{"id":"https://openalex.org/W3139916217","doi":"https://doi.org/10.1109/icassp39728.2021.9414130","title":"Multichannel Overlapping Speaker Segmentation Using Multiple Hypothesis Tracking Of Acoustic And Spatial Features","display_name":"Multichannel Overlapping Speaker Segmentation Using Multiple Hypothesis Tracking Of Acoustic And Spatial Features","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3139916217","doi":"https://doi.org/10.1109/icassp39728.2021.9414130","mag":"3139916217"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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/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":["Imperial College London,Department of Electrical and Electronic Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","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"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christine Evers","raw_affiliation_strings":["University of Southampton,Electronics and Computer Science,UK","Electronics and Computer Science, University of Southampton, UK"],"affiliations":[{"raw_affiliation_string":"University of Southampton,Electronics and Computer Science,UK","institution_ids":["https://openalex.org/I43439940"]},{"raw_affiliation_string":"Electronics and Computer Science, University of Southampton, UK","institution_ids":["https://openalex.org/I43439940"]}]},{"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":["Imperial College London,Department of Electrical and Electronic Engineering,UK"],"affiliations":[{"raw_affiliation_string":"Imperial College London,Department of Electrical and Electronic Engineering,UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031002666"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.1524,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40196078,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.9950000047683716,"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":0.7258551120758057},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.655799388885498},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6243007183074951},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.5148886442184448},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47588932514190674},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.462518572807312},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46077603101730347},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43349355459213257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7258551120758057},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.655799388885498},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243007183074951},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.5148886442184448},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47588932514190674},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.462518572807312},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46077603101730347},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43349355459213257},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.soton.ac.uk:448018","is_oa":false,"landing_page_url":"https://eprints.soton.ac.uk/448018/","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/87556","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/87556","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":"IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307901","display_name":"EDS","ror":"https://ror.org/059rn9488"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W165772547","https://openalex.org/W177037875","https://openalex.org/W1558276682","https://openalex.org/W2044525818","https://openalex.org/W2074394031","https://openalex.org/W2081074144","https://openalex.org/W2098189132","https://openalex.org/W2105934661","https://openalex.org/W2111057910","https://openalex.org/W2113638573","https://openalex.org/W2125336414","https://openalex.org/W2141398670","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/W2746241180","https://openalex.org/W2763188033","https://openalex.org/W2807015669","https://openalex.org/W2936794852","https://openalex.org/W2937501454","https://openalex.org/W2964052309","https://openalex.org/W2987372735","https://openalex.org/W2997785206","https://openalex.org/W3015783745","https://openalex.org/W3021261768","https://openalex.org/W3102937397","https://openalex.org/W3117312663","https://openalex.org/W3137585377","https://openalex.org/W4230251209","https://openalex.org/W4296927107","https://openalex.org/W6633191483","https://openalex.org/W6674548320","https://openalex.org/W6735862337","https://openalex.org/W6788216224","https://openalex.org/W6791642714"],"related_works":["https://openalex.org/W2084086966","https://openalex.org/W2023861399","https://openalex.org/W2730915376","https://openalex.org/W4379231730","https://openalex.org/W2626306547","https://openalex.org/W4389858081","https://openalex.org/W2021396365","https://openalex.org/W2394134009","https://openalex.org/W2119515433","https://openalex.org/W1522196789"],"abstract_inverted_index":{"An":[0,105],"essential":[1],"part":[2],"of":[3,10,31,40,50,70,77,108,114,139],"any":[4],"diarization":[5],"system":[6],"is":[7,14],"the":[8,48,62,71,74,112,128,136],"task":[9],"speaker":[11,20,57,72],"segmentation":[12,58,96],"which":[13,87],"important":[15],"for":[16,55],"many":[17],"applications":[18],"including":[19],"indexing":[21],"and":[22,73,131],"automatic":[23],"speech":[24,33,110],"recognition":[25],"(ASR)":[26],"in":[27,95,135],"multi-speaker":[28],"environments.":[29],"Segmentation":[30],"overlapping":[32,56,109],"has":[34],"recently":[35],"been":[36],"a":[37,51,121,144],"key":[38],"focus":[39],"this":[41,44],"work.":[42],"In":[43],"paper":[45],"we":[46],"explore":[47],"use":[49],"new":[52],"multimodal":[53],"approach":[54],"that":[59],"tracks":[60,89],"both":[61,90],"fundamental":[63],"frequency":[64],"(F":[65],"<inf":[66],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[67],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</inf>":[68],")":[69],"speaker\u2019s":[75],"direction":[76],"arrival":[78],"(DOA)":[79],"simultaneously.":[80],"Our":[81],"proposed":[82,116],"multiple":[83],"hypothesis":[84],"tracking":[85,101],"system,":[86],"simultaneously":[88],"features,":[91],"shows":[92],"an":[93,133],"improvement":[94,134],"performance":[97],"when":[98],"compared":[99],"to":[100],"these":[102],"features":[103],"separately.":[104],"illustrative":[106],"example":[107],"demonstrates":[111],"effectiveness":[113],"our":[115],"system.":[117],"We":[118],"also":[119],"undertake":[120],"statistical":[122],"analysis":[123],"on":[124,141],"12":[125],"meetings":[126],"from":[127],"AMI":[129],"corpus":[130],"show":[132],"HIT":[137],"rate":[138],"14.1%":[140],"average":[142],"against":[143],"commonly":[145],"used":[146],"deep":[147],"learning":[148],"bidirectional":[149],"long":[150],"short":[151],"term":[152],"memory":[153],"network":[154],"(BLSTM)":[155],"approach.":[156]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}