{"id":"https://openalex.org/W2886006657","doi":"https://doi.org/10.21437/interspeech.2018-2305","title":"Triplet Network with Attention for Speaker Diarization","display_name":"Triplet Network with Attention for Speaker Diarization","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2886006657","doi":"https://doi.org/10.21437/interspeech.2018-2305","mag":"2886006657"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-2305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1469466","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101697214","display_name":"Huan Song","orcid":"https://orcid.org/0000-0002-9639-9962"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Huan Song","raw_affiliation_strings":["Arizona State University, Sensor, Signal and Information Processing Center Center"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Sensor, Signal and Information Processing Center Center","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048170894","display_name":"Megan Willi","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Megan Willi","raw_affiliation_strings":["Arizona State University**"],"affiliations":[{"raw_affiliation_string":"Arizona State University**","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046632395","display_name":"Jayaraman J. Thiagarajan","orcid":"https://orcid.org/0000-0002-8517-5816"},"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"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayaraman J. Thiagarajan","raw_affiliation_strings":["Lawrence livermore National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["IAFSE-ECEE: Wireless Information Systems and Computational Architectures (WISCA)"],"affiliations":[{"raw_affiliation_string":"IAFSE-ECEE: Wireless Information Systems and Computational Architectures (WISCA)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074371899","display_name":"Andreas Spanias","orcid":"https://orcid.org/0000-0003-0306-9348"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andreas Spanias","raw_affiliation_strings":["HIDA: Arts, Media and Engineering, School of (AME)"],"affiliations":[{"raw_affiliation_string":"HIDA: Arts, Media and Engineering, School of (AME)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101697214"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":1.0154,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.82640266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3608","last_page":"3612"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9984999895095825,"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":0.9984999895095825,"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":0.9803000092506409,"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":0.9763000011444092,"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":0.8205163478851318},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7732813954353333},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.6992810964584351},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.545569896697998},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5234917402267456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49148499965667725},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4810329079627991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4628905653953552},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.436540424823761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3632822036743164}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8205163478851318},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7732813954353333},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.6992810964584351},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.545569896697998},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5234917402267456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49148499965667725},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4810329079627991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4628905653953552},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.436540424823761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3632822036743164},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-2305","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-2305","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:1469466","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1469466","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1469466","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1469466","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[{"score":0.7200000286102295,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4297807400","https://openalex.org/W1491159402","https://openalex.org/W2144208207","https://openalex.org/W4389984014","https://openalex.org/W1509309911","https://openalex.org/W1940231550","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"In":[0],"automatic":[1],"speech":[2,116],"processing":[3],"systems,":[4],"speaker":[5,88],"diarization":[6,119],"is":[7],"a":[8,125],"crucial":[9],"front-end":[10],"component":[11],"to":[12,94,98],"separate":[13],"segments":[14],"from":[15,79],"different":[16],"speakers.":[17],"Inspired":[18],"by":[19],"the":[20,48,64,73,80,102,113,128],"recent":[21],"success":[22],"of":[23,67,75],"deep":[24],"neural":[25],"networks":[26,56],"(DNNs)":[27],"in":[28,83,105],"semantic":[29],"inferencing,":[30],"triplet":[31],"loss-based":[32],"architectures":[33],"have":[34],"been":[35],"successfully":[36],"used":[37],"for":[38,57,87],"this":[39],"problem.":[40],"However,":[41],"existing":[42,137],"work":[43],"utilizes":[44],"conventional":[45],"i-vectors":[46],"as":[47],"input":[49],"representation":[50],"and":[51,101],"builds":[52],"simple":[53],"fully":[54,62],"connected":[55],"metric":[58,84,103],"learning,":[59],"thus":[60],"not":[61],"leveraging":[63],"modeling":[65],"power":[66],"DNN":[68],"architectures.":[69],"This":[70],"paper":[71],"investigates":[72],"importance":[74],"learning":[76,85],"effective":[77],"representations":[78],"sequences":[81],"directly":[82],"pipelines":[86],"diarization.":[89],"More":[90],"specifically,":[91],"we":[92],"propose":[93],"employ":[95],"attention":[96],"models":[97],"learn":[99],"embeddings":[100],"jointly":[104],"an":[106],"end-to-end":[107],"fashion.":[108],"Experiments":[109],"are":[110],"conducted":[111],"on":[112],"CALLHOME":[114],"conversational":[115],"corpus.":[117],"The":[118],"results":[120],"demonstrate":[121],"that,":[122],"besides":[123],"providing":[124],"unified":[126],"model,":[127],"proposed":[129],"approach":[130],"achieves":[131],"improved":[132],"performance":[133],"when":[134],"compared":[135],"against":[136],"approaches.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}