{"id":"https://openalex.org/W2091774059","doi":"https://doi.org/10.1109/icassp.2014.6853822","title":"Semi-automatic audio semantic concept discovery for multimedia retrieval","display_name":"Semi-automatic audio semantic concept discovery for multimedia retrieval","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2091774059","doi":"https://doi.org/10.1109/icassp.2014.6853822","mag":"2091774059"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6853822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/journal_contribution/Semi-automatic_audio_semantic_concept_discovery_for_multimedia_retrieval/6473678","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101401275","display_name":"Yipei Wang","orcid":"https://orcid.org/0000-0002-9589-7177"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yipei Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086192353","display_name":"Shourabh Rawat","orcid":"https://orcid.org/0009-0000-0160-3741"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shourabh Rawat","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085262529","display_name":"Florian Metze","orcid":"https://orcid.org/0000-0002-6663-8600"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Florian Metze","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, U.S.A","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technology Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101401275"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15281975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1375","last_page":"1379"},"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":0.9987000226974487,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9736999869346619,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8857366442680359},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.691433846950531},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6473594307899475},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.639397919178009},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.5053511261940002},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.49625712633132935},{"id":"https://openalex.org/keywords/semantic-annotation","display_name":"Semantic annotation","score":0.45018327236175537},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.447335809469223},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.4416339695453644},{"id":"https://openalex.org/keywords/cover","display_name":"Cover (algebra)","score":0.42482417821884155},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.39867597818374634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2730209529399872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8857366442680359},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.691433846950531},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6473594307899475},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.639397919178009},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.5053511261940002},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.49625712633132935},{"id":"https://openalex.org/C2985727698","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Semantic annotation","level":3,"score":0.45018327236175537},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.447335809469223},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.4416339695453644},{"id":"https://openalex.org/C2780428219","wikidata":"https://www.wikidata.org/wiki/Q16952335","display_name":"Cover (algebra)","level":2,"score":0.42482417821884155},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39867597818374634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2730209529399872},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/icassp.2014.6853822","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6853822","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.cmu.edu:lti-1077","is_oa":false,"landing_page_url":"http://repository.cmu.edu/cgi/viewcontent.cgi?article=1077&context=lti","pdf_url":null,"source":{"id":"https://openalex.org/S4306400668","display_name":"Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I74973139","host_organization_name":"Carnegie Mellon University","host_organization_lineage":["https://openalex.org/I74973139"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Language Technologies Institute","raw_type":"text"},{"id":"pmh:doi:10.1184/r1/6473678","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Journal contribution"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1000.3050","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1000.3050","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://repository.cmu.edu/cgi/viewcontent.cgi?article%3D1077%26context%3Dlti","raw_type":"text"},{"id":"pmh:oai:figshare.com:article/6473678","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Semi-automatic_audio_semantic_concept_discovery_for_multimedia_retrieval/6473678","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},{"id":"doi:10.1184/r1/6473678.v1","is_oa":true,"landing_page_url":"https://doi.org/10.1184/r1/6473678.v1","pdf_url":null,"source":{"id":"https://openalex.org/S7407050927","display_name":"KiltHub Repository","issn_l":null,"issn":[],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/6473678","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/Semi-automatic_audio_semantic_concept_discovery_for_multimedia_retrieval/6473678","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.8500000238418579,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306116","display_name":"U.S. Department of the Interior","ror":"https://ror.org/03v0pmy70"},{"id":"https://openalex.org/F4320333452","display_name":"Interior Business Center","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1535031652","https://openalex.org/W1600745603","https://openalex.org/W1880262756","https://openalex.org/W1988419820","https://openalex.org/W2036931824","https://openalex.org/W2065784292","https://openalex.org/W2127612600","https://openalex.org/W2144037622","https://openalex.org/W2396707013","https://openalex.org/W2911964244","https://openalex.org/W4237791300","https://openalex.org/W6678951767","https://openalex.org/W6679740967"],"related_works":["https://openalex.org/W2369337446","https://openalex.org/W2126412646","https://openalex.org/W4385569300","https://openalex.org/W2889470921","https://openalex.org/W2574165153","https://openalex.org/W2251095918","https://openalex.org/W2206855020","https://openalex.org/W2105339902","https://openalex.org/W2972508764","https://openalex.org/W1978635732"],"abstract_inverted_index":{"Huge":[0],"amount":[1],"of":[2],"videos":[3],"on":[4,118],"the":[5,32,39,51,76,87,98,109,116],"Internet":[6],"have":[7],"rare":[8],"textual":[9],"information,":[10],"which":[11],"makes":[12],"video":[13],"retrieval":[14],"challenging":[15],"given":[16],"a":[17,44,59,71],"text":[18],"query.":[19,56],"Previous":[20],"work":[21],"explored":[22],"semantic":[23,77],"concepts":[24,34,49,110],"for":[25],"content":[26],"analysis":[27],"to":[28,37,74,93,106],"assist":[29],"retrieval.":[30],"However,":[31],"human-defined":[33],"might":[35],"fail":[36],"cover":[38],"data":[40],"and":[41,50,63,102],"there":[42],"is":[43,61],"potential":[45],"gap":[46],"between":[47],"these":[48,67],"semantics":[52],"expected":[53],"from":[54,97],"user's":[55],"Also,":[57],"building":[58],"corpus":[60],"expensive":[62],"time-consuming.":[64],"To":[65],"address":[66],"issues,":[68],"we":[69,89],"propose":[70],"semi-automatic":[72],"framework":[73],"discover":[75],"concepts.":[78],"We":[79,114],"limit":[80],"ourselves":[81],"in":[82],"audio":[83],"modality":[84],"here.":[85],"In":[86],"paper,":[88],"also":[90],"discuss":[91],"how":[92],"select":[94],"meaningful":[95],"vocabulary":[96],"discovered":[99],"hierarchical":[100],"sub-categories":[101],"provide":[103],"an":[104],"approach":[105],"detect":[107],"all":[108],"without":[111],"further":[112],"annotation.":[113],"evaluate":[115],"method":[117],"NIST":[119],"2011":[120],"multimedia":[121],"event":[122],"detection":[123],"(MED)":[124],"dataset.":[125]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
