{"id":"https://openalex.org/W59149375","doi":"https://doi.org/10.5281/zenodo.42877","title":"Classification Of Audio Scenes Using Narrow-Band Autocorrelation Features","display_name":"Classification Of Audio Scenes Using Narrow-Band Autocorrelation Features","publication_year":2012,"publication_date":"2012-08-27","ids":{"openalex":"https://openalex.org/W59149375","doi":"https://doi.org/10.5281/zenodo.42877","mag":"59149375"},"language":"en","primary_location":{"id":"pmh:oai:zenodo.org:42877","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/42877","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://zenodo.org/record/42877","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160413683","display_name":"Francesc Al\u00edas","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5593406","display_name":"Universitat Ramon Llull","ror":"https://ror.org/04p9k2z50","country_code":"ES","type":"education","lineage":["https://openalex.org/I5593406"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Al\u00edas, Francesc","raw_affiliation_strings":["Grup de Recerca en Tecnologies M\u00e8dia La Salle - Universitat Ramon Llull, Barcelona, Catalonia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grup de Recerca en Tecnologies M\u00e8dia La Salle - Universitat Ramon Llull, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I5593406"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160419004","display_name":"Xavier Valero","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5593406","display_name":"Universitat Ramon Llull","ror":"https://ror.org/04p9k2z50","country_code":"ES","type":"education","lineage":["https://openalex.org/I5593406"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Valero, Xavier","raw_affiliation_strings":["Grup de Recerca en Tecnologies M\u00e8dia La Salle - Universitat Ramon Llull, Barcelona, Catalonia, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grup de Recerca en Tecnologies M\u00e8dia La Salle - Universitat Ramon Llull, Barcelona, Catalonia, Spain","institution_ids":["https://openalex.org/I5593406"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5593406"],"apc_list":null,"apc_paid":null,"fwci":0.327,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.39799537,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2012","last_page":"2019"},"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":0.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/acoustic-scene-classification","display_name":"acoustic scene classification","score":0.9940000176429749},{"id":"https://openalex.org/keywords/autocorrelation-function","display_name":"autocorrelation function","score":0.8679999709129333},{"id":"https://openalex.org/keywords/mel-filter-bank","display_name":"Mel filter bank","score":0.9309999942779541},{"id":"https://openalex.org/keywords/sound-event-recognition","display_name":"sound event recognition","score":0.7580000162124634},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.7459999918937683}],"concepts":[{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.7904418706893921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641679406166077},{"id":"https://openalex.org/C100515483","wikidata":"https://www.wikidata.org/wiki/Q3268235","display_name":"Filter bank","level":3,"score":0.6222374439239502},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5881993174552917},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.572272539138794},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5685704350471497},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5529122352600098},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5274883508682251},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5067375302314758},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5062479376792908},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.49483197927474976},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.44569963216781616},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4448257088661194},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.4372740685939789},{"id":"https://openalex.org/C183223151","wikidata":"https://www.wikidata.org/wiki/Q4826228","display_name":"Autocorrelation technique","level":3,"score":0.4294314980506897},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.364335298538208},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.341214120388031},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22782230377197266},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.17656159400939941},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:zenodo.org:42877","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/42877","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},{"id":"mag:3145295344","doi":null,"is_oa":false,"landing_page_url":"http://yadda.icm.edu.pl/yadda/element/bwmeta1.element.ieee-000006333945","pdf_url":null,"source":{"id":"https://openalex.org/S4363607788","display_name":"European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference","raw_type":null},{"id":"doi:10.5281/zenodo.42877","doi":"https://doi.org/10.5281/zenodo.42877","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.42877","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"mag:59149375","doi":null,"is_oa":false,"landing_page_url":"http://ieeexplore.ieee.org/document/6333945/","pdf_url":null,"source":{"id":"https://openalex.org/S4363607788","display_name":"European Signal Processing Conference (EUSIPCO)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"European Signal Processing Conference","raw_type":null}],"best_oa_location":{"id":"pmh:oai:zenodo.org:42877","doi":null,"is_oa":true,"landing_page_url":"https://zenodo.org/record/42877","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W2043148333","https://openalex.org/W2044822228","https://openalex.org/W2100375615","https://openalex.org/W2103869314","https://openalex.org/W2130640900","https://openalex.org/W2137343183","https://openalex.org/W2140053068","https://openalex.org/W2153811331","https://openalex.org/W2162676242","https://openalex.org/W2170355566"],"related_works":["https://openalex.org/W1996375102","https://openalex.org/W2058189943","https://openalex.org/W2164311876","https://openalex.org/W4249410328","https://openalex.org/W2157279550","https://openalex.org/W2982629693","https://openalex.org/W1940377967","https://openalex.org/W2078666420","https://openalex.org/W3003801034","https://openalex.org/W6941535431"],"abstract_inverted_index":{"Multiple":[0],"single":[1],"sound":[2],"events":[3],"of":[4,28,44,54,68,93,97,102],"very":[5],"different":[6],"characteristics":[7,53],"might":[8],"coincide":[9],"in":[10],"a":[11,36,42,74,91],"given":[12],"space":[13],"and":[14,51,123],"time,":[15],"thus":[16],"composing":[17],"complex":[18],"audio":[19,33,56,99],"scenes.":[20,100],"In":[21],"that":[22,46],"context,":[23],"defining":[24],"signal":[25,88],"features":[26,45,61,83,89],"capable":[27],"effectively":[29],"analyzing":[30],"the":[31,48,55,60,65,103,107,110],"holistic":[32],"scenes":[34],"is":[35],"challenging":[37],"task.":[38],"This":[39],"paper":[40],"introduces":[41],"set":[43],"consider":[47],"temporal,":[49],"spectral":[50],"perceptual":[52],"scene":[57],"signals.":[58],"Specifically,":[59],"are":[62,84],"obtained":[63],"from":[64],"autocorrelation":[66],"function":[67],"band-pass":[69],"signals":[70],"computed":[71],"after":[72],"applying":[73],"Mel":[75,119],"filter":[76],"bank.":[77],"The":[78],"so-called":[79],"Narrow-Band":[80],"Autocorrelation":[81],"(NB-ACF)":[82],"compared":[85],"to":[86],"state-of-the-art":[87],"on":[90],"corpus":[92],"4":[94],"hours":[95],"composed":[96],"15":[98],"Regardless":[101],"learning":[104],"algorithm":[105],"employed,":[106],"NB-ACF":[108],"attains":[109],"highest":[111],"averaged":[112],"recognition":[113],"rates:":[114],"2.3":[115],"%":[116,125],"higher":[117,126],"than":[118,127],"Frequency":[120],"Cepstral":[121],"Coefficients":[122],"5.6":[124],"Discrete":[128],"Wavelet":[129],"Coefficients.":[130]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}