,78,98,109,122],"necessary.":[29],"But":[30],"reliability":[31],"requires":[32],"elaborate":[33],"representations":[34],"content,":[37],"which":[38],"challenges":[39],"by":[42],"similarity":[43,143],"from":[44],"database.":[48],"find":[50],"better":[52],"tradeoff":[53],"between":[54],"quality":[56],"efficiency,":[58],"put":[60],"forward":[61],"an":[62,118],"approach":[63,171],"relying":[64],"on":[65,101,162],"local":[66],"summarization":[67],"multi-level":[69],"Locality-Sensitive":[70],"Hashing":[71],"(LSH).":[72],"More":[73],"precisely,":[74],"each":[75,96],"track":[77,108,179],"divided":[79],"into":[80],"multiple":[81],"Continuously":[82],"Correlated":[83],"Periods":[84],"(CCP)":[85],"variable":[87],"length":[88],"according":[89],"to":[90,138,144],"spectral":[91],"similarity.":[92,158],"The":[93,132,147],"description":[94],"for":[95,124],"CCP":[97],"calculated":[99],"based":[100],"its":[102],"Weighted":[103],"Mean":[104],"Chroma":[105],"(WMC).":[106],"A":[107],"thus":[110],"represented":[111],"as":[112],"sequence":[114],"WMCs.":[116],"Then,":[117],"adapted":[119],"two-level":[120],"LSH":[121],"employed":[123],"efficiently":[125],"delineating":[126],"narrow":[128],"relevant":[129],"search":[130,137],"region.":[131],"\"coarse\"":[133],"hashing":[134],"level":[135,150],"restricts":[136],"items":[139,153],"having":[140],"non-negligible":[142],"query.":[146],"subsequent,":[148],"\"refined\"":[149],"only":[151],"returns":[152],"showing":[154],"much":[156],"higher":[157],"Experimental":[159],"evaluations":[160],"performed":[161],"real":[164],"dataset":[167],"confirm":[168],"that":[169],"our":[170],"supports":[172],"variants.":[180]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-02-23T08:04:50.183275","created_date":"2025-10-10T00:00:00"}