{"id":"https://openalex.org/W1598201010","doi":"https://doi.org/10.1109/icassp.2015.7179072","title":"Speaker change detection and speaker diarization using spatial information","display_name":"Speaker change detection and speaker diarization using spatial information","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1598201010","doi":"https://doi.org/10.1109/icassp.2015.7179072","mag":"1598201010"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7179072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7179072","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042482531","display_name":"Mathieu Hu","orcid":null},"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":"Mathieu Hu","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, UK","Department of Electrical and Electronic Engineering, Imperial College, London, Uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College, London, Uk","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I1292318990","display_name":"Nuance Communications (Austria)","ror":"https://ror.org/04ggpbw68","country_code":"AT","type":"company","lineage":["https://openalex.org/I1292318990","https://openalex.org/I4210125787"]},{"id":"https://openalex.org/I4210142256","display_name":"Nuance Communications (United Kingdom)","ror":"https://ror.org/03ae66d75","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210125787","https://openalex.org/I4210142256"]}],"countries":["AT","GB"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Voicemail-to-Text Research, Nuance Communications Inc., Marlow, UK","Voicemail-To-Text Research, Nuance Communications Inc. Marlow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Voicemail-to-Text Research, Nuance Communications Inc., Marlow, UK","institution_ids":["https://openalex.org/I4210142256"]},{"raw_affiliation_string":"Voicemail-To-Text Research, Nuance Communications Inc. Marlow, UK","institution_ids":["https://openalex.org/I1292318990"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062526199","display_name":"Simon Doclo","orcid":"https://orcid.org/0000-0002-3392-2381"},"institutions":[{"id":"https://openalex.org/I129877168","display_name":"Carl von Ossietzky Universit\u00e4t Oldenburg","ror":"https://ror.org/033n9gh91","country_code":"DE","type":"education","lineage":["https://openalex.org/I129877168"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Simon Doclo","raw_affiliation_strings":["Department of Medical Physics and Acoustics, University of Oldenburg, Oldenburg, Germany","[Department of Medical Physics and Acoustics, University of Oldenburg, Germany]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical Physics and Acoustics, University of Oldenburg, Oldenburg, Germany","institution_ids":["https://openalex.org/I129877168"]},{"raw_affiliation_string":"[Department of Medical Physics and Acoustics, University of Oldenburg, Germany]","institution_ids":["https://openalex.org/I129877168"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004899548","display_name":"Mike Brookes","orcid":"https://orcid.org/0000-0001-7105-4936"},"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":"Mike Brookes","raw_affiliation_strings":["Department of Electrical and Electronic Engineering, Imperial College London, UK","Department of Electrical and Electronic Engineering, Imperial College, London, Uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College, London, Uk","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, UK","Department of Electrical and Electronic Engineering, Imperial College, London, Uk"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, Imperial College, London, Uk","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7398,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.84622462,"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":"5743","last_page":"5747"},"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9988999962806702,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.9041340351104736},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7501386404037476},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7067846655845642},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6020853519439697},{"id":"https://openalex.org/keywords/speaker-identification","display_name":"Speaker identification","score":0.5405977368354797},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5190901756286621},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4971514046192169},{"id":"https://openalex.org/keywords/change-detection","display_name":"Change detection","score":0.4908061921596527},{"id":"https://openalex.org/keywords/impulse-response","display_name":"Impulse response","score":0.4743534326553345},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.44993236660957336},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44890114665031433},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.41238802671432495},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3888911008834839},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1230650544166565}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.9041340351104736},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7501386404037476},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7067846655845642},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6020853519439697},{"id":"https://openalex.org/C2986627078","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker identification","level":3,"score":0.5405977368354797},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5190901756286621},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4971514046192169},{"id":"https://openalex.org/C203595873","wikidata":"https://www.wikidata.org/wiki/Q25389927","display_name":"Change detection","level":2,"score":0.4908061921596527},{"id":"https://openalex.org/C72279823","wikidata":"https://www.wikidata.org/wiki/Q1139726","display_name":"Impulse response","level":2,"score":0.4743534326553345},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.44993236660957336},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44890114665031433},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.41238802671432495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3888911008834839},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1230650544166565},{"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/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7179072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7179072","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1972705698","https://openalex.org/W1997836753","https://openalex.org/W2046791564","https://openalex.org/W2061074721","https://openalex.org/W2096259168","https://openalex.org/W2096465424","https://openalex.org/W2110097273","https://openalex.org/W2117678320","https://openalex.org/W2122807474","https://openalex.org/W2125838338","https://openalex.org/W2140983050","https://openalex.org/W2149197198","https://openalex.org/W2160557558","https://openalex.org/W2172156772","https://openalex.org/W2539508298","https://openalex.org/W3127686677","https://openalex.org/W4296927107","https://openalex.org/W6674325791","https://openalex.org/W6674535885","https://openalex.org/W6728799604","https://openalex.org/W6789826613"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W4318225096","https://openalex.org/W36105149","https://openalex.org/W2545131480","https://openalex.org/W4401661962","https://openalex.org/W4247736853","https://openalex.org/W1521049138","https://openalex.org/W2997340161","https://openalex.org/W1964028329","https://openalex.org/W2136038945"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"present":[4],"a":[5,65,73,84,95],"novel":[6],"speaker":[7,11,79],"change":[8,80],"detection":[9,81],"and":[10,50,83],"diarization":[12,89],"algorithm":[13],"using":[14,58],"spatial":[15],"information":[16],"in":[17,52,77,87],"the":[18,41,45,53,78,88],"form":[19],"of":[20,40],"features":[21],"derived":[22,49],"from":[23,43],"estimated":[24],"Room":[25],"Impulse":[26],"Response":[27],"(RIR)s.":[28],"A":[29],"blind":[30],"system":[31],"identification":[32],"approach":[33,71],"is":[34,48],"used":[35,51],"to":[36],"obtain":[37],"an":[38],"estimate":[39],"RIRs,":[42],"which":[44],"C5":[46],"feature":[47],"labeling":[54],"algorithm.":[55,97],"Experimental":[56],"results":[57],"2":[59],"speakers":[60],"for":[61],"different":[62],"locations":[63],"within":[64],"fixed":[66],"room":[67],"show":[68],"that":[69],"our":[70],"achieves":[72],"higher":[74],"hit":[75],"rate":[76,91],"task":[82],"lower":[85],"variance":[86],"error":[90],"when":[92],"compared":[93],"with":[94],"baseline":[96]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
