{"id":"https://openalex.org/W2491350972","doi":"https://doi.org/10.1109/lsp.2016.2592683","title":"Microphone Array Processing Strategies for Distant-Based Automatic Speech Recognition","display_name":"Microphone Array Processing Strategies for Distant-Based Automatic Speech Recognition","publication_year":2016,"publication_date":"2016-07-18","ids":{"openalex":"https://openalex.org/W2491350972","doi":"https://doi.org/10.1109/lsp.2016.2592683","mag":"2491350972"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2016.2592683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2016.2592683","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-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/A5064497078","display_name":"Soudeh A. Khoubrouy","orcid":null},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soudeh A. Khoubrouy","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057910370","display_name":"John H. L. Hansen","orcid":"https://orcid.org/0000-0003-1382-9929"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John H. L. Hansen","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5064497078"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.7652,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.71616464,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"23","issue":"10","first_page":"1344","last_page":"1348"},"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":0.9990000128746033,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.996999979019165,"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":0.7988865375518799},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7823870182037354},{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.5979146957397461},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5690857172012329},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.5435152053833008},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.5136970281600952},{"id":"https://openalex.org/keywords/microphone-array","display_name":"Microphone array","score":0.5083436369895935},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.41277840733528137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3296658396720886},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18542906641960144},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08043518662452698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7988865375518799},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7823870182037354},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.5979146957397461},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5690857172012329},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.5435152053833008},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5136970281600952},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5083436369895935},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.41277840733528137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3296658396720886},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18542906641960144},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08043518662452698},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"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/lsp.2016.2592683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2016.2592683","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.5199999809265137,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320313176","display_name":"Robert Bosch","ror":"https://ror.org/02venad53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W63488022","https://openalex.org/W173561343","https://openalex.org/W1509052650","https://openalex.org/W1524333225","https://openalex.org/W1904457459","https://openalex.org/W1968493974","https://openalex.org/W1982728343","https://openalex.org/W1987896763","https://openalex.org/W2100103540","https://openalex.org/W2106015547","https://openalex.org/W2117071049","https://openalex.org/W2134533334","https://openalex.org/W2141733498","https://openalex.org/W2150800162","https://openalex.org/W2164007105","https://openalex.org/W2293403369","https://openalex.org/W2616139854","https://openalex.org/W6602594397","https://openalex.org/W6607114211","https://openalex.org/W6630514176","https://openalex.org/W6631362777"],"related_works":["https://openalex.org/W2896203542","https://openalex.org/W876328409","https://openalex.org/W4319068615","https://openalex.org/W4214946933","https://openalex.org/W1879255185","https://openalex.org/W2148473678","https://openalex.org/W2769861442","https://openalex.org/W3004719695","https://openalex.org/W2120442551","https://openalex.org/W1980506188"],"abstract_inverted_index":{"Robust":[0],"distant":[1],"speech":[2,9,56,66],"recognition":[3,57,67],"(DSR)":[4],"is":[5,36,89],"necessary":[6],"in":[7,21,177,190],"many":[8],"technology":[10],"applications":[11,40],"using":[12,51,64,121],"multiple":[13,103],"microphones":[14],"but":[15],"has":[16],"received":[17],"only":[18],"limited":[19],"treatment":[20],"the":[22,39,97,109,122,146,164,169,178,182],"literature.":[23],"In":[24,83,106],"this":[25,107],"paper,":[26,108],"we":[27],"work":[28],"on":[29,99,159],"communicating":[30],"with":[31,166,186],"vehicle":[32],"voice-controlled":[33],"system":[34],"which":[35],"one":[37],"of":[38,41,130,148,172],"DSR.":[42,191],"Two":[43],"approaches":[44],"for":[45,118,139],"DSR":[46],"are":[47],"i)":[48],"signal-level":[49],"combination":[50,63,73,94],"beamforming":[52],"followed":[53,69,75],"by":[54,70,76,95,175],"automatic":[55],"(ACR),":[58],"and":[59,162,180],"ii)":[60],"word":[61],"hypothesis-level":[62],"several":[65],"engines":[68],"confusion":[71],"network":[72],"or":[74],"recognizer":[77,98],"output":[78],"voting":[79],"error":[80],"reduction":[81],"(ROVER).":[82],"addition":[84],"to":[85,91,134],"these":[86,113,131],"approaches,":[87],"it":[88],"possible":[90],"examine":[92],"training-level":[93],"training":[96],"audio":[100],"signals":[101],"from":[102],"channels":[104,161],"(microphones).":[105],"authors":[110,126,143],"investigate":[111,145],"how":[112],"methods":[114,133],"can":[115],"be":[116],"leveraged":[117],"in-vehicle":[119,140],"ACR":[120],"CU-Move":[123],"corpus.":[124],"The":[125,142,152],"propose":[127],"various":[128],"combinations":[129],"three":[132],"find":[135],"an":[136],"optimum":[137],"structure":[138],"ACR.":[141],"also":[144],"effect":[147],"speaker":[149],"adaptation":[150],"(SA).":[151],"author's":[153],"experience":[154],"shows":[155],"that":[156],"applying":[157],"SA":[158,173],"individual":[160],"merging":[163],"results":[165],"ROVER":[167],"reduces":[168],"negative":[170],"effects":[171],"reported":[174],"others":[176],"field,":[179],"illustrates":[181],"overall":[183],"improvement":[184],"obtained":[185],"front-end":[187],"enhancement":[188],"techniques":[189]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-03-23T07:41:27.035349","created_date":"2025-10-10T00:00:00"}