{"id":"https://openalex.org/W2525899488","doi":"https://doi.org/10.1145/2964284.2970377","title":"A Discriminative and Compact Audio Representation for Event Detection","display_name":"A Discriminative and Compact Audio Representation for Event Detection","publication_year":2016,"publication_date":"2016-09-29","ids":{"openalex":"https://openalex.org/W2525899488","doi":"https://doi.org/10.1145/2964284.2970377","mag":"2525899488"},"language":"en","primary_location":{"id":"doi:10.1145/2964284.2970377","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2964284.2970377","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2964284.2970377?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2964284.2970377?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103145531","display_name":"Liping Jing","orcid":"https://orcid.org/0000-0003-2160-1721"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Liping Jing","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461605","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0001-9525-8861"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069814835","display_name":"Jaeyoung Choi","orcid":"https://orcid.org/0000-0001-9118-8050"},"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"]},{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["NL","US"],"is_corresponding":false,"raw_author_name":"Jaeyoung Choi","raw_affiliation_strings":["International Computer Science Institute & Delft University of Technology, Delft, Netherlands, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute & Delft University of Technology, Delft, Netherlands, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063693615","display_name":"Adam Janin","orcid":null},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Adam Janin","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083402055","display_name":"Julia Bernd","orcid":"https://orcid.org/0000-0002-9792-2743"},"institutions":[{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julia Bernd","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033006662","display_name":"Michael W. Mahoney","orcid":"https://orcid.org/0000-0001-7920-4652"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael W. Mahoney","raw_affiliation_strings":["International Computer Science Institute & University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute & University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]},{"id":"https://openalex.org/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute & University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute & University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5103145531"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":1.276,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.81426309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"61"},"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":0.9995999932289124,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9973000288009644,"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/discriminative-model","display_name":"Discriminative model","score":0.9558131098747253},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.7499614357948303},{"id":"https://openalex.org/keywords/grassmannian","display_name":"Grassmannian","score":0.7325363159179688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6817184686660767},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6513024568557739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.550133228302002},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5164549350738525},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5024228096008301},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48550868034362793},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4591905176639557},{"id":"https://openalex.org/keywords/phase","display_name":"Phase (matter)","score":0.4301702678203583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42664653062820435},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3176581561565399},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2230726182460785},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.1460188329219818}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9558131098747253},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.7499614357948303},{"id":"https://openalex.org/C162929932","wikidata":"https://www.wikidata.org/wiki/Q129638","display_name":"Grassmannian","level":2,"score":0.7325363159179688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6817184686660767},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6513024568557739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.550133228302002},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5164549350738525},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5024228096008301},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48550868034362793},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4591905176639557},{"id":"https://openalex.org/C44280652","wikidata":"https://www.wikidata.org/wiki/Q104837","display_name":"Phase (matter)","level":2,"score":0.4301702678203583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42664653062820435},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3176581561565399},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2230726182460785},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.1460188329219818},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2964284.2970377","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2964284.2970377","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2964284.2970377?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2964284.2970377","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2964284.2970377","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2964284.2970377?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM international conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7599999904632568,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G1989447638","display_name":null,"funder_award_id":"61370129","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4085403815","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4698383990","display_name":null,"funder_award_id":"IRT201206","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4844777956","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320337547","funder_display_name":"Laboratory Directed Research and Development"},{"id":"https://openalex.org/G8086048848","display_name":null,"funder_award_id":"61375062","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G991281326","display_name":null,"funder_award_id":"AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337547","display_name":"Laboratory Directed Research and Development","ror":"https://ror.org/01e41cf67"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2525899488.pdf","grobid_xml":"https://content.openalex.org/works/W2525899488.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1600745603","https://openalex.org/W1804110266","https://openalex.org/W1970625287","https://openalex.org/W1986964250","https://openalex.org/W2018951638","https://openalex.org/W2072184377","https://openalex.org/W2086384421","https://openalex.org/W2097187469","https://openalex.org/W2103235956","https://openalex.org/W2105055468","https://openalex.org/W2129476886","https://openalex.org/W2140321362","https://openalex.org/W2150769028","https://openalex.org/W2164882318","https://openalex.org/W2250384498","https://openalex.org/W2294701319","https://openalex.org/W2490800645","https://openalex.org/W2508000579","https://openalex.org/W2525899488","https://openalex.org/W2915722758","https://openalex.org/W3103385400","https://openalex.org/W3143835353","https://openalex.org/W4205293427","https://openalex.org/W6633616865"],"related_works":["https://openalex.org/W2146591867","https://openalex.org/W2289868279","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W4315836293","https://openalex.org/W4243888788","https://openalex.org/W1975359510","https://openalex.org/W3004352674","https://openalex.org/W2769884427"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,26],"novel":[4],"two-phase":[5],"method":[6],"for":[7],"audio":[8,21,80,97],"representation:":[9],"Discriminative":[10],"and":[11,51,63,101],"Compact":[12],"Audio":[13],"Representation":[14],"(DCAR).":[15],"In":[16,54],"the":[17,37,57,77,85,90],"first":[18],"phase,":[19,56],"each":[20],"track":[22],"is":[23],"modeled":[24],"using":[25],"Gaussian":[27],"mixture":[28],"model":[29],"(GMM)":[30],"that":[31,40,89],"includes":[32],"several":[33],"components":[34,58],"to":[35],"capture":[36],"variability":[38],"within":[39],"track.":[41],"The":[42],"second":[43],"phase":[44],"takes":[45],"into":[46],"account":[47],"both":[48],"global":[49],"structure":[50,78],"local":[52],"structure.":[53],"this":[55],"are":[59],"rendered":[60],"more":[61],"discriminative":[62],"compact":[64],"by":[65],"formulating":[66],"an":[67],"optimization":[68],"problem":[69],"on":[70,84],"Grassmannian":[71],"manifolds,":[72],"which":[73],"we":[74],"found":[75],"represents":[76],"of":[79],"effectively.":[81],"Experimental":[82],"results":[83],"YLI-MED":[86],"dataset":[87],"show":[88],"proposed":[91],"DCAR":[92],"representation":[93],"consistently":[94],"outperforms":[95],"state-of-the-art":[96],"representations:":[98],"i-vector,":[99],"mv-vector,":[100],"GMM.":[102]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2}],"updated_date":"2026-05-03T08:25:01.440150","created_date":"2025-10-10T00:00:00"}