{"id":"https://openalex.org/W2137270971","doi":"https://doi.org/10.1109/aspaa.2011.6082352","title":"Machine hearing: Audio analysis by emulation of human hearing","display_name":"Machine hearing: Audio analysis by emulation of human hearing","publication_year":2011,"publication_date":"2011-10-01","ids":{"openalex":"https://openalex.org/W2137270971","doi":"https://doi.org/10.1109/aspaa.2011.6082352","mag":"2137270971"},"language":"en","primary_location":{"id":"doi:10.1109/aspaa.2011.6082352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-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/A5026382065","display_name":"Richard F. Lyon","orcid":"https://orcid.org/0000-0003-2348-811X"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Richard F. Lyon","raw_affiliation_strings":["Google Inc., USA","Google, Inc, USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]},{"raw_affiliation_string":"Google, Inc, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5026382065"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.1725331,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"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/T11309","display_name":"Music and Audio Processing","score":0.9800999760627747,"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/T11309","display_name":"Music and Audio Processing","score":0.9800999760627747,"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/T10860","display_name":"Speech and Audio Processing","score":0.9520000219345093,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.91839998960495,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/emulation","display_name":"Emulation","score":0.8138055801391602},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689203679561615},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5430317521095276},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5388147234916687},{"id":"https://openalex.org/keywords/hearing-aid","display_name":"Hearing aid","score":0.4451969265937805},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.35968852043151855},{"id":"https://openalex.org/keywords/audiology","display_name":"Audiology","score":0.31026583909988403},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.18770095705986023},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.17756536602973938},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.08165627717971802},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.054315030574798584}],"concepts":[{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.8138055801391602},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689203679561615},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5430317521095276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5388147234916687},{"id":"https://openalex.org/C2780801066","wikidata":"https://www.wikidata.org/wiki/Q323808","display_name":"Hearing aid","level":2,"score":0.4451969265937805},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.35968852043151855},{"id":"https://openalex.org/C548259974","wikidata":"https://www.wikidata.org/wiki/Q569965","display_name":"Audiology","level":1,"score":0.31026583909988403},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.18770095705986023},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.17756536602973938},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.08165627717971802},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.054315030574798584},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/aspaa.2011.6082352","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aspaa.2011.6082352","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1603949574","https://openalex.org/W2604447241","https://openalex.org/W2170815394","https://openalex.org/W2353318413","https://openalex.org/W2379113420","https://openalex.org/W2897411159","https://openalex.org/W2125041499","https://openalex.org/W2921688766","https://openalex.org/W4283765032","https://openalex.org/W4287850210"],"abstract_inverted_index":{"While":[0],"many":[1],"approaches":[2],"to":[3,45,60,109,118,128,160,199],"audio":[4],"analysis":[5],"are":[6,175],"based":[7,14],"on":[8,15,153],"elegant":[9],"mathematical":[10],"models,":[11],"an":[12,148,204],"approach":[13],"emulation":[16],"of":[17,54,68,85,114,144,150,203,224],"human":[18],"hearing":[19,228],"is":[20,27,59,171,197],"becoming":[21],"a":[22,65,71,103,211],"strong":[23],"challenger.":[24],"The":[25,121,136,168],"difference":[26],"subtle,":[28],"as":[29,38,91,147,164],"it":[30],"involves":[31,216],"extending":[32],"such":[33,90],"mathematically":[34],"nice":[35],"signal-processing":[36],"concepts":[37],"linear":[39],"systems,":[40,89],"transforms,":[41],"and":[42,51,99,111,158,190,219,234],"second-order":[43],"statistics":[44],"include":[46],"the":[47,57,115,133,155,178,201,206,222],"messier":[48],"nonlinear,":[49],"adaptive,":[50],"evolved":[52],"aspects":[53],"hearing.":[55,120],"Essentially,":[56],"goal":[58],"form":[61],"representations":[62],"that":[63,76,81,107],"do":[64],"good":[66],"job":[67],"capturing":[69],"what":[70,151,183],"signal":[72,230],"\u201csounds":[73],"like\u201d,":[74],"so":[75],"we":[77],"can":[78,220],"make":[79],"systems":[80],"react":[82],"accordingly.":[83],"Some":[84],"our":[86],"recent":[87],"experimental":[88],"sound":[92],"retrieval":[93],"from":[94,177],"text":[95],"queries,":[96],"melody":[97],"matching,":[98],"music":[100],"recommendation,":[101],"employ":[102],"four-layer":[104],"machine-hearing":[105],"architecture":[106],"attempts":[108],"simplify":[110],"systematize":[112],"some":[113],"methods":[116],"used":[117,198],"emulate":[119],"peripheral":[122],"level":[123,138,170],"utilizes":[124],"nonlinear":[125,134],"filter":[126],"cascades":[127],"model":[129],"wave":[130],"propagation":[131],"in":[132,154,186],"cochlea.":[135],"second":[137],"computes":[139],"one":[140],"or":[141],"more":[142],"types":[143],"auditory":[145,156,179,187],"image,":[146],"abstraction":[149],"goes":[152],"brainstem,":[157],"projecting":[159],"cortical":[161],"sheets":[162],"much":[163],"visual":[165],"images":[166],"do.":[167],"third":[169],"where":[172],"application-dependent":[173],"features":[174],"extracted":[176],"images,":[180],"abstractly":[181],"modeling":[182],"likely":[184],"happens":[185],"cortex.":[188],"Finally,":[189],"most":[191],"abstractly,":[192],"any":[193],"appropriate":[194],"machine-learning":[195],"system":[196],"address":[200],"needs":[202],"application,":[205],"brain-motivated":[207],"neural":[208],"network":[209],"being":[210],"prototypical":[212],"example.":[213],"Each":[214],"layer":[215],"different":[217,225],"disciplines,":[218],"leverage":[221],"experiences":[223],"fields,":[226],"including":[227],"science,":[229],"processing,":[231],"machine":[232,235],"vision,":[233],"learning.":[236]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}