{"id":"https://openalex.org/W2126432406","doi":"https://doi.org/10.1109/asru.2009.5373254","title":"Robust Speaker Diarization for short speech recordings","display_name":"Robust Speaker Diarization for short speech recordings","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2126432406","doi":"https://doi.org/10.1109/asru.2009.5373254","mag":"2126432406"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/146061","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037750159","display_name":"David Imseng","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]},{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"David Imseng","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland","Lausanne (EPFL), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]},{"raw_affiliation_string":"Lausanne (EPFL), Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"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/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, Berkeley, CA, USA"],"affiliations":[{"raw_affiliation_string":"International Computer Science Institute, Berkeley, CA, USA","institution_ids":["https://openalex.org/I1297971548"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5037750159"],"corresponding_institution_ids":["https://openalex.org/I5124864","https://openalex.org/I7495430"],"apc_list":null,"apc_paid":null,"fwci":6.3228,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96452919,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"18","issue":null,"first_page":"432","last_page":"437"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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/T11309","display_name":"Music and Audio Processing","score":0.9815999865531921,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.8939082622528076},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8685680031776428},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582614421844482},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7517424821853638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7195135354995728},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.52266925573349},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4462588131427765},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.41128265857696533},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4004649519920349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3628314137458801},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08547523617744446}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8939082622528076},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8685680031776428},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582614421844482},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7517424821853638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7195135354995728},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.52266925573349},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4462588131427765},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.41128265857696533},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4004649519920349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3628314137458801},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08547523617744446},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/asru.2009.5373254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373254","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition &amp; Understanding","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.360.3313","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.360.3313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://publications.idiap.ch/downloads/papers/2009/Imseng_ASRU_2009.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:146061","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},{"id":"pmh:oai:infoscience.epfl.ch:146429","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146429","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:146061","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/146061","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"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":"","raw_type":"Text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.4099999964237213,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W202282565","https://openalex.org/W1482605500","https://openalex.org/W1524832141","https://openalex.org/W1556474518","https://openalex.org/W1574017590","https://openalex.org/W2082968463","https://openalex.org/W2110783210","https://openalex.org/W2134584072","https://openalex.org/W2144125830","https://openalex.org/W2156255174","https://openalex.org/W2169165592","https://openalex.org/W2338994564","https://openalex.org/W2509822191","https://openalex.org/W4285719527","https://openalex.org/W6608286430","https://openalex.org/W6628911050","https://openalex.org/W6659344013","https://openalex.org/W6684648996","https://openalex.org/W6725232968"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W184241528","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2938358845"],"abstract_inverted_index":{"We":[0],"investigate":[1],"a":[2,48,96],"state-of-the-art":[3,56],"speaker":[4,28],"diarization":[5,29,57,99],"system":[6],"regarding":[7],"its":[8],"behavior":[9],"on":[10],"meetings":[11,104],"that":[12,45],"are":[13,38],"much":[14],"shorter":[15],"(from":[16],"500":[17],"seconds":[18],"down":[19],"to":[20,35,120],"100":[21],"seconds)":[22],"than":[23],"those":[24],"typically":[25],"analyzed":[26],"in":[27,92],"benchmarks.":[30],"First,":[31],"the":[32,63,66,70,78,81,89,98,107],"problems":[33],"inherent":[34],"this":[36,93],"task":[37],"analyzed.":[39],"Then,":[40],"we":[41],"propose":[42],"an":[43],"approach":[44],"consists":[46],"of":[47,69,72,80],"novel":[49],"initialization":[50],"parameter":[51],"estimation":[52,60],"method":[53,61],"for":[54,88,102],"typical":[55],"approaches.":[58],"The":[59],"balances":[62],"relationship":[64],"between":[65],"optimal":[67],"value":[68],"duration":[71,79],"speech":[73,82],"data":[74,115],"per":[75],"Gaussian":[76],"and":[77,110],"data,":[83],"which":[84],"is":[85,116],"verified":[86],"experimentally":[87],"first":[90],"time":[91],"article.":[94],"As":[95],"result,":[97],"error":[100],"rate":[101],"short":[103],"extracted":[105],"from":[106],"2006,":[108],"2007,":[109],"2009":[111],"NIST":[112],"RT":[113],"evaluation":[114],"decreased":[117],"by":[118],"up":[119],"50%":[121],"relative.":[122]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
