{"id":"https://openalex.org/W3137585377","doi":"https://doi.org/10.1109/taslp.2021.3067161","title":"Overlapping Speaker Segmentation Using Multiple Hypothesis Tracking of Fundamental Frequency","display_name":"Overlapping Speaker Segmentation Using Multiple Hypothesis Tracking of Fundamental Frequency","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3137585377","doi":"https://doi.org/10.1109/taslp.2021.3067161","mag":"3137585377"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2021.3067161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3067161","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97436/2/Hogg%20Overlapping%20Speaker%20Segmentation%202021%20Accepted.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5031002666","display_name":"Aidan O. T. Hogg","orcid":"https://orcid.org/0000-0001-5501-7799"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Aidan O. T. Hogg","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, London, U.K","Department of Electrical and Electronic Engineering, Imperial college London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-5501-7799","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial college London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061813792","display_name":"Christine Evers","orcid":"https://orcid.org/0000-0003-0757-5504"},"institutions":[{"id":"https://openalex.org/I43439940","display_name":"University of Southampton","ror":"https://ror.org/01ryk1543","country_code":"GB","type":"education","lineage":["https://openalex.org/I43439940"]},{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christine Evers","raw_affiliation_strings":["Department Electrical and Electronic Engineering, Imperial College London","School of Electronics and Computer Science, University of Southampton, Southampton, U.K","Department Electrical and Electronic Engineering, Imperial College London; School of Electronics and Computer Science, University of Southampton, Southampton, U.K"],"raw_orcid":"https://orcid.org/0000-0003-0757-5504","affiliations":[{"raw_affiliation_string":"Department Electrical and Electronic Engineering, Imperial College London","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"School of Electronics and Computer Science, University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]},{"raw_affiliation_string":"Department Electrical and Electronic Engineering, Imperial College London; School of Electronics and Computer Science, University of Southampton, Southampton, U.K","institution_ids":["https://openalex.org/I43439940"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072438406","display_name":"Alastair H. Moore","orcid":"https://orcid.org/0000-0001-8911-1601"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Alastair H. Moore","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, London, U.K","Department of Electrical and Electronic Engineering, Imperial college London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8911-1601","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial college London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016227729","display_name":"Patrick A. Naylor","orcid":"https://orcid.org/0000-0001-8546-8013"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Patrick A. Naylor","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, London, U.K","Department of Electrical and Electronic Engineering, Imperial college London, London, U.K"],"raw_orcid":"https://orcid.org/0000-0001-8546-8013","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, London, U.K","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial college London, London, U.K","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5031002666"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.9253,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.73187048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"1479","last_page":"1490"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/computer-science","display_name":"Computer science","score":0.7672480344772339},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7244619131088257},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6978060007095337},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.674284040927887},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5886006951332092},{"id":"https://openalex.org/keywords/harmonics","display_name":"Harmonics","score":0.512906551361084},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5048299431800842},{"id":"https://openalex.org/keywords/fundamental-frequency","display_name":"Fundamental frequency","score":0.4469788670539856},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4447230398654938},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31075525283813477},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.11124297976493835}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7672480344772339},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7244619131088257},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6978060007095337},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.674284040927887},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5886006951332092},{"id":"https://openalex.org/C188414643","wikidata":"https://www.wikidata.org/wiki/Q3001183","display_name":"Harmonics","level":3,"score":0.512906551361084},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5048299431800842},{"id":"https://openalex.org/C10513763","wikidata":"https://www.wikidata.org/wiki/Q1331774","display_name":"Fundamental frequency","level":2,"score":0.4469788670539856},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4447230398654938},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31075525283813477},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.11124297976493835},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/taslp.2021.3067161","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2021.3067161","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmh:oai:eprints.soton.ac.uk:448040","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306401019","display_name":"ePrints Soton (University of Southampton)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I43439940","host_organization_name":"University of Southampton","host_organization_lineage":["https://openalex.org/I43439940"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97436","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97436","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97436/2/Hogg%20Overlapping%20Speaker%20Segmentation%202021%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/88508","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/88508","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"1490","raw_type":"Journal Article"}],"best_oa_location":{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/97436","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/97436","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/97436/2/Hogg%20Overlapping%20Speaker%20Segmentation%202021%20Accepted.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G3788727841","display_name":"Acoustic Signal Processing and Scene Analysis for Socially Assistive Robots","funder_award_id":"EP/P001017/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G5201431165","display_name":"EPSRC Centre for Doctoral Training in High Performance Embedded and Distributed Systems","funder_award_id":"EP/L016796/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G7870544646","display_name":null,"funder_award_id":"EP/P001017/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3137585377.pdf","grobid_xml":"https://content.openalex.org/works/W3137585377.grobid-xml"},"referenced_works_count":65,"referenced_works":["https://openalex.org/W86348706","https://openalex.org/W165772547","https://openalex.org/W177037875","https://openalex.org/W1558276682","https://openalex.org/W1568122762","https://openalex.org/W1916910924","https://openalex.org/W1990449877","https://openalex.org/W2044525818","https://openalex.org/W2062470372","https://openalex.org/W2074394031","https://openalex.org/W2081074144","https://openalex.org/W2098189132","https://openalex.org/W2101702585","https://openalex.org/W2102308274","https://openalex.org/W2102601039","https://openalex.org/W2105934661","https://openalex.org/W2114511803","https://openalex.org/W2116007667","https://openalex.org/W2119599673","https://openalex.org/W2122201922","https://openalex.org/W2125336414","https://openalex.org/W2127923214","https://openalex.org/W2129070077","https://openalex.org/W2131010183","https://openalex.org/W2135933868","https://openalex.org/W2136105097","https://openalex.org/W2139417397","https://openalex.org/W2158992331","https://openalex.org/W2160475605","https://openalex.org/W2160566140","https://openalex.org/W2164512637","https://openalex.org/W2169264834","https://openalex.org/W2237765446","https://openalex.org/W2602334317","https://openalex.org/W2618760106","https://openalex.org/W2735405579","https://openalex.org/W2746241180","https://openalex.org/W2750259098","https://openalex.org/W2791203079","https://openalex.org/W2800665363","https://openalex.org/W2807015669","https://openalex.org/W2936794852","https://openalex.org/W2937501454","https://openalex.org/W2964052309","https://openalex.org/W2968071640","https://openalex.org/W2997785206","https://openalex.org/W3015783745","https://openalex.org/W3021261768","https://openalex.org/W3102937397","https://openalex.org/W3117312663","https://openalex.org/W3127686677","https://openalex.org/W3139916217","https://openalex.org/W3209073848","https://openalex.org/W4230251209","https://openalex.org/W4296927107","https://openalex.org/W6633191483","https://openalex.org/W6674548320","https://openalex.org/W6679097437","https://openalex.org/W6735862337","https://openalex.org/W6743299418","https://openalex.org/W6748326514","https://openalex.org/W6770434673","https://openalex.org/W6788216224","https://openalex.org/W6789826613","https://openalex.org/W6791876239"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162","https://openalex.org/W1521049138"],"abstract_inverted_index":{"This":[0,92],"paper":[1],"demonstrates":[2],"how":[3,25],"the":[4,29,74,85,101,121,125,143,156],"harmonic":[5],"structure":[6],"of":[7,76,80,87,133,147,162,166,172],"voiced":[8,42],"speech":[9],"can":[10,31,44,150],"be":[11,32,45,151],"exploited":[12],"to":[13,67,155,158],"segment":[14],"multiple":[15,69],"overlapping":[16,59],"speakers":[17],"in":[18,28,37,47,84,131,164,170],"a":[19,26,35,81,97,105],"speaker":[20,30,53,60,137],"diarization":[21],"task.":[22],"We":[23,39,139],"explore":[24],"change":[27,36],"inferred":[33],"from":[34,100],"pitch.":[38],"show":[40,141],"that":[41,103,120,142],"harmonics":[43,70],"useful":[46],"detecting":[48],"when":[49],"more":[50],"than":[51],"one":[52],"is":[54,65,94],"talking,":[55],"such":[56],"as":[57,153],"during":[58],"activity.":[61],"A":[62],"novel":[63],"system":[64,93,99,149],"proposed":[66,122],"track":[68],"simultaneously,":[71],"allowing":[72],"for":[73,136],"determination":[75],"onsets":[77],"and":[78,114,168],"end-points":[79],"speaker's":[82],"utterance":[83],"presence":[86],"an":[88],"additional":[89],"active":[90],"speaker.":[91],"bench-marked":[95],"against":[96],"segmentation":[98],"literature":[102],"employs":[104],"bidirectional":[106],"long":[107],"short":[108],"term":[109],"memory":[110],"network":[111],"(BLSTM)":[112],"approach":[113,123,128],"requires":[115],"training.":[116],"Experimental":[117],"results":[118],"highlight":[119],"outperforms":[124],"BLSTM":[126,157],"baseline":[127],"by":[129],"12.9%":[130],"terms":[132,165,171],"HIT":[134],"rate":[135],"segmentation.":[138],"also":[140],"estimated":[144],"pitch":[145],"tracks":[146],"our":[148],"used":[152],"features":[154],"achieve":[159],"further":[160],"improvements":[161],"1.21%":[163],"coverage":[167],"2.45%":[169],"purity.":[173]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}