{"id":"https://openalex.org/W2913959203","doi":"https://doi.org/10.1109/slt.2018.8639630","title":"Investigating Deep Neural Networks for Speaker Diarization in the DIHARD Challenge","display_name":"Investigating Deep Neural Networks for Speaker Diarization in the DIHARD Challenge","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913959203","doi":"https://doi.org/10.1109/slt.2018.8639630","mag":"2913959203"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/123248/1/himawan_1145.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039529498","display_name":"Ivan Himawan","orcid":"https://orcid.org/0000-0003-3848-244X"},"institutions":[{"id":"https://openalex.org/I2802536394","display_name":"Speech Pathology Australia","ror":"https://ror.org/03z4zm883","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802536394"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Ivan Himawan","raw_affiliation_strings":["Speech Research Lab, Queensland University of Technologym, Australia"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Queensland University of Technologym, Australia","institution_ids":["https://openalex.org/I2802536394","https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100776664","display_name":"Md Hafizur Rahman","orcid":"https://orcid.org/0000-0001-6576-1554"},"institutions":[{"id":"https://openalex.org/I2802536394","display_name":"Speech Pathology Australia","ror":"https://ror.org/03z4zm883","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802536394"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Md Hafizur Rahman","raw_affiliation_strings":["Speech Research Lab, Queensland University of Technologym, Australia"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Queensland University of Technologym, Australia","institution_ids":["https://openalex.org/I2802536394","https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"institutions":[{"id":"https://openalex.org/I2802536394","display_name":"Speech Pathology Australia","ror":"https://ror.org/03z4zm883","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802536394"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Speech Research Lab, Queensland University of Technologym, Australia"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Queensland University of Technologym, Australia","institution_ids":["https://openalex.org/I2802536394","https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034095159","display_name":"Clinton Fookes","orcid":"https://orcid.org/0000-0002-8515-6324"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]},{"id":"https://openalex.org/I2802536394","display_name":"Speech Pathology Australia","ror":"https://ror.org/03z4zm883","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802536394"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Clinton Fookes","raw_affiliation_strings":["Speech Research Lab, Queensland University of Technologym, Australia"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Queensland University of Technologym, Australia","institution_ids":["https://openalex.org/I2802536394","https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023434638","display_name":"Ahilan Kanagasundaram","orcid":"https://orcid.org/0000-0002-0533-7986"},"institutions":[{"id":"https://openalex.org/I2802536394","display_name":"Speech Pathology Australia","ror":"https://ror.org/03z4zm883","country_code":"AU","type":"other","lineage":["https://openalex.org/I2802536394"]},{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ahilan Kanagasundaram","raw_affiliation_strings":["Speech Research Lab, Queensland University of Technologym, Australia"],"affiliations":[{"raw_affiliation_string":"Speech Research Lab, Queensland University of Technologym, Australia","institution_ids":["https://openalex.org/I2802536394","https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039529498"],"corresponding_institution_ids":["https://openalex.org/I160993911","https://openalex.org/I2802536394"],"apc_list":null,"apc_paid":null,"fwci":0.6761,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78899801,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1997","issue":null,"first_page":"1029","last_page":"1035"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9986000061035156,"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":0.8226925730705261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7613248825073242},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5991081595420837},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5813348889350891},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5310063362121582},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5109642744064331},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.506308913230896},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.46676725149154663},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.45453929901123047},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44943156838417053},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.4213634729385376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3842695355415344},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.11032634973526001},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06812837719917297}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8226925730705261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7613248825073242},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5991081595420837},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5813348889350891},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5310063362121582},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5109642744064331},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.506308913230896},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.46676725149154663},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.45453929901123047},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44943156838417053},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.4213634729385376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3842695355415344},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.11032634973526001},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06812837719917297},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/slt.2018.8639630","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:123248","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/123248/1/himawan_1145.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 7th IEEE Workshop on Spoken Language Technology (SLT-2018)","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:123248","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/123248/1/himawan_1145.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 7th IEEE Workshop on Spoken Language Technology (SLT-2018)","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2913959203.pdf","grobid_xml":"https://content.openalex.org/works/W2913959203.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W204053250","https://openalex.org/W866349134","https://openalex.org/W1480629789","https://openalex.org/W1484181928","https://openalex.org/W1506438021","https://openalex.org/W1524333225","https://openalex.org/W1836465849","https://openalex.org/W1965819578","https://openalex.org/W2039057510","https://openalex.org/W2046056978","https://openalex.org/W2081074144","https://openalex.org/W2096733369","https://openalex.org/W2114925438","https://openalex.org/W2115599677","https://openalex.org/W2150769028","https://openalex.org/W2160815625","https://openalex.org/W2166980079","https://openalex.org/W2198484938","https://openalex.org/W2338994564","https://openalex.org/W2360384684","https://openalex.org/W2406555014","https://openalex.org/W2481304079","https://openalex.org/W2514794854","https://openalex.org/W2549349626","https://openalex.org/W2612434969","https://openalex.org/W2638067502","https://openalex.org/W2743167696","https://openalex.org/W2745733005","https://openalex.org/W2748488820","https://openalex.org/W2772376594","https://openalex.org/W2890964092","https://openalex.org/W3099206234","https://openalex.org/W3208240190","https://openalex.org/W4234330420","https://openalex.org/W4245862033","https://openalex.org/W4248480789","https://openalex.org/W6608353291","https://openalex.org/W6623950054","https://openalex.org/W6628623136","https://openalex.org/W6628802092","https://openalex.org/W6631362777","https://openalex.org/W6638667902","https://openalex.org/W6714102123","https://openalex.org/W6737575990","https://openalex.org/W6742972455","https://openalex.org/W6746670937","https://openalex.org/W6802591457"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W66821593","https://openalex.org/W2149220986","https://openalex.org/W1521299571","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W4235705411","https://openalex.org/W1493012537","https://openalex.org/W2144470400","https://openalex.org/W2911612049"],"abstract_inverted_index":{"We":[0,56],"investigate":[1],"the":[2,10,50,53,61,68,88,97],"use":[3],"of":[4,77,99],"deep":[5],"neural":[6],"networks":[7],"(DNNs)":[8],"for":[9,49,67,87],"speaker":[11,45],"diarization":[12,70,89],"task":[13],"to":[14,47],"improve":[15],"performance":[16,98],"under":[17],"domain":[18,23,36,84],"mismatched":[19,85],"conditions.":[20],"Three":[21],"unsupervised":[22],"adaptation":[24],"techniques,":[25],"namely":[26],"inter-dataset":[27],"variability":[28],"compensation":[29],"(IDVC),":[30],"domain-invariant":[31],"covariance":[32],"normalization":[33],"(DICN),":[34],"and":[35],"mismatch":[37,51],"modeling":[38],"(DMM),":[39],"are":[40],"applied":[41],"on":[42,60],"DNN":[43],"based":[44],"embeddings":[46],"compensate":[48],"in":[52],"embedding":[54],"subspace.":[55],"present":[57],"results":[58,92],"conducted":[59],"DIHARD":[62],"data,":[63],"which":[64],"was":[65],"released":[66],"2018":[69],"challenge.":[71],"Collected":[72],"from":[73],"a":[74],"diverse":[75],"set":[76],"domains,":[78],"this":[79],"data":[80],"provides":[81],"very":[82],"challenging":[83],"conditions":[86],"task.":[90],"Our":[91],"provide":[93],"insights":[94],"into":[95],"how":[96],"our":[100],"proposed":[101],"system":[102],"could":[103],"be":[104],"further":[105],"improved.":[106]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
