{"id":"https://openalex.org/W2612810660","doi":"https://doi.org/10.1109/tmm.2017.2703939","title":"DCAR: A Discriminative and Compact Audio Representation for Audio Processing","display_name":"DCAR: A Discriminative and Compact Audio Representation for Audio Processing","publication_year":2017,"publication_date":"2017-05-12","ids":{"openalex":"https://openalex.org/W2612810660","doi":"https://doi.org/10.1109/tmm.2017.2703939","mag":"2612810660"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2017.2703939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2017.2703939","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-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/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 Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2160-1721","affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461646","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-3603-6617"},"institutions":[{"id":"https://openalex.org/I108160477","display_name":"Hebei Agricultural University","ror":"https://ror.org/009fw8j44","country_code":"CN","type":"education","lineage":["https://openalex.org/I108160477"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China","College of Information Science and Technology, Agricultural University of Hebei, Hebei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China","institution_ids":[]},{"raw_affiliation_string":"College of Information Science and Technology, Agricultural University of Hebei, Hebei, China","institution_ids":["https://openalex.org/I108160477"]}]},{"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/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"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","US"],"is_corresponding":false,"raw_author_name":"Jaeyoung Choi","raw_affiliation_strings":["Delft University of Technology, Delft, The Netherlands","International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology, Delft, The Netherlands","institution_ids":["https://openalex.org/I98358874"]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"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/I1297971548","display_name":"International Computer Science Institute","ror":"https://ror.org/01ewh7m12","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1297971548"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael W. Mahoney","raw_affiliation_strings":["Department of Statistics, University of California, Berkeley, Berkeley, CA, USA","International Computer Science Institute, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Statistics, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"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/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]},{"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA, USA","Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"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":0.9321,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.74752914,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"19","issue":"12","first_page":"2637","last_page":"2650"},"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":0.9997000098228455,"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":0.9891999959945679,"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/discriminative-model","display_name":"Discriminative model","score":0.9132951498031616},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8184042572975159},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7356034517288208},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7121134996414185},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6524646282196045},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.6345986127853394},{"id":"https://openalex.org/keywords/grassmannian","display_name":"Grassmannian","score":0.6011098027229309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5917534232139587},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47025975584983826},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.43406230211257935},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3261425495147705},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.17877015471458435},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11885946989059448}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.9132951498031616},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8184042572975159},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7356034517288208},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7121134996414185},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6524646282196045},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.6345986127853394},{"id":"https://openalex.org/C162929932","wikidata":"https://www.wikidata.org/wiki/Q129638","display_name":"Grassmannian","level":2,"score":0.6011098027229309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5917534232139587},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47025975584983826},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.43406230211257935},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3261425495147705},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17877015471458435},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11885946989059448},{"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2017.2703939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2017.2703939","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.699999988079071}],"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/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/G8863732217","display_name":null,"funder_award_id":"61632004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1600745603","https://openalex.org/W1970625287","https://openalex.org/W1978274651","https://openalex.org/W1983496390","https://openalex.org/W1986964250","https://openalex.org/W2018832017","https://openalex.org/W2018951638","https://openalex.org/W2026012689","https://openalex.org/W2029223910","https://openalex.org/W2072184377","https://openalex.org/W2078950386","https://openalex.org/W2086384421","https://openalex.org/W2097187469","https://openalex.org/W2103235956","https://openalex.org/W2105055468","https://openalex.org/W2106326596","https://openalex.org/W2116373735","https://openalex.org/W2129476886","https://openalex.org/W2140321362","https://openalex.org/W2150769028","https://openalex.org/W2152322845","https://openalex.org/W2156481234","https://openalex.org/W2164882318","https://openalex.org/W2166334548","https://openalex.org/W2168010845","https://openalex.org/W2250384498","https://openalex.org/W2294993808","https://openalex.org/W2511428026","https://openalex.org/W2525899488","https://openalex.org/W2526050071","https://openalex.org/W2566935005","https://openalex.org/W2750790669","https://openalex.org/W2905522029","https://openalex.org/W3099514962","https://openalex.org/W3103385400","https://openalex.org/W4205293427","https://openalex.org/W6635660841","https://openalex.org/W6697597305","https://openalex.org/W6725104640"],"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":[3,40,85],"novel":[4],"two-phase":[5],"method":[6],"for":[7,133],"audio":[8,13,35,122],"representation,":[9],"discriminative":[10,76],"and":[11,16,23,65,77,103,127,136],"compact":[12,78],"representation":[14,117],"(DCAR),":[15],"evaluates":[17],"its":[18],"performance":[19,144],"at":[20],"detecting":[21],"events":[22],"scenes":[24],"in":[25],"consumer-produced":[26],"videos.":[27],"In":[28,68],"the":[29,51,71,94,101,114,160,164],"first":[30],"phase":[31,58],"of":[32,96,153,163],"DCAR,":[33],"each":[34,151],"track":[36],"is":[37,131],"modeled":[38],"using":[39],"Gaussian":[41],"mixture":[42],"model":[43,154],"(GMM)":[44],"that":[45,54,111],"includes":[46],"several":[47],"components":[48,72,90],"to":[49],"capture":[50],"variability":[52],"within":[53],"track.":[55],"The":[56,88,108,129],"second":[57],"takes":[59],"into":[60],"account":[61],"both":[62,134],"global":[63],"structure":[64,95,162],"local":[66],"structure.":[67],"this":[69],"phase,":[70],"are":[73],"rendered":[74],"more":[75],"by":[79],"formulating":[80],"an":[81],"optimization":[82],"problem":[83],"on":[84,113],"Grassmannian":[86],"manifold.":[87],"learned":[89],"can":[91],"effectively":[92],"represent":[93],"audio.":[97],"Our":[98],"experiments":[99],"used":[100],"YLI-MED":[102],"DCASE":[104],"Acoustic":[105],"Scenes":[106],"datasets.":[107],"results":[109],"show":[110],"variants":[112],"proposed":[115],"DCAR":[116],"consistently":[118],"outperform":[119],"four":[120],"popular":[121],"representations":[123],"(mv-vector,":[124],"i-vector,":[125],"GMM,":[126],"HEM-GMM).":[128],"advantage":[130],"significant":[132],"easier":[135],"harder":[137],"discrimination":[138],"tasks;":[139],"we":[140],"discuss":[141],"how":[142,150],"these":[143],"differences":[145],"across":[146],"tasks":[147],"follow":[148],"from":[149],"type":[152],"leverages":[155],"(or":[156],"does":[157],"not":[158],"leverage)":[159],"intrinsic":[161],"data.":[165]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}