{"id":"https://openalex.org/W2015433306","doi":"https://doi.org/10.1109/jproc.2013.2251591","title":"An Overview on Perceptually Motivated Audio Indexing and Classification","display_name":"An Overview on Perceptually Motivated Audio Indexing and Classification","publication_year":2013,"publication_date":"2013-07-16","ids":{"openalex":"https://openalex.org/W2015433306","doi":"https://doi.org/10.1109/jproc.2013.2251591","mag":"2015433306"},"language":"en","primary_location":{"id":"doi:10.1109/jproc.2013.2251591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2013.2251591","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-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/A5113927018","display_name":"Ga\u00ebl Richard","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Gael Richard","raw_affiliation_strings":["T\u00e9l\u00e9com ParisTech, Paris, France","Telecom-ParisTech, paris, France#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T\u00e9l\u00e9com ParisTech, Paris, France","institution_ids":["https://openalex.org/I12356871"]},{"raw_affiliation_string":"Telecom-ParisTech, paris, France#TAB#","institution_ids":["https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["Audyssey Laboratories, Inc., Los Angeles, CA, USA","Audyssey Labs., Los Angeles, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Audyssey Laboratories, Inc., Los Angeles, CA, USA","institution_ids":[]},{"raw_affiliation_string":"Audyssey Labs., Los Angeles, CA, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104114055","display_name":"Shrikanth Narayanan","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["University of Southern California, Los Angeles, CA, USA","[University of Southern California Los, Angeles, CA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"[University of Southern California Los, Angeles, CA, USA]","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":2.9951,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.90896602,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"101","issue":"9","first_page":"1939","last_page":"1954"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9944000244140625,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.8090307712554932},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7837326526641846},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.6832587122917175},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.575486421585083},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5462548136711121},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.490852415561676},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.48096218705177307},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4741379916667938},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46408841013908386},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.4293973743915558},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.4223557114601135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3713759183883667},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3358880281448364},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.2708480954170227},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2135310173034668},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.18343853950500488}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.8090307712554932},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7837326526641846},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.6832587122917175},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.575486421585083},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5462548136711121},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.490852415561676},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.48096218705177307},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4741379916667938},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46408841013908386},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4293973743915558},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.4223557114601135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3713759183883667},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3358880281448364},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2708480954170227},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2135310173034668},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.18343853950500488},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"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/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/jproc.2013.2251591","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jproc.2013.2251591","pdf_url":null,"source":{"id":"https://openalex.org/S68686220","display_name":"Proceedings of the IEEE","issn_l":"0018-9219","issn":["0018-9219","1558-2256"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the IEEE","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.646.8284","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.646.8284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://perso.telecom-paristech.fr/~grichard/Publications/Preprint-Richard-ProcIEEE2013.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:hal-02286490v1","is_oa":false,"landing_page_url":"https://telecom-paris.hal.science/hal-02286490","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the IEEE, 2013","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":142,"referenced_works":["https://openalex.org/W24912070","https://openalex.org/W40351532","https://openalex.org/W57570932","https://openalex.org/W65340009","https://openalex.org/W84813673","https://openalex.org/W99009587","https://openalex.org/W180805716","https://openalex.org/W181056519","https://openalex.org/W396690109","https://openalex.org/W875533737","https://openalex.org/W1480485976","https://openalex.org/W1489184006","https://openalex.org/W1578856370","https://openalex.org/W1579979987","https://openalex.org/W1602667807","https://openalex.org/W1619226191","https://openalex.org/W1863372652","https://openalex.org/W1868379447","https://openalex.org/W1964287530","https://openalex.org/W1966273763","https://openalex.org/W1966365432","https://openalex.org/W1968311960","https://openalex.org/W1973746598","https://openalex.org/W1977863522","https://openalex.org/W1986023967","https://openalex.org/W1986595194","https://openalex.org/W1990014053","https://openalex.org/W1991661457","https://openalex.org/W1992272902","https://openalex.org/W1996227995","https://openalex.org/W2001832747","https://openalex.org/W2010486494","https://openalex.org/W2018844855","https://openalex.org/W2019276416","https://openalex.org/W2023952145","https://openalex.org/W2026000986","https://openalex.org/W2028895660","https://openalex.org/W2029654180","https://openalex.org/W2032360374","https://openalex.org/W2036403449","https://openalex.org/W2048174296","https://openalex.org/W2057745663","https://openalex.org/W2057812517","https://openalex.org/W2059020775","https://openalex.org/W2062170755","https://openalex.org/W2073553508","https://openalex.org/W2074188409","https://openalex.org/W2077456266","https://openalex.org/W2082308387","https://openalex.org/W2089355218","https://openalex.org/W2090879738","https://openalex.org/W2094429819","https://openalex.org/W2095725796","https://openalex.org/W2096569327","https://openalex.org/W2103218155","https://openalex.org/W2103253424","https://openalex.org/W2103267130","https://openalex.org/W2103652234","https://openalex.org/W2103869314","https://openalex.org/W2107157326","https://openalex.org/W2110465268","https://openalex.org/W2113539812","https://openalex.org/W2114708606","https://openalex.org/W2115800223","https://openalex.org/W2116244429","https://openalex.org/W2119479037","https://openalex.org/W2119662931","https://openalex.org/W2121407761","https://openalex.org/W2122736533","https://openalex.org/W2126525201","https://openalex.org/W2126693545","https://openalex.org/W2127566601","https://openalex.org/W2127778164","https://openalex.org/W2127807804","https://openalex.org/W2128301448","https://openalex.org/W2128838222","https://openalex.org/W2129258718","https://openalex.org/W2130426352","https://openalex.org/W2130640900","https://openalex.org/W2131981197","https://openalex.org/W2132399916","https://openalex.org/W2132606418","https://openalex.org/W2133824856","https://openalex.org/W2135733734","https://openalex.org/W2136951780","https://openalex.org/W2137075158","https://openalex.org/W2137337354","https://openalex.org/W2137343183","https://openalex.org/W2137561966","https://openalex.org/W2141517887","https://openalex.org/W2143728216","https://openalex.org/W2144037622","https://openalex.org/W2144345993","https://openalex.org/W2147152072","https://openalex.org/W2147324912","https://openalex.org/W2148154194","https://openalex.org/W2149368536","https://openalex.org/W2151305614","https://openalex.org/W2152909444","https://openalex.org/W2153039158","https://openalex.org/W2154016477","https://openalex.org/W2158508307","https://openalex.org/W2158630797","https://openalex.org/W2159277110","https://openalex.org/W2160691368","https://openalex.org/W2162867699","https://openalex.org/W2164764235","https://openalex.org/W2164767140","https://openalex.org/W2164877274","https://openalex.org/W2166693890","https://openalex.org/W2167314423","https://openalex.org/W2167836729","https://openalex.org/W2168441989","https://openalex.org/W2169131441","https://openalex.org/W2181860161","https://openalex.org/W2248316279","https://openalex.org/W2294993808","https://openalex.org/W2295300449","https://openalex.org/W2305540842","https://openalex.org/W2331166300","https://openalex.org/W2606760755","https://openalex.org/W3146463283","https://openalex.org/W3217467030","https://openalex.org/W4230706820","https://openalex.org/W4235128394","https://openalex.org/W4242964401","https://openalex.org/W4248853067","https://openalex.org/W4256399001","https://openalex.org/W4285719527","https://openalex.org/W4297795103","https://openalex.org/W6601025087","https://openalex.org/W6603446537","https://openalex.org/W6639041776","https://openalex.org/W6675656264","https://openalex.org/W6677088163","https://openalex.org/W6681049385","https://openalex.org/W6696886941","https://openalex.org/W6697597305","https://openalex.org/W6702387769","https://openalex.org/W6736174358","https://openalex.org/W6805302155","https://openalex.org/W7073618627"],"related_works":["https://openalex.org/W2131156500","https://openalex.org/W2118916824","https://openalex.org/W2289868279","https://openalex.org/W4231351862","https://openalex.org/W1479881079","https://openalex.org/W1611900921","https://openalex.org/W2064012922","https://openalex.org/W1620668332","https://openalex.org/W2033602688","https://openalex.org/W2156141367"],"abstract_inverted_index":{"An":[0],"audio":[1,7,20,72,149,167,180,185],"indexing":[2,23,75,150],"system":[3,52],"aims":[4],"at":[5],"describing":[6],"content":[8],"by":[9,44],"identifying,":[10],"labeling,":[11],"or":[12,80,129,151],"categorizing":[13],"different":[14,92],"acoustic":[15],"events.":[16],"Since":[17],"the":[18,49,54,67,100,107,114,142,145,148,162],"resulting":[19],"classification":[21,73,152],"and":[22,74,140,175],"is":[24,31],"meant":[25],"for":[26,113],"direct":[27],"human":[28,50,96,179],"consumption,":[29],"it":[30,35],"highly":[32],"desirable":[33],"that":[34,76,81,117,169],"produces":[36],"perceptually":[37,78,110,119],"relevant":[38,111],"results.":[39],"This":[40],"can":[41],"be":[42],"obtained":[43],"integrating":[45],"specific":[46],"knowledge":[47],"of":[48,66,85,102,109,125,137,144,161,178],"auditory":[51],"in":[53,71,147,165],"design":[55],"process":[56],"to":[57,94],"various":[58],"extent.":[59],"In":[60,87,154],"this":[61,155],"paper,":[62,156],"we":[63,89,157],"highlight":[64],"some":[65,83,160],"important":[68],"concepts":[69],"used":[70],"are":[77,118],"motivated":[79],"exploit":[82],"principles":[84],"perception.":[86],"particular,":[88],"discuss":[90],"several":[91],"strategies":[93],"integrate":[95],"perception,":[97],"including:":[98],"1)":[99],"use":[101,108],"generic":[103],"audition":[104],"models;":[105],"2)":[106],"features":[112],"analysis":[115],"stage":[116],"justified":[120],"either":[121],"as":[122,130],"a":[123,126,134],"component":[124],"hearing":[127],"model":[128],"being":[131],"correlated":[132],"with":[133],"perceptual":[135,173],"dimension":[136],"sound":[138],"similarity;":[139],"3)":[141],"involvement":[143],"user":[146],"task.":[153],"also":[158],"illustrate":[159],"recent":[163],"trends":[164],"semantic":[166],"retrieval":[168],"approximate":[170],"higher":[171],"level":[172],"processing":[174],"cognitive":[176],"aspects":[177],"recognition":[181],"capabilities,":[182],"including":[183],"affect-based":[184],"retrieval.":[186]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}