{"id":"https://openalex.org/W2100103540","doi":"https://doi.org/10.1109/acssc.2010.5757831","title":"Microphone array processing for distance speech capture: A probe study on whisper speech detection","display_name":"Microphone array processing for distance speech capture: A probe study on whisper speech detection","publication_year":2010,"publication_date":"2010-11-01","ids":{"openalex":"https://openalex.org/W2100103540","doi":"https://doi.org/10.1109/acssc.2010.5757831","mag":"2100103540"},"language":"en","primary_location":{"id":"doi:10.1109/acssc.2010.5757831","doi":"https://doi.org/10.1109/acssc.2010.5757831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2010.5757831","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-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":"2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5100458232","display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0003-1911-3446","observed_orcids":["https://orcid.org/0000-0003-1911-3446"]},"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":"Chi Zhang","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75080, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103652301","display_name":"Tao Yu","orcid":"https://orcid.org/0000-0003-2523-4404","observed_orcids":["https://orcid.org/0000-0003-2523-4404"]},"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":"Tao Yu","raw_affiliation_strings":["Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75080, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75080, 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","observed_orcids":["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 (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75080, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas, Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Center for Robust Speech Systems (CRSS), Erik Jonsson School of Engineering & Computer Science, University of Texas at Dallas, Richardson, 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.22851184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1707","last_page":"1710"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9824000000953674,"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":0.9824000000953674,"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":0.01679999940097332,"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/T12031","display_name":"Speech and dialogue systems","score":9.999999747378752e-05,"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/microphone-array-beamforming","display_name":"microphone array beamforming","score":0.9240000247955322},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"speech enhancement","score":0.7749999761581421}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741976261138916},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.7355722188949585},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.7330638766288757},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6747670769691467},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.6651471853256226},{"id":"https://openalex.org/C77052588","wikidata":"https://www.wikidata.org/wiki/Q644307","display_name":"Constant false alarm rate","level":2,"score":0.6066006422042847},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5937551259994507},{"id":"https://openalex.org/C2778806681","wikidata":"https://www.wikidata.org/wiki/Q907293","display_name":"Microphone array","level":4,"score":0.5891218185424805},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5053480267524719},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.41711753606796265},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.3430923819541931},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2905108630657196},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11523538827896118},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10783472657203674},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09451800584793091},{"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/acssc.2010.5757831","doi":"https://doi.org/10.1109/acssc.2010.5757831","is_oa":false,"landing_page_url":"https://doi.org/10.1109/acssc.2010.5757831","pdf_url":null,"source":{"id":"https://openalex.org/S4363608623","display_name":"Asilomar Conference on Signals, Systems and Computers (ACSSC)","issn_l":"1058-6393","issn":["1058-6393","2576-2303"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-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":"2010 Conference Record of the Forty Fourth Asilomar Conference on Signals, Systems and Computers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W37326695","https://openalex.org/W177407077","https://openalex.org/W653761051","https://openalex.org/W2022047569","https://openalex.org/W2074936909","https://openalex.org/W2104353650","https://openalex.org/W2145404233","https://openalex.org/W2398145559"],"related_works":["https://openalex.org/W2023697902","https://openalex.org/W2229487294","https://openalex.org/W1982728343","https://openalex.org/W109284678","https://openalex.org/W2157774199","https://openalex.org/W14578209","https://openalex.org/W2539797148","https://openalex.org/W2795025117","https://openalex.org/W2149577017","https://openalex.org/W2303872962"],"abstract_inverted_index":{"In":[0],"this":[1,43],"study,":[2],"we":[3],"develop":[4],"a":[5,16,102],"probe":[6],"system":[7],"for":[8,11,42,111,121],"whisper-island":[9,62,98,119],"detection":[10,63,75,84,99,104,120],"distance":[12,25,55,67,94,122],"speech":[13,26,35,56,68,123],"capture":[14],"using":[15],"microphone":[17,46,126],"array":[18,47,127],"technique.":[19],"The":[20,45,65,96],"developed":[21],"corpus":[22],"consists":[23],"of":[24,118],"in":[27],"neutral":[28],"vocal":[29,71],"effort":[30,72],"and":[31,106],"embedded":[32],"with":[33],"whisper":[34],"which":[36,77,114],"are":[37],"produced":[38],"at":[39],"different":[40],"distances":[41],"study.":[44],"beamforming":[48],"technique":[49],"is":[50,78],"used":[51],"to":[52,92],"enhance":[53],"the":[54,61,116],"before":[57],"being":[58],"processed":[59],"by":[60,80],"system.":[64],"enhanced":[66,112],"provides":[69],"better":[70],"change":[73],"point":[74],"results,":[76],"indicated":[79],"either":[81],"0.0%":[82],"miss":[83],"rate":[85,105,110],"or":[86],"lower":[87,107],"Multi-Error":[88],"Score":[89],"(MES)":[90],"compared":[91],"unprocessed":[93],"speech.":[95],"final":[97],"results":[100],"produce":[101],"higher":[103],"false":[108],"alarm":[109],"speech,":[113],"illustrates":[115],"improvement":[117],"attained":[124],"from":[125],"processing.":[128]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-06-24T00:00:00"}