{"id":"https://openalex.org/W2146845882","doi":"https://doi.org/10.1109/aiccsa.2008.4493578","title":"Far-field continuous speech recognition system based on speaker Localization and sub-band Beamforming","display_name":"Far-field continuous speech recognition system based on speaker Localization and sub-band Beamforming","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2146845882","doi":"https://doi.org/10.1109/aiccsa.2008.4493578","mag":"2146845882"},"language":"en","primary_location":{"id":"doi:10.1109/aiccsa.2008.4493578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2008.4493578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE/ACS International Conference on Computer Systems and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/181696","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5063249055","display_name":"Afsaneh Asaei","orcid":"https://orcid.org/0000-0002-1917-601X"},"institutions":[{"id":"https://openalex.org/I4210102178","display_name":"ICT Research Institute","ror":"https://ror.org/01a3g2z22","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210102178"]}],"countries":["IR"],"is_corresponding":true,"raw_author_name":"Afsaneh Asaei","raw_affiliation_strings":["Multimedia Research Group, Iran Telecommunication Research Center, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Multimedia Research Group, Iran Telecommunication Research Center, Tehran, Iran","institution_ids":["https://openalex.org/I4210102178"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101412090","display_name":"Mohammad J. Taghizadeh","orcid":"https://orcid.org/0000-0002-3383-2255"},"institutions":[{"id":"https://openalex.org/I4210102178","display_name":"ICT Research Institute","ror":"https://ror.org/01a3g2z22","country_code":"IR","type":"facility","lineage":["https://openalex.org/I4210102178"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Mohammad Javad Taghizadeh","raw_affiliation_strings":["Multimedia Research Group, Iran Telecommunication Research Center, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Multimedia Research Group, Iran Telecommunication Research Center, Tehran, Iran","institution_ids":["https://openalex.org/I4210102178"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024773257","display_name":"Hossein Sameti","orcid":"https://orcid.org/0000-0002-8087-8889"},"institutions":[{"id":"https://openalex.org/I133529467","display_name":"Sharif University of Technology","ror":"https://ror.org/024c2fq17","country_code":"IR","type":"education","lineage":["https://openalex.org/I133529467"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Hossein Sameti","raw_affiliation_strings":["Computer Engineering Faculty, Sharif University of Technology, Tehran, Iran"],"affiliations":[{"raw_affiliation_string":"Computer Engineering Faculty, Sharif University of Technology, Tehran, Iran","institution_ids":["https://openalex.org/I133529467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5063249055"],"corresponding_institution_ids":["https://openalex.org/I4210102178"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.18045603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"495","last_page":"500"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9991999864578247,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991000294685364,"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/speech-recognition","display_name":"Speech recognition","score":0.8292208909988403},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.7872343063354492},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7632228136062622},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.6333887577056885},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.611768901348114},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5952687859535217},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5600221157073975},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.45543229579925537},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.44671157002449036},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42786705493927},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40803787112236023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3655575215816498},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18961384892463684},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1641584038734436},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.0883525013923645}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.8292208909988403},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7872343063354492},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7632228136062622},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.6333887577056885},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.611768901348114},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5952687859535217},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5600221157073975},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.45543229579925537},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.44671157002449036},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42786705493927},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40803787112236023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3655575215816498},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18961384892463684},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1641584038734436},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0883525013923645},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/aiccsa.2008.4493578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aiccsa.2008.4493578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE/ACS International Conference on Computer Systems and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.422.6807","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.422.6807","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.idiap.ch/%7Eaasaei/papers/paper_select/ASR_Beamforming.pdf","raw_type":"text"},{"id":"pmh:oai:infoscience.tind.io:181696","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/181696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"}],"best_oa_location":{"id":"pmh:oai:infoscience.tind.io:181696","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/181696","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference proceedings"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.5,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1510878418","https://openalex.org/W1560904098","https://openalex.org/W1800365115","https://openalex.org/W2117678320","https://openalex.org/W2128653836","https://openalex.org/W2158541934","https://openalex.org/W2170771399","https://openalex.org/W4238850318","https://openalex.org/W6630572136"],"related_works":["https://openalex.org/W2120771489","https://openalex.org/W2294333436","https://openalex.org/W2653598178","https://openalex.org/W2373767407","https://openalex.org/W3110551121","https://openalex.org/W2131486661","https://openalex.org/W2089240210","https://openalex.org/W642007152","https://openalex.org/W2072884270","https://openalex.org/W4200596008"],"abstract_inverted_index":{"This":[0,38],"paper":[1],"proposes":[2],"a":[3,10,60,125],"distant":[4],"speech":[5,34,61,73,132,145],"recognition":[6,62,74,99,136],"system":[7,63,129],"based":[8,24],"on":[9,25,89],"novel":[11],"speaker":[12,21,45,127],"localization":[13,97],"and":[14,83,87,107,134],"beamforming":[15],"(SRLB)":[16],"algorithm.":[17],"To":[18],"localize":[19],"the":[20,42,57,68,71,112,142],"an":[22],"algorithm":[23,122],"steered":[26],"response":[27],"power":[28],"by":[29,47,94,102],"utilizing":[30,95],"harmonic":[31],"structures":[32],"of":[33,44,59,70,81,114,120,144],"signal":[35],"is":[36,76],"proposed.":[37],"new":[39],"scheme":[40],"has":[41],"ability":[43],"verification":[46],"fundamental":[48],"frequency":[49],"variation;":[50],"therefore":[51],"it":[52],"can":[53],"be":[54],"utilized":[55],"in":[56,104,123,141],"design":[58],"for":[64],"verified":[65,126],"speakers.":[66],"Then":[67],"performance":[69],"Farsi":[72],"engine":[75],"evaluated":[77],"under":[78],"notorious":[79],"conditions":[80,109],"noise":[82,106],"reverberation.":[84],"Simulation":[85],"results":[86],"tests":[88],"real":[90],"data":[91],"shows":[92],"that":[93],"proposed":[96],"scheme,":[98],"accuracy":[100,113],"improves":[101,128],"28%":[103],"high":[105],"reverberant":[108],"compared":[110],"to":[111,131,139],"single":[115],"channel":[116],"recognition.":[117],"The":[118],"capability":[119],"this":[121],"localizing":[124],"robustness":[130],"noises":[133],"reduces":[135],"errors":[137],"up":[138],"%52":[140],"presence":[143],"noise.":[146]},"counts_by_year":[{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
