{"id":"https://openalex.org/W2164512637","doi":"https://doi.org/10.1109/tasl.2009.2015089","title":"Prosodic and other Long-Term Features for Speaker Diarization","display_name":"Prosodic and other Long-Term Features for Speaker Diarization","publication_year":2009,"publication_date":"2009-06-16","ids":{"openalex":"https://openalex.org/W2164512637","doi":"https://doi.org/10.1109/tasl.2009.2015089","mag":"2164512637"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2009.2015089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2015089","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Audio, Speech, and Language Processing","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/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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Gerald Friedland","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"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/A5003562101","display_name":"Oriol Vinyals","orcid":"https://orcid.org/0000-0001-7848-7283"},"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":"Oriol Vinyals","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"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/A5100715216","display_name":"Yan Huang","orcid":"https://orcid.org/0000-0002-7925-4841"},"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":"Yan Huang","raw_affiliation_strings":["International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5035471597","display_name":"Christian M\u00fcller","orcid":"https://orcid.org/0000-0002-3216-8516"},"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":"Christian Muller","raw_affiliation_strings":["DFKI, Saarbrucken, Germany","International Computer Science Institute, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"DFKI, Saarbrucken, Germany","institution_ids":[]},{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062323483"],"corresponding_institution_ids":["https://openalex.org/I1297971548"],"apc_list":null,"apc_paid":null,"fwci":17.8835,"has_fulltext":false,"cited_by_count":79,"citation_normalized_percentile":{"value":0.99349514,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":"5","first_page":"985","last_page":"993"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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/nist","display_name":"NIST","score":0.9372889995574951},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9245142340660095},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.773210883140564},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.733320951461792},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6974495053291321},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5782928466796875},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.48040011525154114},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4390188753604889},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3839466869831085},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3308274745941162},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.061639755964279175}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.9372889995574951},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9245142340660095},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.773210883140564},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.733320951461792},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6974495053291321},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5782928466796875},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.48040011525154114},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4390188753604889},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3839466869831085},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3308274745941162},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.061639755964279175},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2009.2015089","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2009.2015089","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"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 Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6399999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W7559903","https://openalex.org/W48568691","https://openalex.org/W75083802","https://openalex.org/W1482605500","https://openalex.org/W1506281249","https://openalex.org/W1538905335","https://openalex.org/W1563235770","https://openalex.org/W1591607137","https://openalex.org/W1622483327","https://openalex.org/W1827418370","https://openalex.org/W1875231349","https://openalex.org/W1983746412","https://openalex.org/W1989674379","https://openalex.org/W2008957275","https://openalex.org/W2042860351","https://openalex.org/W2044591814","https://openalex.org/W2075978670","https://openalex.org/W2107831318","https://openalex.org/W2110783210","https://openalex.org/W2113386290","https://openalex.org/W2114851258","https://openalex.org/W2121765613","https://openalex.org/W2129244720","https://openalex.org/W2144125830","https://openalex.org/W2146889072","https://openalex.org/W2153994037","https://openalex.org/W2156255174","https://openalex.org/W2169165592","https://openalex.org/W2338994564","https://openalex.org/W3127686677","https://openalex.org/W4214556932","https://openalex.org/W4244494905","https://openalex.org/W4285719527","https://openalex.org/W6628911050","https://openalex.org/W6636526691","https://openalex.org/W6639350448","https://openalex.org/W6659344013","https://openalex.org/W6676245417","https://openalex.org/W6684648996"],"related_works":["https://openalex.org/W2118039276","https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2149402184","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,32,104],"is":[2],"defined":[3],"as":[4],"the":[5,56,68,80,109,114],"task":[6],"of":[7,21,59,82,99],"determining":[8],"ldquowho":[9],"spoke":[10],"whenrdquo":[11],"given":[12],"an":[13],"audio":[14],"track":[15],"and":[16,45,94],"no":[17],"other":[18,46],"prior":[19],"knowledge":[20],"any":[22],"kind.":[23],"The":[24,85],"following":[25],"article":[26],"shows":[27],"how":[28,67],"a":[29,52,96],"state-of-the-art":[30],"speaker":[31,57,83],"system":[33,111],"can":[34,72],"be":[35,73],"improved":[36],"by":[37],"combining":[38],"traditional":[39],"short-term":[40,76],"features":[41,71,77],"(MFCCs)":[42],"with":[43,75],"prosodic":[44],"long-term":[47,62,70],"features.":[48,63],"First,":[49],"we":[50,65],"present":[51],"framework":[53],"to":[54,78,108],"study":[55],"discriminability":[58],"70":[60],"different":[61],"Then,":[64],"show":[66,95],"top-ranked":[69],"combined":[74],"increase":[79],"accuracy":[81],"diarization.":[84],"results":[86],"were":[87],"measured":[88],"on":[89],"standardized":[90],"datasets":[91],"(NIST":[92],"RT)":[93],"consistent":[97],"improvement":[98],"about":[100],"30%":[101],"relative":[102],"in":[103,117],"error":[105],"rate":[106],"compared":[107],"best":[110],"presented":[112],"at":[113],"NIST":[115],"evaluation":[116],"2007.":[118]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":6},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}