{"id":"https://openalex.org/W2260465653","doi":null,"title":"A perceptual auditory spectral centroid model","display_name":"A perceptual auditory spectral centroid model","publication_year":1998,"publication_date":"1998-01-01","ids":{"openalex":"https://openalex.org/W2260465653","mag":"2260465653"},"language":"en","primary_location":{"id":"mag:2260465653","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=926722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","indexed_in":[],"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/A5089183504","display_name":"Ashok Kumar Krishnamurthy","orcid":"https://orcid.org/0000-0002-3215-7622","observed_orcids":["https://orcid.org/0000-0002-3215-7622"]},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashok Krishnamurthy","raw_affiliation_strings":["the Ohio State University"],"raw_orcid":"https://orcid.org/0000-0002-3215-7622","affiliations":[{"raw_affiliation_string":"the Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002478334","display_name":"Jayanth N. Anantharaman","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jayanth N. Anantharaman","raw_affiliation_strings":["the Ohio State University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"the Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37563048,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6104000210762024,"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":0.6104000210762024,"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/T10788","display_name":"Neuroscience and Music Perception","score":0.18310000002384186,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.13609999418258667,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/time-frequency-representation","display_name":"time-frequency representation","score":0.6290000081062317},{"id":"https://openalex.org/keywords/auditory-filterbank","display_name":"auditory filterbank","score":0.7480000257492065},{"id":"https://openalex.org/keywords/spectral-integration","display_name":"spectral integration","score":0.9589999914169312},{"id":"https://openalex.org/keywords/temporal-integration","display_name":"temporal integration","score":0.7609999775886536},{"id":"https://openalex.org/keywords/formant-tracking","display_name":"formant tracking","score":0.7960000038146973},{"id":"https://openalex.org/keywords/speech-processing","display_name":"speech processing","score":0.41600000858306885},{"id":"https://openalex.org/keywords/psychoacoustic-modeling","display_name":"psychoacoustic modeling","score":0.6150000095367432}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6754997968673706},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6110875606536865},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.5721821784973145},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.571153998374939},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.5709783434867859},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.5598106384277344},{"id":"https://openalex.org/C2777443451","wikidata":"https://www.wikidata.org/wiki/Q821413","display_name":"Auditory system","level":2,"score":0.5481109023094177},{"id":"https://openalex.org/C2776096036","wikidata":"https://www.wikidata.org/wiki/Q1140483","display_name":"Narrowband","level":2,"score":0.5190808773040771},{"id":"https://openalex.org/C79018884","wikidata":"https://www.wikidata.org/wiki/Q622324","display_name":"Loudness","level":2,"score":0.5176318287849426},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.493472695350647},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.46773892641067505},{"id":"https://openalex.org/C146599234","wikidata":"https://www.wikidata.org/wiki/Q511093","display_name":"Centroid","level":2,"score":0.41874057054519653},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3273228108882904},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.2929942011833191},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.2527102530002594},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.17420944571495056},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.12035202980041504},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10182610154151917},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.0},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2260465653","doi":null,"is_oa":false,"landing_page_url":"http://dl.acm.org/citation.cfm?id=926722","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2163679336","https://openalex.org/W2516900350","https://openalex.org/W2045917385","https://openalex.org/W2122516409","https://openalex.org/W2015056402","https://openalex.org/W7019763230","https://openalex.org/W1643557102","https://openalex.org/W4396556573","https://openalex.org/W2338821614","https://openalex.org/W2064944707"],"abstract_inverted_index":{"This":[0,179,200],"work":[1],"is":[2,42,51,64,85,111,172,181],"based":[3,86,143],"on":[4,87,144,255],"the":[5,8,13,18,28,79,88,102,120,125,158,247,266,288],"fact":[6],"that":[7,41,49,62,77,171,239],"human":[9,80],"auditory":[10,81,133,289],"system":[11,16],"outperforms":[12],"best":[14],"automated":[15],"in":[17,48,61,100,175,197,225,250,270],"processing":[19,39,54,67,84],"and":[20,147,165,177,191,222],"extraction":[21],"of":[22,30,53,66,78,91,105,119,157,188,211,246,287],"information":[23],"from":[24,27,279],"sounds.":[25],"Results":[26],"field":[29],"experimental":[31],"psychoacoustics":[32],"are":[33,169,240,282],"used":[34,183],"to":[35,76,184,194,205,208,264],"develop":[36],"a":[37,72,114,154,166,186,203,209,242],"signal":[38],"model":[40,95,110,123,152],"(1)":[43,129,182],"perceptually":[44],"motivated;":[45],"(2)":[46,132,192],"dynamic,":[47],"it":[50,63],"capable":[52,65],"sounds":[55,69],"with":[56,257,285],"time-varying":[57],"spectra;":[58],"(3)":[59,135],"multi-channel,":[60],"wideband":[68],"by":[70],"providing":[71],"filtering":[73],"mechanism":[74,232],"similar":[75],"system.":[82],"The":[83,122,151],"intensity-weighted":[89],"average":[90],"instantaneous":[92],"frequency":[93,104,163,237],"(IWAIF)":[94],"which":[96],"has":[97,202],"been":[98],"successful":[99],"predicting":[101],"perceived":[103,162],"stationary":[106],"narrowband":[107],"signals.":[108],"Our":[109],"built":[112],"using":[113],"positive":[115],"time-frequency":[116],"representation":[117,156,180,201],"(TFR)":[118],"signal.":[121,160],"includes":[124],"following":[126],"main":[127],"stages:":[128],"equal-loudness":[130],"pre-emphasis,":[131],"filterbank,":[134],"intensity-loudness":[136],"compression,":[137],"(4)":[138],"localized":[139,173],"spectral":[140,145,227,267],"centroid":[141],"computation":[142],"integration":[146,149,228,268],"temporal":[148],"studies.":[150],"generates":[153],"perceptual":[155,226],"physical":[159],"A":[161,260],"value":[164,168],"level":[167],"produced":[170],"both":[174],"time":[176],"frequency.":[178],"predict":[185],"number":[187,210],"psychoacoustic":[189],"results,":[190],"applied":[193,207],"track":[195],"formants":[196],"natural":[198],"speech.":[199],"potential":[204],"be":[206],"applications":[212],"such":[213],"as":[214],"automatic":[215],"speech":[216,218,220],"recognition,":[217],"syllthesis,":[219],"coding":[221],"source":[223],"segregation.\r\nStudies":[224],"indicate":[229],"an":[230],"averaging":[231],"or":[233],"center-of-gravity":[234],"effect":[235,269],"for":[236],"components":[238],"within":[241],"critical":[243],"distance.":[244],"Most":[245],"studies":[248],"conducted":[249,263],"this":[251,280],"area":[252],"have":[253],"concentrated":[254],"signals":[256,273],"steady-state":[258],"spectra.":[259],"study":[261,281],"was":[262],"examine":[265],"dynamic":[271],"tone":[272],"called":[274],"virtual":[275],"glides.":[276],"Subject":[277],"results":[278],"presented":[283],"along":[284],"predictions":[286],"spectral-centroid":[290],"model.":[291]},"counts_by_year":[],"updated_date":"2026-09-22T06:50:58.402377","created_date":"2016-06-24T00:00:00"}