{"id":"https://openalex.org/W2131486661","doi":"https://doi.org/10.1109/icassp.2004.1325964","title":"Speech enhancement based on a combined multi-channel array with constrained iterative and auditory masked processing","display_name":"Speech enhancement based on a combined multi-channel array with constrained iterative and auditory masked processing","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2131486661","doi":"https://doi.org/10.1109/icassp.2004.1325964","mag":"2131486661"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1325964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"},"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/A5082681724","display_name":"Xianxian Zhang","orcid":"https://orcid.org/0000-0003-1238-1341"},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xianxian Zhang","raw_affiliation_strings":["Robust Speech Processing Group Center for Spoken Language Research","Robust Speech Process. Group, Center for Spoken Language Res., Colorado Univ., Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Robust Speech Processing Group Center for Spoken Language Research","institution_ids":[]},{"raw_affiliation_string":"Robust Speech Process. Group, Center for Spoken Language Res., Colorado Univ., Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"middle","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/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J.H.L. Hansen","raw_affiliation_strings":["Department of Speech, Language and Hearing Sciences University of Colorado, Boulder, USA","Robust Speech Processing Group Center for Spoken Language Research","Robust Speech Process. Group, Center for Spoken Language Res., Colorado Univ., Boulder, CO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Speech, Language and Hearing Sciences University of Colorado, Boulder, USA","institution_ids":["https://openalex.org/I188538660"]},{"raw_affiliation_string":"Robust Speech Processing Group Center for Spoken Language Research","institution_ids":[]},{"raw_affiliation_string":"Robust Speech Process. Group, Center for Spoken Language Res., Colorado Univ., Boulder, CO, USA","institution_ids":["https://openalex.org/I188538660"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068076789","display_name":"K.A. Rehar","orcid":null},"institutions":[{"id":"https://openalex.org/I188538660","display_name":"University of Colorado Boulder","ror":"https://ror.org/02ttsq026","country_code":"US","type":"education","lineage":["https://openalex.org/I188538660"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"K.A. Rehar","raw_affiliation_strings":["University of Colorado \u2010 Boulder"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado \u2010 Boulder","institution_ids":["https://openalex.org/I188538660"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I188538660"],"apc_list":null,"apc_paid":null,"fwci":1.0376,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75313808,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"229"},"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":0.9995999932289124,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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/speech-enhancement","display_name":"Speech enhancement","score":0.8229838609695435},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7591453790664673},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7287373542785645},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7255316376686096},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.666732907295227},{"id":"https://openalex.org/keywords/array-processing","display_name":"Array processing","score":0.6016426682472229},{"id":"https://openalex.org/keywords/beamforming","display_name":"Beamforming","score":0.587874710559845},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5181142687797546},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.49161297082901},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4723958671092987},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4563766419887543},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.45536181330680847},{"id":"https://openalex.org/keywords/signal-processing","display_name":"Signal processing","score":0.3824290335178375},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.1955755054950714},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19131499528884888},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.13353368639945984},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.1108488142490387},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.0693240761756897}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.8229838609695435},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591453790664673},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7287373542785645},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7255316376686096},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.666732907295227},{"id":"https://openalex.org/C2778545087","wikidata":"https://www.wikidata.org/wiki/Q4795883","display_name":"Array processing","level":4,"score":0.6016426682472229},{"id":"https://openalex.org/C54197355","wikidata":"https://www.wikidata.org/wiki/Q5782992","display_name":"Beamforming","level":2,"score":0.587874710559845},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5181142687797546},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.49161297082901},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4723958671092987},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4563766419887543},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.45536181330680847},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.3824290335178375},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.1955755054950714},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19131499528884888},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.13353368639945984},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.1108488142490387},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0693240761756897},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1325964","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1325964","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.47999998927116394}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W167105602","https://openalex.org/W299913130","https://openalex.org/W1493163583","https://openalex.org/W1983079281","https://openalex.org/W1995536493","https://openalex.org/W2109349638","https://openalex.org/W2121973264","https://openalex.org/W2141017704","https://openalex.org/W2167204516","https://openalex.org/W4249052411","https://openalex.org/W6649113906","https://openalex.org/W6680526386"],"related_works":["https://openalex.org/W4375869169","https://openalex.org/W2597829360","https://openalex.org/W2921661700","https://openalex.org/W2138406058","https://openalex.org/W3211091508","https://openalex.org/W2153897396","https://openalex.org/W2136586452","https://openalex.org/W2005805562","https://openalex.org/W68492818","https://openalex.org/W2131486661"],"abstract_inverted_index":{"While":[0],"a":[1,17,41,70,113,126],"number":[2],"of":[3,33,115,129],"studies":[4],"have":[5],"investigated":[6],"various":[7],"speech":[8,56,77,86],"enhancement":[9,78],"and":[10,92,132],"noise":[11,39,122,130],"suppression":[12,131],"schemes,":[13],"most":[14],"consider":[15],"either":[16],"single":[18,51,81],"channel":[19,52,82],"or":[20,59],"array":[21,34],"processing":[22,35,90],"framework.":[23],"Clearly":[24],"there":[25],"are":[26],"potential":[27],"advantages":[28],"in":[29,37,50,149],"leveraging":[30],"the":[31,45,107,116,138,152],"strengths":[32],"solutions":[36],"suppressing":[38],"from":[40,151],"direction":[42],"other":[43],"than":[44],"speaker,":[46],"with":[47,79,119],"that":[48,54],"seen":[49],"methods":[53,83],"include":[55],"spectral":[57,87],"constraints":[58],"psychoacoustically":[60],"motivated":[61],"processing.":[62],"In":[63],"this":[64],"paper,":[65],"we":[66,109],"propose":[67],"to":[68],"integrate":[69],"combined":[71],"fixed/adaptive":[72],"beamforming":[73],"algorithm":[74],"(CFA-BF)":[75],"for":[76],"two":[80],"based":[84,97],"on":[85,112],"constrained":[88],"iterative":[89],"(Auto-LSP),":[91],"an":[93,144],"auditory":[94],"masked":[95],"threshold":[96],"method":[98,140],"using":[99,137],"equivalent":[100],"rectangular":[101],"bandwidth":[102],"filtering":[103],"(GMMSE-AMTERB).":[104],"After":[105],"formulating":[106],"method,":[108],"evaluate":[110],"performance":[111],"subset":[114],"TIMIT":[117],"corpus":[118],"four":[120],"real":[121],"sources.":[123],"We":[124],"demonstrate":[125],"consistent":[127],"level":[128],"voice":[133],"communication":[134],"quality":[135],"improvement":[136],"proposed":[139],"as":[141],"reflected":[142],"by":[143],"overall":[145],"average":[146],"26dB":[147],"increase":[148],"SegSNR":[150],"original":[153],"degraded":[154],"audio":[155],"corpus.":[156]},"counts_by_year":[{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}