{"id":"https://openalex.org/W1978274651","doi":"https://doi.org/10.1109/tmm.2012.2199972","title":"Gammatone Cepstral Coefficients: Biologically Inspired Features for Non-Speech Audio Classification","display_name":"Gammatone Cepstral Coefficients: Biologically Inspired Features for Non-Speech Audio Classification","publication_year":2012,"publication_date":"2012-11-22","ids":{"openalex":"https://openalex.org/W1978274651","doi":"https://doi.org/10.1109/tmm.2012.2199972","mag":"1978274651"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2012.2199972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2012.2199972","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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":"IEEE Transactions on Multimedia","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/A5031820530","display_name":"Xavier Valero","orcid":null},"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":"X. Valero","raw_affiliation_strings":["GTM-Grup de Recerca en Tecnologies M\u00e8dia, La Salle, Universitat Ramon Llull, Barcelona, Spain","GTM-Grup de Recerca en Tecnologies Media, La Salle-Univ. Ramon Llull, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GTM-Grup de Recerca en Tecnologies M\u00e8dia, La Salle, Universitat Ramon Llull, Barcelona, Spain","institution_ids":["https://openalex.org/I5593406"]},{"raw_affiliation_string":"GTM-Grup de Recerca en Tecnologies Media, La Salle-Univ. Ramon Llull, Barcelona, Spain","institution_ids":["https://openalex.org/I5593406"]}]},{"author_position":"last","author":{"id":null,"display_name":"F. Alias","orcid":null},"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":"F. Alias","raw_affiliation_strings":["GTM-Grup de Recerca en Tecnologies M\u00e8dia, La Salle, Universitat Ramon Llull, Barcelona, Spain","GTM-Grup de Recerca en Tecnologies Media, La Salle-Univ. Ramon Llull, Barcelona, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GTM-Grup de Recerca en Tecnologies M\u00e8dia, La Salle, Universitat Ramon Llull, Barcelona, Spain","institution_ids":["https://openalex.org/I5593406"]},{"raw_affiliation_string":"GTM-Grup de Recerca en Tecnologies Media, La Salle-Univ. Ramon Llull, Barcelona, Spain","institution_ids":["https://openalex.org/I5593406"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.706,"has_fulltext":false,"cited_by_count":274,"citation_normalized_percentile":{"value":0.96509201,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"14","issue":"6","first_page":"1684","last_page":"1689"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T11665","display_name":"Animal Vocal Communication and Behavior","score":0.9882000088691711,"subfield":{"id":"https://openalex.org/subfields/1309","display_name":"Developmental Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8990908861160278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8350832462310791},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6888035535812378},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5592188239097595},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.5538950562477112},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.549642026424408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46371009945869446},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44438275694847107},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.4297642707824707},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4233269691467285},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4126214385032654},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3939400017261505},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.35457709431648254},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.32488059997558594},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.272954523563385}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8990908861160278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8350832462310791},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6888035535812378},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5592188239097595},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.5538950562477112},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.549642026424408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46371009945869446},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44438275694847107},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.4297642707824707},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4233269691467285},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4126214385032654},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3939400017261505},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.35457709431648254},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.32488059997558594},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.272954523563385},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2012.2199972","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2012.2199972","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"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":"IEEE Transactions on Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W396690109","https://openalex.org/W607133330","https://openalex.org/W1940630837","https://openalex.org/W1996160964","https://openalex.org/W2005015221","https://openalex.org/W2037976268","https://openalex.org/W2050758723","https://openalex.org/W2107430826","https://openalex.org/W2113968275","https://openalex.org/W2130640900","https://openalex.org/W2137343183","https://openalex.org/W2140647972","https://openalex.org/W2156481234","https://openalex.org/W2161025448","https://openalex.org/W2161036973","https://openalex.org/W2170355566","https://openalex.org/W2362520863","https://openalex.org/W4250499635"],"related_works":["https://openalex.org/W2140099343","https://openalex.org/W2372033758","https://openalex.org/W2366006547","https://openalex.org/W2167481420","https://openalex.org/W2363301696","https://openalex.org/W2363056088","https://openalex.org/W62929309","https://openalex.org/W2527692153","https://openalex.org/W2808395304","https://openalex.org/W2354848066"],"abstract_inverted_index":{"In":[0,70],"the":[1,48,52,73,81,121,147,156],"context":[2],"of":[3,19,83,101,159],"non-speech":[4,89,160],"audio":[5,28,42,90,99,108,135,161],"recognition":[6],"and":[7,25,107,114],"classification":[8,91,123],"for":[9,41,88],"multimedia":[10],"applications,":[11],"it":[12],"becomes":[13],"essential":[14],"to":[15,22,120],"have":[16,35,76],"a":[17,37,46,58,138,143],"set":[18],"features":[20],"able":[21],"accurately":[23],"represent":[24],"discriminate":[26],"among":[27],"signals.":[29],"Mel":[30],"frequency":[31],"cepstral":[32,54],"coefficients":[33,55],"(MFCC)":[34],"become":[36],"de":[38],"facto":[39],"standard":[40],"parameterization.":[43],"Taking":[44],"as":[45],"basis":[47],"MFCC":[49,153],"computation":[50],"scheme,":[51],"Gammatone":[53,63],"(GTCCs)":[56],"are":[57,86,125,149],"biologically":[59],"inspired":[60],"modification":[61],"employing":[62,129],"filters":[64],"with":[65,142],"equivalent":[66],"rectangular":[67],"bandwidth":[68],"bands.":[69],"this":[71],"letter,":[72],"GTCCs,":[74],"which":[75],"been":[77],"previously":[78],"employed":[79],"in":[80,154],"field":[82],"speech":[84],"research,":[85],"adapted":[87],"purposes.":[92],"Their":[93],"performance":[94],"is":[95],"evaluated":[96],"on":[97],"two":[98,111],"corpora":[100],"4":[102],"h":[103],"each":[104],"(general":[105],"sounds":[106],"scenes),":[109],"following":[110],"cross-validation":[112],"schemes":[113],"four":[115],"machine":[116],"learning":[117],"methods.":[118],"According":[119],"results,":[122],"accuracies":[124],"significantly":[126],"higher":[127],"when":[128],"GTCC":[130,148],"rather":[131],"than":[132,152],"other":[133],"state-of-the-art":[134],"features.":[136],"As":[137],"detailed":[139],"analysis":[140],"shows,":[141],"similar":[144],"computational":[145],"cost,":[146],"more":[150],"effective":[151],"representing":[155],"spectral":[157],"characteristics":[158],"signals,":[162],"especially":[163],"at":[164],"low":[165],"frequencies.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":20},{"year":2024,"cited_by_count":34},{"year":2023,"cited_by_count":40},{"year":2022,"cited_by_count":29},{"year":2021,"cited_by_count":31},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":23},{"year":2018,"cited_by_count":16},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}