{"id":"https://openalex.org/W78370326","doi":"https://doi.org/10.21437/interspeech.2007-583","title":"Detection, diarization, and transcription of far-field lecture speech","display_name":"Detection, diarization, and transcription of far-field lecture speech","publication_year":2007,"publication_date":"2007-08-27","ids":{"openalex":"https://openalex.org/W78370326","doi":"https://doi.org/10.21437/interspeech.2007-583","mag":"78370326"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2007-583","doi":"https://doi.org/10.21437/interspeech.2007-583","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-583","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101522204","display_name":"Jing Huang","orcid":"https://orcid.org/0009-0005-5651-9033","observed_orcids":["https://orcid.org/0009-0005-5651-9033"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jing Huang","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010196081","display_name":"Etienne Marcheret","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Etienne Marcheret","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045869355","display_name":"Karthik Visweswariah","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karthik Visweswariah","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047716643","display_name":"Vit Libal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vit Libal","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024184433","display_name":"Gerasimos Potamianos","orcid":"https://orcid.org/0000-0002-9833-7124","observed_orcids":["https://orcid.org/0000-0002-9833-7124"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gerasimos Potamianos","raw_affiliation_strings":["IBM, ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM, ,","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1341412227"],"apc_list":null,"apc_paid":null,"fwci":0.2368,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35820015,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2161","last_page":"2164"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9848999977111816,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9848999977111816,"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/T10860","display_name":"Speech and Audio Processing","score":0.014299999922513962,"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/T12031","display_name":"Speech and dialogue systems","score":0.00019999999494757503,"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/lecture-speech","display_name":"lecture speech","score":0.7070000171661377},{"id":"https://openalex.org/keywords/far-field-speech","display_name":"far-field speech","score":0.8899999856948853},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"voice activity detection","score":0.9570000171661377},{"id":"https://openalex.org/keywords/speaker-diarization","display_name":"speaker diarization","score":0.9990000128746033},{"id":"https://openalex.org/keywords/speech-to-text","display_name":"speech-to-text","score":0.9380000233650208},{"id":"https://openalex.org/keywords/smart-rooms","display_name":"smart rooms","score":0.6880000233650208},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"word error rate","score":0.6539999842643738}],"concepts":[{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.8051661252975464},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.7595056295394897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7547457218170166},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7454461455345154},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.672334611415863},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6267443895339966},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5860872864723206},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.4826115369796753},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46676111221313477},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4581988453865051},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45572108030319214},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4407833218574524},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.41543352603912354},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4145178198814392},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4132692515850067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3959169387817383},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37185898423194885},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13719409704208374},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0817980170249939},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2007-583","doi":"https://doi.org/10.21437/interspeech.2007-583","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2007-583","pdf_url":null,"source":{"id":"https://openalex.org/S4393918409","display_name":"Interspeech (USB)","issn_l":"2308-457X","issn":["2308-457X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-1","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2007","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1797288984","https://openalex.org/W1904457459","https://openalex.org/W1936118753","https://openalex.org/W2118097082","https://openalex.org/W2125610823","https://openalex.org/W2160237783","https://openalex.org/W2915347754","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2177420620","https://openalex.org/W2178600993","https://openalex.org/W2177650602","https://openalex.org/W3129653033","https://openalex.org/W2118097082","https://openalex.org/W24570992","https://openalex.org/W7098789073","https://openalex.org/W2060656758","https://openalex.org/W2177686784","https://openalex.org/W2569324142"],"abstract_inverted_index":{"Speech":[0],"processing":[1],"of":[2,77,83,97,139,159],"lectures":[3],"recorded":[4],"inside":[5],"smart":[6,175],"rooms":[7],"has":[8,17],"recently":[9],"attracted":[10],"much":[11],"interest.":[12],"In":[13,52],"particular,":[14],"the":[15,21,57,68,74,90,98,160],"topic":[16],"been":[18],"central":[19],"to":[20,61,136],"Rich":[22],"Transcription":[23],"(RT)":[24],"Meeting":[25],"Recognition":[26],"Evaluation":[27],"campaign":[28],"series,":[29],"sponsored":[30],"by":[31],"NIST,":[32],"with":[33],"emphasis":[34],"placed":[35],"on":[36,73,94,149],"benchmarking":[37],"speech":[38,165,167,171],"activity":[39,172],"detection":[40],"(SAD),":[41],"speaker":[42,169],"diarization":[43],"(SPKR),":[44],"speech-to-text":[45],"(STT),":[46],"and":[47,115],"speakerattributed":[48],"STT":[49,116],"(SASTT)":[50],"technologies.":[51],"this":[53],"paper,":[54],"we":[55],"present":[56],"IBM":[58],"systems":[59,91],"developed":[60],"address":[62],"these":[63],"tasks":[64,117],"in":[65,127,133,155,157],"preparation":[66],"for":[67,111,121],"RT":[69,99],"2007":[70,156],"evaluation,":[71],"focusing":[72],"far-field":[75],"condition":[76],"lecture":[78],"data":[79],"collected":[80],"as":[81],"part":[82],"European":[84],"project":[85],"CHIL.":[86],"For":[87],"their":[88],"development,":[89],"are":[92,146],"benchmarked":[93],"a":[95,123,137,151],"subset":[96],"Spring":[100],"2006":[101],"(RT06s)":[102],"evaluation":[103],"test":[104],"set,":[105],"where":[106],"they":[107],"yield":[108],"significant":[109],"improvements":[110],"all":[112],"SAD,":[113],"SPKR,":[114],"over":[118],"RT06s":[119],"results;":[120],"example,":[122],"16%":[124],"relative":[125],"reduction":[126],"word":[128],"error":[129],"rate":[130],"is":[131],"reported":[132],"STT,":[134],"attributed":[135],"number":[138],"system":[140],"advances":[141],"discussed":[142],"here.":[143],"Initial":[144],"results":[145],"also":[147],"presented":[148],"SASTT,":[150],"task":[152],"newly":[153],"introduced":[154],"place":[158],"discontinued":[161],"SAD.":[162],"Index":[163],"Terms:":[164],"processing,":[166],"recognition,":[168],"diarization,":[170],"detection,":[173],"lectures,":[174],"rooms.":[176]},"counts_by_year":[],"updated_date":"2026-10-06T10:28:23.643775","created_date":"2016-06-24T00:00:00"}