{"id":"https://openalex.org/W2124495245","doi":"https://doi.org/10.1145/1180639.1180825","title":"Towards optimal audio \"keywords\" detection for audio content analysis and discovery","display_name":"Towards optimal audio \"keywords\" detection for audio content analysis and discovery","publication_year":2006,"publication_date":"2006-10-23","ids":{"openalex":"https://openalex.org/W2124495245","doi":"https://doi.org/10.1145/1180639.1180825","mag":"2124495245"},"language":"en","primary_location":{"id":"doi:10.1145/1180639.1180825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1180639.1180825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimedia","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/A5110491600","display_name":"Lie Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lie Lu","raw_affiliation_strings":["Microsoft Research Asia","Microsoft Research Asia,"],"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia","institution_ids":["https://openalex.org/I4210113369"]},{"raw_affiliation_string":"Microsoft Research Asia,","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037486611","display_name":"Alan Hanjali\u0107","orcid":"https://orcid.org/0000-0002-5771-2549"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Alan Hanjalic","raw_affiliation_strings":["Delft University of Technology","Delft University of Technology,,,,,"],"affiliations":[{"raw_affiliation_string":"Delft University of Technology","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"Delft University of Technology,,,,,","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5110491600"],"corresponding_institution_ids":["https://openalex.org/I4210113369"],"apc_list":null,"apc_paid":null,"fwci":1.2721,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.79645952,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"825","last_page":"834"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9925000071525574,"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":0.9890999794006348,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7549378871917725},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.735572099685669},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5342893600463867},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.48147740960121155},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4474845826625824},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4227026700973511},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.34109216928482056},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.32307615876197815},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07499313354492188}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7549378871917725},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.735572099685669},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5342893600463867},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.48147740960121155},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4474845826625824},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4227026700973511},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.34109216928482056},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.32307615876197815},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07499313354492188},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1180639.1180825","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1180639.1180825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 14th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1545046063","https://openalex.org/W1660390307","https://openalex.org/W1999956262","https://openalex.org/W2008611008","https://openalex.org/W2048390151","https://openalex.org/W2077456266","https://openalex.org/W2097088566","https://openalex.org/W2115453400","https://openalex.org/W2124000984","https://openalex.org/W2126109423","https://openalex.org/W2131981197","https://openalex.org/W2132124894","https://openalex.org/W2135674549","https://openalex.org/W2139855016","https://openalex.org/W2144577430","https://openalex.org/W2152322845","https://openalex.org/W2157933833","https://openalex.org/W2160605377","https://openalex.org/W2165874743","https://openalex.org/W2600687292","https://openalex.org/W2799061466","https://openalex.org/W4230946174","https://openalex.org/W6682541512","https://openalex.org/W6684578312"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817","https://openalex.org/W3004352674","https://openalex.org/W3110605476","https://openalex.org/W3043119899","https://openalex.org/W2766269877"],"abstract_inverted_index":{"Natural":[0],"semantic":[1],"sound":[2],"clusters":[3],"in":[4,22,48,85,104,140],"an":[5,18],"audio":[6,12,32,36,39,53,65,80,93,98,120,127,138,142,177,183,193,202],"document,":[7],"also":[8],"referred":[9],"to":[10,20,92,101,124,170],"as":[11,17],"elements,":[13,33,37],"can":[14,41,58,144],"be":[15,42,59,145],"seen":[16],"analogy":[19],"words":[21],"a":[23,88],"text":[24,105],"document.":[25],"Based":[26],"on":[27,131,197],"the":[28,34,50,72,75,126,133,172,181],"obtained":[29,182],"set":[30],"of":[31,52,60,74,136,175,180,200],"key":[35,79],"or":[38],"\"keywords\",":[40],"detected,":[43],"which":[44,132],"are":[45,115,166],"most":[46],"prominent":[47],"characterizing":[49],"content":[51,66],"data.":[54],"As":[55],"such,":[56],"they":[57],"great":[61],"use":[62],"for":[63,78,188],"automatic":[64],"analysis":[67],"and":[68,122,161,168,185,192],"discovery.":[69],"Motivated":[70],"by":[71],"limitations":[73],"existing":[76],"methods":[77],"element":[81,139],"detection,":[82],"we":[83],"propose":[84],"this":[86],"paper":[87],"novel":[89],"unsupervised":[90],"approach":[91],"elements":[94,128],"weighting":[95,103],"using":[96],"multiple":[97],"documents,":[99],"analog":[100],"word":[102],"document":[106,156,164,194],"analysis.":[107],"In":[108],"our":[109],"approach,":[110],"dominant":[111],"feature":[112],"vectors":[113],"(DFV)":[114],"first":[116],"extracted":[117],"from":[118],"each":[119,176],"element,":[121],"used":[123],"measure":[125],"similarity,":[129],"based":[130],"occurrence":[134],"probability":[135],"one":[137],"different":[141],"documents":[143],"estimated.":[146],"Then,":[147],"four":[148],"factors,":[149],"including":[150],"expected":[151,154,158,162],"term":[152,159],"frequency,":[153,157],"inverse":[155,163],"duration,":[160,165],"calculated":[167],"combined":[169],"give":[171],"importance":[173],"weight":[174],"element.":[178],"Evaluation":[179],"\"keywords\"":[184],"their":[186],"usability":[187],"auditory":[189],"scene":[190],"segmentation":[191],"clustering,":[195],"performed":[196],"5":[198],"hours":[199],"diverse":[201],"data,":[203],"shows":[204],"highly":[205],"promising":[206],"results.":[207]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2014,"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"}