{"id":"https://openalex.org/W2891527745","doi":"https://doi.org/10.1109/icassp.2018.8461654","title":"Multichannel Speaker Activity Detection for Meetings","display_name":"Multichannel Speaker Activity Detection for Meetings","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2891527745","doi":"https://doi.org/10.1109/icassp.2018.8461654","mag":"2891527745"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5019858282","display_name":"Patrick Meyer","orcid":"https://orcid.org/0000-0001-6479-213X"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Patrick Meyer","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit&#x00E4;t Braunschweig, Braunschweig, 38106, Germany","Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit&#x00E4;t Braunschweig, Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]},{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040698655","display_name":"Rolf Jongebloed","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rolf Jongebloed","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit&#x00E4;t Braunschweig, Braunschweig, 38106, Germany","Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit&#x00E4;t Braunschweig, Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]},{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002593702","display_name":"Tim Fingscheidt","orcid":"https://orcid.org/0000-0002-8895-5041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Fingscheidt","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit&#x00E4;t Braunschweig, Braunschweig, 38106, Germany","Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit&#x00E4;t Braunschweig, Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]},{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, Braunschweig, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019858282"],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":0.8257,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.73645826,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5539","last_page":"5543"},"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9986000061035156,"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/headset","display_name":"Headset","score":0.8814890384674072},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.8323812484741211},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7748032808303833},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.712379515171051},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.5936545729637146},{"id":"https://openalex.org/keywords/crosstalk","display_name":"Crosstalk","score":0.573305606842041},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.48818403482437134},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.4492560029029846},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43340855836868286},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32029247283935547},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1592790186405182},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12708687782287598},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.09105738997459412}],"concepts":[{"id":"https://openalex.org/C2780657452","wikidata":"https://www.wikidata.org/wiki/Q1193170","display_name":"Headset","level":2,"score":0.8814890384674072},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.8323812484741211},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7748032808303833},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.712379515171051},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.5936545729637146},{"id":"https://openalex.org/C169822122","wikidata":"https://www.wikidata.org/wiki/Q230187","display_name":"Crosstalk","level":2,"score":0.573305606842041},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.48818403482437134},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.4492560029029846},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43340855836868286},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32029247283935547},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1592790186405182},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12708687782287598},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.09105738997459412},{"id":"https://openalex.org/C68115822","wikidata":"https://www.wikidata.org/wiki/Q1068172","display_name":"Sound pressure","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461654","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461654","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W76901566","https://openalex.org/W197511395","https://openalex.org/W202024829","https://openalex.org/W1558276682","https://openalex.org/W1591607137","https://openalex.org/W1946893126","https://openalex.org/W1973672195","https://openalex.org/W2054634052","https://openalex.org/W2054875385","https://openalex.org/W2098441927","https://openalex.org/W2104835909","https://openalex.org/W2115483887","https://openalex.org/W2120478181","https://openalex.org/W2121147010","https://openalex.org/W2146324387","https://openalex.org/W2155524176","https://openalex.org/W2163704482","https://openalex.org/W2171757151","https://openalex.org/W2396164315","https://openalex.org/W2402768323","https://openalex.org/W2755897894","https://openalex.org/W4211153864","https://openalex.org/W4243971525","https://openalex.org/W6603097216","https://openalex.org/W6607878040","https://openalex.org/W6608232238","https://openalex.org/W6633191483","https://openalex.org/W6675912722","https://openalex.org/W6678251047","https://openalex.org/W6685102802","https://openalex.org/W6712102944","https://openalex.org/W6712662408"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1493012537","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Multichannel":[0],"recordings":[1],"of":[2,24,33,57,107],"meetings":[3],"with":[4],"a":[5,42,74,86,104,117,128],"(wireless)":[6],"headset":[7],"for":[8,17],"each":[9],"person":[10],"deliver":[11],"commonly":[12],"the":[13,30,34,54,58,62,113],"best":[14],"audio":[15],"quality":[16],"subsequent":[18],"analyses.":[19],"However,":[20],"still":[21],"speech":[22,55],"portions":[23,56],"other":[25],"participants":[26],"can":[27,91],"couple":[28],"into":[29],"microphone":[31,64],"channel":[32],"associated":[35],"target":[36,59],"speaker.":[37],"Due":[38],"to":[39,51],"this":[40],"crosstalk,":[41],"speaker":[43,60],"activity":[44,120],"detection":[45,114,121],"(SAD)":[46],"is":[47],"required":[48],"in":[49,61,81,103],"order":[50],"identify":[52],"only":[53],"related":[63],"channel.":[65],"While":[66],"most":[67],"solutions":[68],"are":[69],"either":[70],"complex":[71],"and":[72,95,101,111],"need":[73],"training":[75],"process,":[76],"or":[77],"achieve":[78],"insufficient":[79],"results":[80],"multi-talk":[82,96,102],"situations,":[83],"we":[84],"propose":[85],"low":[87],"complexity":[88],"method,":[89],"which":[90],"handle":[92],"both":[93],"crosstalk":[94,109],"situations.":[97],"We":[98],"investigate":[99],"single-":[100],"wide":[105],"range":[106],"different":[108],"levels,":[110],"improved":[112],"accuracy":[115],"towards":[116],"standardized":[118],"voice":[119],"overall":[122],"by":[123,135],"12.89":[124],"%":[125,137],"absolute,":[126],"whereas":[127],"state-of-the-art":[129],"multichannel":[130],"SAD":[131],"was":[132],"exceeded":[133],"even":[134],"13.76":[136],"absolute.":[138]},"counts_by_year":[{"year":2020,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
