{"id":"https://openalex.org/W1670780163","doi":"https://doi.org/10.1109/icassp.2015.7178888","title":"A cluster-voting approach for speaker diarization and linking of Australian broadcast news recordings","display_name":"A cluster-voting approach for speaker diarization and linking of Australian broadcast news recordings","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1670780163","doi":"https://doi.org/10.1109/icassp.2015.7178888","mag":"1670780163"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/85159/1/Houman_paper2_ICASSP15.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012849807","display_name":"Houman Ghaemmaghami","orcid":null},"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"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Houman Ghaemmaghami","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia#TAB#","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000014182","display_name":"David Dean","orcid":"https://orcid.org/0000-0003-1274-9775"},"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"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"David Dean","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia#TAB#","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055128383","display_name":"Sridha Sridharan","orcid":"https://orcid.org/0000-0003-4316-9001"},"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"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sridha Sridharan","raw_affiliation_strings":["Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia#TAB#"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]},{"raw_affiliation_string":"Speech and Audio Research Laboratory, Queensland University of Technology, Brisbane, Australia#TAB#","institution_ids":["https://openalex.org/I160993911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012849807"],"corresponding_institution_ids":["https://openalex.org/I160993911"],"apc_list":null,"apc_paid":null,"fwci":3.5586,"has_fulltext":true,"cited_by_count":10,"citation_normalized_percentile":{"value":0.934162,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4829","last_page":"4833"},"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/T11309","display_name":"Music and Audio Processing","score":0.9983999729156494,"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/T10860","display_name":"Speech and Audio Processing","score":0.9979000091552734,"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":0.8421666026115417},{"id":"https://openalex.org/keywords/viterbi-algorithm","display_name":"Viterbi algorithm","score":0.7877751588821411},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7813127040863037},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7521010637283325},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.5570636987686157},{"id":"https://openalex.org/keywords/complete-linkage-clustering","display_name":"Complete-linkage clustering","score":0.5159795880317688},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.49658137559890747},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.483447402715683},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4606705904006958},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4067593514919281},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3880295157432556},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.27460265159606934},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.18528953194618225},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.1594735085964203},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.12228080630302429}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8421666026115417},{"id":"https://openalex.org/C60582962","wikidata":"https://www.wikidata.org/wiki/Q83886","display_name":"Viterbi algorithm","level":3,"score":0.7877751588821411},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7813127040863037},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7521010637283325},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.5570636987686157},{"id":"https://openalex.org/C23822008","wikidata":"https://www.wikidata.org/wiki/Q5156437","display_name":"Complete-linkage clustering","level":5,"score":0.5159795880317688},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.49658137559890747},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.483447402715683},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4606705904006958},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4067593514919281},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3880295157432556},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.27460265159606934},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.18528953194618225},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.1594735085964203},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.12228080630302429}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2015.7178888","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178888","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:85159","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/85159/1/Houman_paper2_ICASSP15.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 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015","raw_type":"Chapter in Book, Report or Conference volume"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:85159","is_oa":true,"landing_page_url":null,"pdf_url":"https://eprints.qut.edu.au/85159/1/Houman_paper2_ICASSP15.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 40th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2015","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1670780163.pdf","grobid_xml":"https://content.openalex.org/works/W1670780163.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W37845981","https://openalex.org/W204053250","https://openalex.org/W1482605500","https://openalex.org/W2081074144","https://openalex.org/W2110023316","https://openalex.org/W2115599677","https://openalex.org/W2140623944","https://openalex.org/W2142333570","https://openalex.org/W2146818968","https://openalex.org/W2151293655","https://openalex.org/W2159591770","https://openalex.org/W2166980079","https://openalex.org/W2250641567","https://openalex.org/W2338994564","https://openalex.org/W2396101999","https://openalex.org/W2396559392","https://openalex.org/W2397634864","https://openalex.org/W2397770179","https://openalex.org/W2398046462","https://openalex.org/W2404175974","https://openalex.org/W2612380871","https://openalex.org/W2977447808","https://openalex.org/W4239330706","https://openalex.org/W6601517864","https://openalex.org/W6608353291","https://openalex.org/W6628911050","https://openalex.org/W6682143266","https://openalex.org/W6691613585","https://openalex.org/W6712325649","https://openalex.org/W6768473177"],"related_works":["https://openalex.org/W1502693945","https://openalex.org/W1556857061","https://openalex.org/W2177420620","https://openalex.org/W4308671730","https://openalex.org/W2405439032","https://openalex.org/W4380994539","https://openalex.org/W2146603315","https://openalex.org/W2101165556","https://openalex.org/W3151768066","https://openalex.org/W159467828"],"abstract_inverted_index":{"We":[0,27,54,92,114],"present":[1],"a":[2,33,46,65,79],"clustering-only":[3],"approach":[4,97,130],"to":[5,11,44,63,75,82,98,118,138],"the":[6,13,16,69,83,89,106,133,139],"problem":[7],"of":[8,32,48,109],"speaker":[9,101],"diarization":[10,102,140],"eliminate":[12],"need":[14],"for":[15,51],"commonly":[17],"employed":[18],"and":[19,24,35,71,103,126,144],"computationally":[20],"expensive":[21],"Viterbi":[22,124],"segmentation":[23,42],"realignment":[25,125],"stage.":[26],"use":[28,93],"multiple":[29],"linear":[30,90],"segmentations":[31],"recording":[34],"carry":[36,99],"out":[37,100],"complete-linkage":[38,73],"clustering":[39,49,58,74],"within":[40],"each":[41,52],"scenario":[43],"obtain":[45],"set":[47],"decisions":[50],"case.":[53],"then":[55],"collect":[56],"all":[57,61],"decisions,":[59],"across":[60,105],"cases,":[62],"compute":[64],"pairwise":[66],"vote":[67],"between":[68],"segments":[70],"conduct":[72],"cluster":[76],"them":[77],"at":[78],"resolution":[80],"equal":[81],"minimum":[84],"segment":[85],"length":[86],"used":[87],"in":[88],"segmentations.":[91],"our":[94,116,129],"proposed":[95],"cluster-voting":[96],"linking":[104],"SAIVT-BNEWS":[107],"corpus":[108],"Australian":[110],"broadcast":[111],"news":[112],"data.":[113],"compare":[115],"technique":[117,135],"an":[119],"equivalent":[120],"baseline":[121,134],"system":[122],"with":[123,136],"show":[127],"that":[128],"can":[131],"outperform":[132],"respect":[137],"error":[141,146],"rate":[142,147],"(DER)":[143],"attribution":[145],"(AER).":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}