{"id":"https://openalex.org/W7559903","doi":"https://doi.org/10.21437/interspeech.2006-568","title":"Multi-stream speaker diarization systems for the meetings domain","display_name":"Multi-stream speaker diarization systems for the meetings domain","publication_year":2006,"publication_date":"2006-09-17","ids":{"openalex":"https://openalex.org/W7559903","doi":"https://doi.org/10.21437/interspeech.2006-568","mag":"7559903"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2006-568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-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/A5065719579","display_name":"Ascensi\u00f3n Gallardo-Antol\u00edn","orcid":"https://orcid.org/0000-0002-9322-3128"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ascensi\u00f3n Gallardo-Antol\u00edn","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051383020","display_name":"Xavier Anguera","orcid":"https://orcid.org/0000-0001-8659-3991"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xavier Anguera","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025158987","display_name":"Chuck Wooters","orcid":"https://orcid.org/0000-0002-3751-6313"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuck Wooters","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.7976,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.90233874,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"paper 1620","last_page":"Thu1A1O.3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9951000213623047,"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":0.9951000213623047,"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":0.9736999869346619,"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/T12031","display_name":"Speech and dialogue systems","score":0.9516000151634216,"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/speaker-diarisation","display_name":"Speaker diarisation","score":0.9129546880722046},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8286459445953369},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7129818201065063},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6609941124916077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.627304196357727},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6051960587501526},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5741823315620422},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5712399482727051},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5548322796821594},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5360878109931946},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5124691128730774},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4524582028388977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44692230224609375},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.43060022592544556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.425403356552124}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9129546880722046},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8286459445953369},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7129818201065063},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6609941124916077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.627304196357727},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6051960587501526},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5741823315620422},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5712399482727051},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5548322796821594},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5360878109931946},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5124691128730774},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4524582028388977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44692230224609375},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.43060022592544556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.425403356552124},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2006-568","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2006-568","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2006","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1539668574","https://openalex.org/W1553693276","https://openalex.org/W1986174057","https://openalex.org/W2052269122","https://openalex.org/W2099333848","https://openalex.org/W2104353650","https://openalex.org/W2118313846","https://openalex.org/W2144125830","https://openalex.org/W2156255174","https://openalex.org/W2172081649","https://openalex.org/W2400390095","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W1963976507","https://openalex.org/W2206035908","https://openalex.org/W3119288895","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W2185075503","https://openalex.org/W4247736853","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2162158162"],"abstract_inverted_index":{"In":[0,41],"the":[1,14,26,66,78,83,112,119,124],"context":[2],"of":[3,16,28,71,92,107],"speech":[4],"and":[5,59,68,88,96,98,101,129],"speaker":[6,33,73,135],"recognition":[7],"systems,":[8],"it":[9],"is":[10],"well":[11],"known":[12],"that":[13,111],"combination":[15,58,115,128],"different":[17,50,79,90],"feature":[18,55,127],"streams":[19],"can":[20],"improve":[21],"significantly":[22],"their":[23,62],"performance.":[24],"However,":[25],"application":[27,64],"multi-stream":[29,137],"(MS)":[30],"techniques":[31],"to":[32,65,118],"diarization":[34,74],"systems":[35],"has":[36],"not":[37],"been":[38],"extensively":[39],"studied.":[40],"this":[42,46],"paper,":[43],"we":[44,48],"address":[45],"issue:":[47],"formulate":[49],"MS":[51,113,126,130],"techniques,":[52],"such":[53],"as":[54],"combination,":[56],"probability":[57,114],"selection,":[60],"for":[61,82],"specific":[63],"segmentation":[67,120],"clustering":[69],"modules":[70],"a":[72],"system.":[75],"We":[76],"evaluate":[77],"methods":[80],"proposed":[81],"meetings":[84],"domain":[85],"(RT04s":[86],"database)":[87],"two":[89],"pairs":[91],"streams:":[93],"first,":[94],"MFCC":[95,100],"PLP":[97],"second,":[99],"prosodic":[102,139],"features.":[103,140],"For":[104],"both":[105],"types":[106],"multi-streams,":[108],"results":[109],"show":[110],"approach":[116],"applied":[117],"stage":[121],"clearly":[122],"outperforms":[123],"single-stream,":[125],"selection":[131],"systems.":[132],"Index":[133],"Terms:":[134],"diarization,":[136],"features,":[138]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}