{"id":"https://openalex.org/W1997581315","doi":"https://doi.org/10.4018/jmdem.2012070101","title":"On the Applicability of Speaker Diarization to Audio Indexing of Non-Speech and Mixed Non-Speech/Speech Video Soundtracks","display_name":"On the Applicability of Speaker Diarization to Audio Indexing of Non-Speech and Mixed Non-Speech/Speech Video Soundtracks","publication_year":2012,"publication_date":"2012-07-01","ids":{"openalex":"https://openalex.org/W1997581315","doi":"https://doi.org/10.4018/jmdem.2012070101","mag":"1997581315"},"language":"en","primary_location":{"id":"doi:10.4018/jmdem.2012070101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jmdem.2012070101","pdf_url":null,"source":{"id":"https://openalex.org/S87630009","display_name":"International Journal of Multimedia Data Engineering and Management","issn_l":"1947-8534","issn":["1947-8534","1947-8542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Multimedia Data Engineering and Management","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/A5001835623","display_name":"Robert Mertens","orcid":"https://orcid.org/0000-0002-9442-4140"},"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":true,"raw_author_name":"Robert Mertens","raw_affiliation_strings":["International Computer Science Institute, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076474156","display_name":"Po-Sen Huang","orcid":"https://orcid.org/0000-0003-1470-0991"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Po-Sen Huang","raw_affiliation_strings":["Beckman Institute, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006513718","display_name":"Luke Gottlieb","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"]},{"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":"Luke Gottlieb","raw_affiliation_strings":["International Computer Science Institute, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062323483","display_name":"Gerald Friedland","orcid":"https://orcid.org/0000-0002-9400-6539"},"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":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, University of California, Berkeley, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, University of California, Berkeley, USA","institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028124265","display_name":"Ajay Divakaran","orcid":"https://orcid.org/0000-0003-0371-5346"},"institutions":[{"id":"https://openalex.org/I1298353152","display_name":"SRI International","ror":"https://ror.org/05s570m15","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1298353152"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ajay Divakaran","raw_affiliation_strings":["SRI International Sarnoff, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SRI International Sarnoff, USA","institution_ids":["https://openalex.org/I1298353152"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Beckman Institute, University of Illinois at Urbana-Champaign, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, University of Illinois at Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001835623"],"corresponding_institution_ids":["https://openalex.org/I1297971548","https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.2476,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.52502056,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"3","issue":"3","first_page":"1","last_page":"19"},"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/T11439","display_name":"Video Analysis and Summarization","score":0.9965999722480774,"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/T10860","display_name":"Speech and Audio Processing","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8409055471420288},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.8308722972869873},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6261618733406067},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5982759594917297},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.4769112765789032},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.45239678025245667},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.43679821491241455},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41575315594673157},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36773401498794556},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3195255994796753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3171781897544861}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8409055471420288},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8308722972869873},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6261618733406067},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5982759594917297},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.4769112765789032},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.45239678025245667},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.43679821491241455},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41575315594673157},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36773401498794556},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3195255994796753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3171781897544861},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.4018/jmdem.2012070101","is_oa":false,"landing_page_url":"https://doi.org/10.4018/jmdem.2012070101","pdf_url":null,"source":{"id":"https://openalex.org/S87630009","display_name":"International Journal of Multimedia Data Engineering and Management","issn_l":"1947-8534","issn":["1947-8534","1947-8542"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320424","host_organization_name":"IGI Global","host_organization_lineage":["https://openalex.org/P4310320424"],"host_organization_lineage_names":["IGI Global"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Multimedia Data Engineering and Management","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1033.4365","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1033.4365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/%7Ehuang146/papers/AudioIndexing_IJDEM.pdf","raw_type":"text"},{"id":"pmh:oai:RePEc:igg:jmdem0:v:3:y:2012:i:3:p:1-19","is_oa":false,"landing_page_url":"http://services.igi-global.com/resolvedoi/resolve.aspx?doi=10.4018/jmdem.2012070101","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"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":"article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5799999833106995}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1493036841","https://openalex.org/W1564518192","https://openalex.org/W1929391603","https://openalex.org/W2024932032","https://openalex.org/W2082968463","https://openalex.org/W2098553397","https://openalex.org/W2110783210","https://openalex.org/W2112306108","https://openalex.org/W2119577488","https://openalex.org/W2126432406","https://openalex.org/W2137117795","https://openalex.org/W2147069236","https://openalex.org/W2153635508","https://openalex.org/W2154159734","https://openalex.org/W2164882318","https://openalex.org/W2274583232","https://openalex.org/W2396707013","https://openalex.org/W2497516627","https://openalex.org/W2917409665","https://openalex.org/W3148746558","https://openalex.org/W4296262844","https://openalex.org/W6759908577"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2122924390","https://openalex.org/W2964829415","https://openalex.org/W2131711534","https://openalex.org/W642007152","https://openalex.org/W2341426843"],"abstract_inverted_index":{"A":[0],"video\u2019s":[1],"soundtrack":[2],"is":[3,78,168],"usually":[4,85],"highly":[5,59,64],"correlated":[6],"to":[7,24,68,108,115,134,206,223,234],"its":[8],"content.":[9],"Hence,":[10],"audio-based":[11],"techniques":[12],"have":[13],"recently":[14],"emerged":[15],"as":[16,39,56,232],"a":[17,71,89,158,195,238],"means":[18],"for":[19,126,241],"video":[20],"concept":[21],"detection":[22],"complementary":[23],"visual":[25],"analysis.":[26],"Most":[27],"state-of-the-art":[28],"approaches":[29,45],"rely":[30],"on":[31,181],"manual":[32,51,61],"definition":[33],"of":[34,74,91,164,185,203,229],"predefined":[35,82,196],"sound":[36,112,155],"concepts":[37,83,113,118,122],"such":[38],"\u201cngine":[40],"sounds,\u201d":[41],"\u201cutdoor/indoor":[42],"sounds.\u201d":[43],"These":[44],"come":[46],"with":[47,66,246],"three":[48],"major":[49],"drawbacks:":[50],"definitions":[52,62],"do":[53],"not":[54],"scale":[55],"they":[57],"are":[58,63,84,132,173],"domain-dependent,":[60],"subjective":[65],"respect":[67],"annotators":[69],"and":[70,119,170,199,236],"large":[72],"part":[73],"the":[75,81,92,136,162,182,191,200,226],"audio":[76,99,127,145,166],"content":[77,163],"omitted":[79],"since":[80],"found":[86],"only":[87],"in":[88,143,151,194,221],"fraction":[90],"soundtrack.":[93],"This":[94,175],"paper":[95],"explores":[96],"how":[97,120,216],"unsupervised":[98],"segmentation":[100],"systems":[101,131],"like":[102],"speaker":[103],"diarization":[104,130,159,192,217],"can":[105,123,218],"be":[106,124,219],"adapted":[107],"automatically":[109],"identify":[110],"low-level":[111],"similar":[114,149,171,186],"annotator":[116],"defined":[117],"these":[121],"used":[125],"indexing.":[128,248],"Speaker":[129],"designed":[133],"answer":[135],"question":[137],"\u201cho":[138],"spoke":[139],"when?\u201dby":[140],"finding":[141],"segments":[142,188],"an":[144,165,178],"stream":[146],"that":[147],"exhibit":[148],"properties":[150,184,228],"feature":[152],"space,":[153],"i.e.,":[154],"similar.":[156],"Using":[157],"system,":[160],"all":[161],"file":[167],"analyzed":[169],"sounds":[172,231],"clustered.":[174],"article":[176],"provides":[177],"in-depth":[179],"analysis":[180],"statistic":[183],"acoustic":[187,227],"identified":[189],"by":[190],"system":[193,240],"document":[197,209],"set":[198],"theoretical":[201],"fitness":[202],"this":[204],"approach":[205],"discern":[207],"one":[208],"class":[210],"from":[211],"another.":[212],"It":[213],"also":[214],"discusses":[215],"tuned":[220],"order":[222],"better":[224],"reflect":[225],"general":[230],"opposed":[233],"speech":[235],"introduces":[237],"proof-of-concept":[239],"multimedia":[242],"event":[243],"classification":[244],"working":[245],"diarization-based":[247]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
