{"id":"https://openalex.org/W2900024717","doi":"https://doi.org/10.1109/iwaenc.2018.8521339","title":"Robust Feature Extraction from AD-HOC Microphones for Meeting Diarization","display_name":"Robust Feature Extraction from AD-HOC Microphones for Meeting Diarization","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2900024717","doi":"https://doi.org/10.1109/iwaenc.2018.8521339","mag":"2900024717"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5108774400","display_name":"Dushyant Sharma","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dushyant Sharma","raw_affiliation_strings":["Nuance Communications Inc, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc, Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065094891","display_name":"Amr H. Nour-Eldin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amr Nour-Eldin","raw_affiliation_strings":["Nuance Communications Inc, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc, Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018475330","display_name":"Philip J. Harding","orcid":null},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Philip Harding","raw_affiliation_strings":["Nuance Communications Inc, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc, Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027383698","display_name":"Sam Karimian-Azari","orcid":"https://orcid.org/0000-0002-6225-2663"},"institutions":[{"id":"https://openalex.org/I4210125787","display_name":"Nuance Communications (United States)","ror":"https://ror.org/0311h6702","country_code":"US","type":"company","lineage":["https://openalex.org/I4210125787"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sam Karimian-Azari","raw_affiliation_strings":["Nuance Communications Inc, Burlington, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuance Communications Inc, Burlington, MA, USA","institution_ids":["https://openalex.org/I4210125787"]}]},{"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, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Imperial College London, UK","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3325,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.58130744,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"20","issue":null,"first_page":"296","last_page":"300"},"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":0.9994999766349792,"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":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.793126106262207},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.774787962436676},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.7321782112121582},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6234973073005676},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5069254040718079},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5037698149681091},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46518296003341675},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4385177195072174},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4294648766517639},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39890164136886597},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36693283915519714},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.25526607036590576},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12398630380630493}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.793126106262207},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.774787962436676},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.7321782112121582},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6234973073005676},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5069254040718079},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5037698149681091},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46518296003341675},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4385177195072174},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4294648766517639},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39890164136886597},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36693283915519714},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.25526607036590576},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12398630380630493},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/iwaenc.2018.8521339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W142991516","https://openalex.org/W1498436455","https://openalex.org/W1499712254","https://openalex.org/W1963976507","https://openalex.org/W2010114458","https://openalex.org/W2046317813","https://openalex.org/W2081074144","https://openalex.org/W2130178255","https://openalex.org/W2169165592","https://openalex.org/W2170951662","https://openalex.org/W2181212125","https://openalex.org/W2240726287","https://openalex.org/W2297490458","https://openalex.org/W2405970501","https://openalex.org/W2638067502","https://openalex.org/W2765334250","https://openalex.org/W2771813982","https://openalex.org/W2915280872","https://openalex.org/W4296927107","https://openalex.org/W6605762983","https://openalex.org/W6629815555","https://openalex.org/W6684648996","https://openalex.org/W6690311182","https://openalex.org/W6713679436"],"related_works":["https://openalex.org/W2216290105","https://openalex.org/W1556857061","https://openalex.org/W2177420620","https://openalex.org/W4296594783","https://openalex.org/W4387225169","https://openalex.org/W4380994539","https://openalex.org/W4308671730","https://openalex.org/W2499802997","https://openalex.org/W1893339448","https://openalex.org/W2915347927"],"abstract_inverted_index":{"Speaker":[0],"diarization":[1,106,113],"in":[2,33,40],"the":[3,29,71,92,100,105],"meeting":[4,95],"scenario":[5],"is":[6],"a":[7,23,41,59,68,111,116,120],"challenging":[8],"problem":[9],"due":[10],"to":[11,110],"spontaneous,":[12],"conversational":[13],"speech":[14],"and":[15,36,49,97],"distant":[16,30],"nature":[17],"of":[18,70],"signal":[19],"acquisition.":[20],"We":[21,88],"present":[22,89],"novel":[24],"method":[25,44,102,118],"that":[26,99],"operates":[27],"with":[28,37,52,76],"microphones":[31],"placed":[32],"unknown":[34],"locations":[35],"ad-hoc":[38],"configurations":[39],"room.":[42],"The":[43,63],"exploits":[45],"robust":[46,54],"spatial":[47,64],"features":[48,65,85],"combines":[50],"them":[51],"noise":[53],"spectral":[55,84],"features,":[56],"enhanced":[57,83],"using":[58],"modulation":[60],"domain":[61],"algorithm.":[62],"extracted":[66],"include":[67],"model":[69],"time-difference-of-arrival":[72],"(TDOA)":[73],"information":[74],"along":[75],"optimal":[77],"channel-pair":[78],"selection,":[79],"based":[80],"on":[81,91],"which":[82],"are":[86],"computed.":[87],"results":[90],"NIST":[93],"RT05":[94],"corpora":[96],"show":[98],"proposed":[101],"significantly":[103],"reduces":[104],"error":[107],"rate":[108],"compared":[109],"baseline":[112],"system,":[114],"outperforming":[115],"previous":[117],"by":[119],"relative":[121],"33.1":[122],"%":[123],"DER.":[124]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}