{"id":"https://openalex.org/W2058189943","doi":"https://doi.org/10.1109/icassp.2002.5745009","title":"Computational auditory scene recognition","display_name":"Computational auditory scene recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2058189943","doi":"https://doi.org/10.1109/icassp.2002.5745009","mag":"2058189943"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745009","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","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/A5026652585","display_name":"Vesa Peltonen","orcid":"https://orcid.org/0000-0002-6155-9954"},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Vesa Peltonen","raw_affiliation_strings":["Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","Tampere University of Technology, Signal Processing Laboratory, P. O. Box 553, FIN-33101, Finland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere University of Technology, Signal Processing Laboratory, P. O. Box 553, FIN-33101, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111774883","display_name":"J. Tuomi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Juha Tuomi","raw_affiliation_strings":["Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","Tampere University of Technology, Signal Processing Laboratory, P. O. Box 553, FIN-33101, Finland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere University of Technology, Signal Processing Laboratory, P. O. Box 553, FIN-33101, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035987859","display_name":"Anssi Klapuri","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Anssi Klapuri","raw_affiliation_strings":["Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","Tampere University of Technology, Signal Processing Laboratory, P. O. Box 553, FIN-33101, Finland"],"affiliations":[{"raw_affiliation_string":"Signal Processing Laboratory, Tampere University of Technology, Tampere, Finland","institution_ids":["https://openalex.org/I4210133110"]},{"raw_affiliation_string":"Tampere University of Technology, Signal Processing Laboratory, P. O. Box 553, FIN-33101, Finland","institution_ids":["https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057652089","display_name":"Jyri Huopaniemi","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Jyri Huopaniemi","raw_affiliation_strings":["Speech and Audio Systems Laboratory, Nokia Group, Noka Research Center, Finland","Nokia Research Center, Speech and Audio Systems Laboratory, P.O. Box 407, FIN-00045 Nokia Group, Finland"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Systems Laboratory, Nokia Group, Noka Research Center, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Research Center, Speech and Audio Systems Laboratory, P.O. Box 407, FIN-00045 Nokia Group, Finland","institution_ids":["https://openalex.org/I2738502077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054055354","display_name":"T. Sorsa","orcid":null},"institutions":[{"id":"https://openalex.org/I2738502077","display_name":"Nokia (Finland)","ror":"https://ror.org/04pkc8m17","country_code":"FI","type":"company","lineage":["https://openalex.org/I2738502077"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Timo Sorsa","raw_affiliation_strings":["Speech and Audio Systems Laboratory, Nokia Group, Noka Research Center, Finland","Nokia Research Center, Speech and Audio Systems Laboratory, P.O. Box 407, FIN-00045 Nokia Group, Finland"],"affiliations":[{"raw_affiliation_string":"Speech and Audio Systems Laboratory, Nokia Group, Noka Research Center, Finland","institution_ids":["https://openalex.org/I2738502077"]},{"raw_affiliation_string":"Nokia Research Center, Speech and Audio Systems Laboratory, P.O. Box 407, FIN-00045 Nokia Group, Finland","institution_ids":["https://openalex.org/I2738502077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5026652585"],"corresponding_institution_ids":["https://openalex.org/I4210133110"],"apc_list":null,"apc_paid":null,"fwci":13.8501,"has_fulltext":false,"cited_by_count":214,"citation_normalized_percentile":{"value":0.9974337,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"1941"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9757000207901001,"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/computer-science","display_name":"Computer science","score":0.7196669578552246},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6724356412887573},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.6031851768493652},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5961259603500366},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.54982590675354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.543074369430542},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5063446760177612},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4506920278072357},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4431183934211731},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.330485999584198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7196669578552246},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6724356412887573},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.6031851768493652},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5961259603500366},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.54982590675354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.543074369430542},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5063446760177612},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4506920278072357},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4431183934211731},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.330485999584198},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2002.5745009","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745009","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.10.3174","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.10.3174","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/dippafinal.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.17.7724","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.17.7724","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.tut.fi/sgn/arg/klap/peltonen_icassp2002.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7400000095367432,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":53,"referenced_works":["https://openalex.org/W78111734","https://openalex.org/W172974767","https://openalex.org/W1485484592","https://openalex.org/W1494527387","https://openalex.org/W1517697860","https://openalex.org/W1529817334","https://openalex.org/W1545046063","https://openalex.org/W1560013842","https://openalex.org/W1567997379","https://openalex.org/W1572868897","https://openalex.org/W1575431606","https://openalex.org/W1596689267","https://openalex.org/W1603597715","https://openalex.org/W1623080549","https://openalex.org/W1863372652","https://openalex.org/W1957105039","https://openalex.org/W1964538581","https://openalex.org/W1965324089","https://openalex.org/W1965392255","https://openalex.org/W1993625798","https://openalex.org/W2007180964","https://openalex.org/W2022554507","https://openalex.org/W2031300154","https://openalex.org/W2032360374","https://openalex.org/W2044222806","https://openalex.org/W2058170734","https://openalex.org/W2058189943","https://openalex.org/W2065587674","https://openalex.org/W2071396781","https://openalex.org/W2081353817","https://openalex.org/W2086699924","https://openalex.org/W2103076542","https://openalex.org/W2106055371","https://openalex.org/W2114294947","https://openalex.org/W2122111042","https://openalex.org/W2124864596","https://openalex.org/W2124988752","https://openalex.org/W2126281861","https://openalex.org/W2128838222","https://openalex.org/W2144331580","https://openalex.org/W2147174722","https://openalex.org/W2147292340","https://openalex.org/W2149340425","https://openalex.org/W2155413697","https://openalex.org/W2156468046","https://openalex.org/W2158691456","https://openalex.org/W2160149277","https://openalex.org/W2169850486","https://openalex.org/W2264577990","https://openalex.org/W2535270358","https://openalex.org/W2539114660","https://openalex.org/W6603154609","https://openalex.org/W6665314674"],"related_works":["https://openalex.org/W2048014685","https://openalex.org/W2370972896","https://openalex.org/W4317383455","https://openalex.org/W2548511587","https://openalex.org/W4293232884","https://openalex.org/W2422472940","https://openalex.org/W2019475500","https://openalex.org/W2548162870","https://openalex.org/W2138847091","https://openalex.org/W1578916557"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3,26],"address":[4],"the":[5,105,117,132],"problem":[6],"of":[7,29,41,91,98,108,127,134],"computational":[8],"auditory":[9,17,23,37],"scene":[10,24],"recognition":[11,25,28,84,106],"and":[12,44,54,73,93,116,131],"describe":[13],"methods":[14],"to":[15],"classify":[16],"scenes":[18,38,89,115],"into":[19],"predefined":[20],"classes.":[21],"By":[22],"mean":[27],"an":[30,95],"environment":[31],"using":[32],"audio":[33],"information":[34],"only.":[35],"The":[36,81,125],"comprised":[39],"tens":[40],"everyday":[42],"outside":[43],"inside":[45],"environments,":[46],"such":[47],"as":[48],"streets,":[49],"restaurants,":[50],"offices,":[51],"family":[52],"homes,":[53],"cars.":[55],"Two":[56],"completely":[57],"different":[58,88,114,128],"but":[59],"almost":[60],"equally":[61],"effective":[62],"classification":[63],"systems":[64],"were":[65,138],"used:":[66],"band-energy":[67],"ratio":[68],"features":[69,130],"with":[70,77],"1-NN":[71],"classifier":[72],"Mel-frequency":[74],"cepstral":[75],"coefficients":[76],"Gaussian":[78],"mixture":[79],"models.":[80],"best":[82],"obtained":[83],"rate":[85],"for":[86,94,112],"17":[87],"out":[90],"26":[92],"analysis":[96],"duration":[97],"30":[99],"seconds":[100],"was":[101,110,121],"68.4%.":[102],"For":[103],"comparison,":[104],"accuracy":[107],"humans":[109],"70%":[111],"25":[113],"average":[118],"response":[119],"time":[120],"around":[122],"20":[123],"seconds.":[124],"efficiency":[126],"acoustic":[129],"effect":[133],"test":[135],"sequence":[136],"length":[137],"studied.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":13}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}