{"id":"https://openalex.org/W1966522704","doi":"https://doi.org/10.1109/ijcnn.2014.6889669","title":"Audio onset detection: A wavelet packet based approach with recurrent neural networks","display_name":"Audio onset detection: A wavelet packet based approach with recurrent neural networks","publication_year":2014,"publication_date":"2014-07-01","ids":{"openalex":"https://openalex.org/W1966522704","doi":"https://doi.org/10.1109/ijcnn.2014.6889669","mag":"1966522704"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn.2014.6889669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","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/A5009327522","display_name":"Erik Marchi","orcid":"https://orcid.org/0000-0002-5335-6356"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Erik Marchi","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210094487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013662216","display_name":"Giacomo Ferroni","orcid":null},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giacomo Ferroni","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Italy","Dept. of Inf. Eng., Univ. Politec. delle Marche, Marche, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Italy","institution_ids":["https://openalex.org/I122534668"]},{"raw_affiliation_string":"Dept. of Inf. Eng., Univ. Politec. delle Marche, Marche, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023264395","display_name":"Florian Eyben","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Eyben","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210094487"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034253968","display_name":"Stefano Squartini","orcid":"https://orcid.org/0000-0001-9374-0128"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Stefano Squartini","raw_affiliation_strings":["Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Italy","Dept. of Inf. Eng., Univ. Politec. delle Marche, Marche, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e0 Politecnica delle Marche, Italy","institution_ids":["https://openalex.org/I122534668"]},{"raw_affiliation_string":"Dept. of Inf. Eng., Univ. Politec. delle Marche, Marche, Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043060302","display_name":"Bj\u00f6rn W. Schuller","orcid":"https://orcid.org/0000-0002-6478-8699"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]},{"id":"https://openalex.org/I4210094487","display_name":"Intel (Germany)","ror":"https://ror.org/00m2x0g47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210094487"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bjorn Schuller","raw_affiliation_strings":["Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany"],"affiliations":[{"raw_affiliation_string":"Machine Intelligence & Signal Processing Group, Technische Universit\u00e4t M\u00fcnchen, Germany","institution_ids":["https://openalex.org/I62916508"]},{"raw_affiliation_string":"Machine Intell. & Signal Process. Group, Tech. Univ. Munchen, Mu\u0308nchen, Germany","institution_ids":["https://openalex.org/I62916508","https://openalex.org/I4210094487"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5009327522"],"corresponding_institution_ids":["https://openalex.org/I4210094487","https://openalex.org/I62916508"],"apc_list":null,"apc_paid":null,"fwci":2.0379,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.86481481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"18","issue":null,"first_page":"3585","last_page":"3591"},"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":0.9987999796867371,"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":0.9868000149726868,"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":0.8117153644561768},{"id":"https://openalex.org/keywords/wavelet-packet-decomposition","display_name":"Wavelet packet decomposition","score":0.7520947456359863},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6591699123382568},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.5982383489608765},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5938827991485596},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5890553593635559},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49475711584091187},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.49070537090301514},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4874763488769531},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4791635572910309},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.4677325189113617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46636781096458435},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.44565677642822266},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09767323732376099},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.09308302402496338}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8117153644561768},{"id":"https://openalex.org/C155777637","wikidata":"https://www.wikidata.org/wiki/Q2736187","display_name":"Wavelet packet decomposition","level":4,"score":0.7520947456359863},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6591699123382568},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.5982383489608765},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5938827991485596},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5890553593635559},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49475711584091187},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.49070537090301514},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4874763488769531},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4791635572910309},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.4677325189113617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46636781096458435},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.44565677642822266},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09767323732376099},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.09308302402496338},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ijcnn.2014.6889669","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn.2014.6889669","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:iris.univpm.it:11566/153905","is_oa":false,"landing_page_url":"http://hdl.handle.net/11566/153905","pdf_url":null,"source":{"id":"https://openalex.org/S4306402571","display_name":"Universit\u00e0 Politecnica delle Marche (Universit\u00e0 Politecnica delle Marche)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I122534668","host_organization_name":"Marche Polytechnic University","host_organization_lineage":["https://openalex.org/I122534668"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:uni-augsburg.opus-bayern.de:72544","is_oa":false,"landing_page_url":"https://nbn-resolving.org/urn:nbn:de:bvb:384-opus4-725449","pdf_url":null,"source":{"id":"https://openalex.org/S4306400930","display_name":"OPUS (Augsburg University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I119916105","host_organization_name":"Augsburg University","host_organization_lineage":["https://openalex.org/I119916105"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"bookpart"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8899999856948853,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1598214593","https://openalex.org/W1899504021","https://openalex.org/W1990190154","https://openalex.org/W1991460008","https://openalex.org/W2038613237","https://openalex.org/W2040870580","https://openalex.org/W2048060899","https://openalex.org/W2056280078","https://openalex.org/W2064675550","https://openalex.org/W2079985975","https://openalex.org/W2090438737","https://openalex.org/W2098580349","https://openalex.org/W2103527825","https://openalex.org/W2103727353","https://openalex.org/W2110485445","https://openalex.org/W2114537739","https://openalex.org/W2120132744","https://openalex.org/W2131963441","https://openalex.org/W2133824856","https://openalex.org/W2139238328","https://openalex.org/W2140304104","https://openalex.org/W2142967796","https://openalex.org/W2144499799","https://openalex.org/W2148770797","https://openalex.org/W2152429995","https://openalex.org/W2159433418","https://openalex.org/W2167854178","https://openalex.org/W2293202270","https://openalex.org/W2397818963","https://openalex.org/W2402539476","https://openalex.org/W3113172960","https://openalex.org/W3139750691","https://openalex.org/W3142760365","https://openalex.org/W3148843594","https://openalex.org/W4254816979","https://openalex.org/W4297068979","https://openalex.org/W6635681657","https://openalex.org/W6674927801","https://openalex.org/W6697171384","https://openalex.org/W6713054120"],"related_works":["https://openalex.org/W4245508182","https://openalex.org/W4233511069","https://openalex.org/W2046633342","https://openalex.org/W2370050053","https://openalex.org/W2372936409","https://openalex.org/W53954450","https://openalex.org/W2365287829","https://openalex.org/W2389645710","https://openalex.org/W2379553594","https://openalex.org/W2351059076"],"abstract_inverted_index":{"This":[0],"paper":[1],"concerns":[2],"the":[3,44,50,56,69,74,78,110,147],"exploitation":[4],"of":[5,49,77,91,124,135,161],"multi-resolution":[6,70],"time-frequency":[7],"features":[8],"via":[9],"Wavelet":[10,21],"Packet":[11,22],"Transform":[12],"to":[13,101,117,120],"improve":[14],"audio":[15,79],"onset":[16,92,98,111,149,168],"detection.":[17],"In":[18],"our":[19,105,154],"approach,":[20],"Energy":[23],"Coefficients":[24],"(WPEC)":[25],"and":[26,97,114,133,139],"Auditory":[27],"Spectral":[28],"Features":[29],"(ASF)":[30],"are":[31],"processed":[32],"by":[33,73],"Bidirectional":[34],"Long":[35],"Short-Term":[36],"Memory":[37],"(BLSTM)":[38],"recurrent":[39,136],"neural":[40,83,137],"network":[41,84],"that":[42,65,153],"yields":[43],"onsets":[45],"location.":[46],"The":[47,82],"combination":[48],"two":[51],"feature":[52],"sets,":[53],"together":[54],"with":[55,87,130,143],"BLSTM":[57],"based":[58],"detector,":[59],"form":[60],"an":[61],"advanced":[62],"energy-based":[63],"approach":[64,106,155],"takes":[66],"advantage":[67],"from":[68],"analysis":[71],"given":[72],"wavelet":[75],"decomposition":[76],"input":[80],"signal.":[81],"is":[85],"trained":[86],"a":[88,121,128],"large":[89],"database":[90],"data":[93],"covering":[94],"various":[95],"genres":[96,166],"types.":[99],"Due":[100],"its":[102,115],"data-driven":[103],"nature,":[104],"does":[107],"not":[108],"require":[109],"detection":[112],"method":[113],"parameters":[116],"be":[118],"tuned":[119],"particular":[122],"type":[123,169],"music.":[125],"We":[126,151],"show":[127],"comparison":[129],"other":[131],"types":[132],"sizes":[134],"networks":[138],"we":[140],"compare":[141],"results":[142],"state-of-the-art":[144],"methods":[145],"on":[146],"whole":[148],"dataset.":[150],"conclude":[152],"significantly":[156],"increase":[157],"performance":[158],"in":[159],"terms":[160],"F-measure":[162],"without":[163],"any":[164],"music":[165],"or":[167],"constraints.":[170]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}