{"id":"https://openalex.org/W2408491073","doi":"https://doi.org/10.21437/interspeech.2012-561","title":"Bag-of-audio-words approach for multimedia event classification","display_name":"Bag-of-audio-words approach for multimedia event classification","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2408491073","doi":"https://doi.org/10.21437/interspeech.2012-561","mag":"2408491073"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-561","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5045567366","display_name":"Stephanie Pancoast","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Stephanie Pancoast","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5076998541","display_name":"Murat Akbacak","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murat Akbacak","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5045567366"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.9364,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.9821846,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2105","last_page":"2108"},"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":0.9733999967575073,"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/T13996","display_name":"Diverse Musicological Studies","score":0.9376000165939331,"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/computer-science","display_name":"Computer science","score":0.8418974876403809},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.7210646867752075},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5362975001335144},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5197777152061462},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.5088582038879395},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4843110144138336},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.46749722957611084},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4582068920135498},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4447067677974701},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.4385184347629547},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3873702585697174},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33861833810806274},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3014361560344696},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14666405320167542},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.14196181297302246},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.13329923152923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8418974876403809},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.7210646867752075},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5362975001335144},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5197777152061462},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.5088582038879395},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4843110144138336},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.46749722957611084},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4582068920135498},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4447067677974701},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.4385184347629547},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3873702585697174},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33861833810806274},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3014361560344696},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14666405320167542},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.14196181297302246},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.13329923152923584},{"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/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-561","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-561","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.300.917","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.300.917","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.speech.sri.com/papers/Interspeech2012_BagOfAudioWord_Pancoast_Akbacak_v4.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"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/W1620668332"],"abstract_inverted_index":{"With":[0],"the":[1,22,35,66,110,142],"popularity":[2],"of":[3,24,31,122,141],"online":[4,25],"multimedia":[5,41,93,126,151,159],"videos,":[6],"there":[7],"has":[8,34,50,109],"been":[9],"much":[10],"interest":[11],"in":[12,15,46,102,125],"recent":[13],"years":[14],"acoustic":[16],"event":[17,42,94,152,160],"detection":[18,153,161],"and":[19,55,84,145],"classification":[20,49],"for":[21,92,118],"improvement":[23],"video":[26,33],"search.":[27],"The":[28,96],"audio":[29,47,76,100,123],"component":[30],"a":[32,119,131],"potential":[36],"to":[37,40,53,64,72],"contribute":[38],"significantly":[39],"classification.":[43,95],"Recent":[44],"research":[45],"document":[48,57],"drawn":[51],"parallels":[52],"text":[54],"image":[56],"retrieval":[58],"by":[59],"employing":[60],"what":[61],"is":[62],"referred":[63],"as":[65,89],"bag-of-audio":[67],"words":[68],"(BoAW)":[69],"method.":[70],"Compared":[71],"supervised":[73],"approaches":[74],"where":[75],"concept":[77],"detectors":[78],"are":[79,87],"trained":[80],"using":[81],"annotated":[82],"data":[83],"extracted":[85],"labels":[86],"used":[88],"lowlevel":[90],"features":[91],"BoAW":[97,143],"approach":[98],"extracts":[99],"concepts":[101,124],"an":[103],"unsupervised":[104],"fashion.":[105],"Hence":[106],"this":[107,136],"method":[108,144],"advantage":[111],"that":[112],"it":[113],"can":[114],"be":[115],"employed":[116],"easily":[117],"new":[120],"set":[121],"videos":[127],"without":[128],"going":[129],"through":[130],"laborious":[132],"annotation":[133],"effort.":[134],"In":[135],"paper,":[137],"we":[138],"explore":[139],"variations":[140],"present":[146],"results":[147],"on":[148],"NIST":[149],"2011":[150],"(MED)":[154],"dataset.":[155],"Index":[156],"Terms:":[157],"Bag-of-audio-words,":[158],"1.":[162]},"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":6},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":15},{"year":2019,"cited_by_count":20},{"year":2018,"cited_by_count":7},{"year":2017,"cited_by_count":13},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":9},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":12}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
