{"id":"https://openalex.org/W2120751918","doi":"https://doi.org/10.1109/icassp.2005.1415267","title":"A Study of Auditory Modeling and Processing for Speech Signals","display_name":"A Study of Auditory Modeling and Processing for Speech Signals","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2120751918","doi":"https://doi.org/10.1109/icassp.2005.1415267","mag":"2120751918"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5055671046","display_name":"Woojay Jeon","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Woojay Jeon","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","Sch. of Electr. & Comput. Eng.,, Georgia Inst. of Technol., Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng.,, Georgia Inst. of Technol., Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070867959","display_name":"Biing\u2010Hwang Juang","orcid":"https://orcid.org/0000-0002-5773-5679"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Biing-Hwang Juang","raw_affiliation_strings":["School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","Sch. of Electr. & Comput. Eng.,, Georgia Inst. of Technol., Atlanta, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electrical and Computer Engineering, Georgia Institute of Technology, Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Sch. of Electr. & Comput. Eng.,, Georgia Inst. of Technol., Atlanta, GA, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.2631,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.777658,"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":"929","last_page":"932"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9970999956130981,"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/T11447","display_name":"Blind Source Separation Techniques","score":0.9970999956130981,"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/T10320","display_name":"Neural Networks and Applications","score":0.9961000084877014,"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/T10581","display_name":"Neural dynamics and brain function","score":0.9943000078201294,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.726213276386261},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7219758629798889},{"id":"https://openalex.org/keywords/auditory-system","display_name":"Auditory system","score":0.6770761013031006},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6496469974517822},{"id":"https://openalex.org/keywords/auditory-scene-analysis","display_name":"Auditory scene analysis","score":0.5565210580825806},{"id":"https://openalex.org/keywords/computational-auditory-scene-analysis","display_name":"Computational auditory scene analysis","score":0.547429084777832},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5276692509651184},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5192053914070129},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5135255455970764},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4721498489379883},{"id":"https://openalex.org/keywords/auditory-cortex","display_name":"Auditory cortex","score":0.46944260597229004},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44914111495018005},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4237365126609802},{"id":"https://openalex.org/keywords/auditory-perception","display_name":"Auditory perception","score":0.4210396111011505},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4200054407119751},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3532026708126068},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3252869248390198},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14559385180473328},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09886503219604492}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.726213276386261},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219758629798889},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.6770761013031006},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6496469974517822},{"id":"https://openalex.org/C38129911","wikidata":"https://www.wikidata.org/wiki/Q4820038","display_name":"Auditory scene analysis","level":3,"score":0.5565210580825806},{"id":"https://openalex.org/C73208851","wikidata":"https://www.wikidata.org/wiki/Q5157303","display_name":"Computational auditory scene analysis","level":2,"score":0.547429084777832},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5276692509651184},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5192053914070129},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5135255455970764},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4721498489379883},{"id":"https://openalex.org/C2780297895","wikidata":"https://www.wikidata.org/wiki/Q18676","display_name":"Auditory cortex","level":2,"score":0.46944260597229004},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44914111495018005},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4237365126609802},{"id":"https://openalex.org/C3020799230","wikidata":"https://www.wikidata.org/wiki/Q160289","display_name":"Auditory perception","level":3,"score":0.4210396111011505},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4200054407119751},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3532026708126068},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3252869248390198},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14559385180473328},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09886503219604492},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1986795928","https://openalex.org/W1990208414","https://openalex.org/W2012352340","https://openalex.org/W2067098744","https://openalex.org/W2077804127","https://openalex.org/W2122516409","https://openalex.org/W2129715180","https://openalex.org/W2132606418","https://openalex.org/W2163680580","https://openalex.org/W2799061466","https://openalex.org/W4205687621"],"related_works":["https://openalex.org/W1567098080","https://openalex.org/W2362704157","https://openalex.org/W2051363478","https://openalex.org/W3199891340","https://openalex.org/W1539684593","https://openalex.org/W7819095","https://openalex.org/W2004648780","https://openalex.org/W2000677804","https://openalex.org/W2076931986","https://openalex.org/W2474557191"],"abstract_inverted_index":{"We":[0],"study":[1,105,167],"a":[2,6,80,103,131,146,184],"modified":[3],"version":[4],"of":[5,9,32,51,63,72,91,106,134,165,186],"computational":[7],"model":[8,93,124],"the":[10,30,41,52,61,67,73,89,92,107,122,135,141,156],"human":[11,136,187],"peripheral":[12],"and":[13,19,28,189],"central":[14,74],"auditory":[15,55,75,123,137],"system":[16,76],"(Wang,":[17],"K.":[18],"Shamma,":[20],"S.A.,":[21],"1995;":[22],"Yang,":[23],"X.":[24],"et":[25],"al.,":[26],"1992),":[27],"examine":[29],"validity":[31],"its":[33],"output":[34],"from":[35,66],"two":[36],"practical":[37],"perspectives.":[38],"One":[39],"considers":[40],"well-known":[42],"Mel-frequency":[43],"cepstral":[44],"coefficients":[45],"(MFCC)":[46],"as":[47],"an":[48,95],"approximate":[49],"representation":[50],"physiology-based":[53],"early":[54],"processing":[56],"result.":[57],"The":[58,163],"other":[59],"allows":[60],"derivation":[62],"feature":[64],"vectors":[65],"dimension":[68],"expanded":[69],"cortical":[70,108,142],"response":[71,109,143],"for":[77],"use":[78],"in":[79,110,120,175],"conventional":[81],"phoneme":[82],"recognition":[83,99],"task.":[84],"In":[85,139],"addition":[86],"to":[87,116,125,155,170,182],"confirming":[88],"relevancy":[90],"under":[94],"existing":[96],"statistical":[97],"speech":[98],"framework,":[100],"we":[101],"conduct":[102],"preliminary":[104],"connection":[111],"with":[112],"known":[113],"physiological":[114],"studies,":[115],"find":[117],"new":[118],"possibilities":[119],"using":[121],"perform":[126],"cognitive":[127,190],"functions":[128],"based":[129],"on":[130],"better":[132],"understanding":[133],"system.":[138],"particular,":[140],"may":[144,179],"be":[145,180],"place-coded":[147],"data":[148],"set":[149],"where":[150],"sounds":[151],"are":[152],"categorized":[153],"according":[154],"regions":[157],"containing":[158],"their":[159],"most":[160],"distinguishing":[161],"features.":[162],"results":[164],"this":[166,177],"encourage":[168],"us":[169],"develop":[171],"hierarchical,":[172],"detection-based":[173],"methods":[174],"which":[176],"mechanism":[178],"utilized":[181],"simulate":[183],"variety":[185],"perceptual":[188],"functions.":[191]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}