{"id":"https://openalex.org/W2567461233","doi":"https://doi.org/10.1109/icassp.2017.7952907","title":"Adaptive DCTNet for audio signal classification","display_name":"Adaptive DCTNet for audio signal classification","publication_year":2017,"publication_date":"2017-03-01","ids":{"openalex":"https://openalex.org/W2567461233","doi":"https://doi.org/10.1109/icassp.2017.7952907","mag":"2567461233"},"language":"en","primary_location":{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1612.04028","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080949748","display_name":"Yin Xian","orcid":"https://orcid.org/0000-0002-3985-1836"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"funder","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yin Xian","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023417820","display_name":"Yunchen Pu","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"funder","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunchen Pu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066666034","display_name":"Zhe Gan","orcid":null},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"funder","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhe Gan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101607148","display_name":"Liang Lu","orcid":"https://orcid.org/0000-0003-4005-679X"},"institutions":[{"id":"https://openalex.org/I160992636","display_name":"Toyota Technological Institute at Chicago","ror":"https://ror.org/02sn5gb64","country_code":"US","type":"education","lineage":["https://openalex.org/I160992636"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liang Lu","raw_affiliation_strings":["Toyota Technological Institute at Chicago, Chicago, IL, USA"],"affiliations":[{"raw_affiliation_string":"Toyota Technological Institute at Chicago, Chicago, IL, USA","institution_ids":["https://openalex.org/I160992636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101752265","display_name":"Andrew Thompson","orcid":"https://orcid.org/0000-0002-4580-0357"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"funder","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Andrew Thompson","raw_affiliation_strings":["Mathematical Institute, University of Oxford, Oxford, UK"],"affiliations":[{"raw_affiliation_string":"Mathematical Institute, University of Oxford, Oxford, UK","institution_ids":["https://openalex.org/I40120149"]}]}],"institution_assertions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.297,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":7,"citation_normalized_percentile":{"value":0.789812,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":82,"max":83},"biblio":{"volume":"3361","issue":null,"first_page":"3999","last_page":"4003"},"is_retracted":false,"is_paratext":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":0.9993,"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":0.9955,"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/signal","display_name":"SIGNAL (programming language)","score":0.58487517},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5212805},{"id":"https://openalex.org/keywords/identification","display_name":"Identification","score":0.4211749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.73470247},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.69580454},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.6710042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.64339405},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.58487517},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.57910264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5728077},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.54622453},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5212805},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.513536},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.4674011},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43835244},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4211749},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.20275733},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.16752315},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15345562},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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":3,"locations":[{"is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2017.7952907","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1612.04028","pdf_url":"https://arxiv.org/pdf/1612.04028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},{"is_oa":false,"landing_page_url":"http://arxiv.org/abs/1612.04028","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/1612.04028","pdf_url":"https://arxiv.org/pdf/1612.04028","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":25,"referenced_works":["https://openalex.org/W1538131130","https://openalex.org/W1570009578","https://openalex.org/W1605417594","https://openalex.org/W1606347560","https://openalex.org/W1832115024","https://openalex.org/W1865351371","https://openalex.org/W1969851134","https://openalex.org/W1994906459","https://openalex.org/W1996021349","https://openalex.org/W2040622050","https://openalex.org/W2064675550","https://openalex.org/W2076608692","https://openalex.org/W2093231248","https://openalex.org/W2098477387","https://openalex.org/W2103869314","https://openalex.org/W2107789863","https://openalex.org/W2109816922","https://openalex.org/W2148154194","https://openalex.org/W2157331557","https://openalex.org/W2159254954","https://openalex.org/W2160815625","https://openalex.org/W2188563164","https://openalex.org/W2345511019","https://openalex.org/W3102431071","https://openalex.org/W3102503590"],"related_works":["https://openalex.org/W4316036082","https://openalex.org/W3097613282","https://openalex.org/W3090190000","https://openalex.org/W2970176078","https://openalex.org/W2905220255","https://openalex.org/W2890436937","https://openalex.org/W2289868279","https://openalex.org/W1927135183","https://openalex.org/W1820289435","https://openalex.org/W1596300871"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"DCTNet":[5,27],"for":[6,29,91],"audio":[7,30,72],"signal":[8,125],"classification.":[9],"Its":[10],"output":[11],"feature":[12,32],"is":[13,52,68],"related":[14],"to":[15,54,70,124],"Cohen's":[16],"class":[17],"of":[18,25,39,46],"time-frequency":[19],"distributions.":[20],"We":[21,82],"introduce":[22],"the":[23,37,87,97],"use":[24,83],"adaptive":[26,53],"(A-DCTNet)":[28],"signals":[31],"extraction.":[33],"The":[34,50],"A-DCTNet":[35,51,88,98],"applies":[36],"idea":[38],"constant-Q":[40],"transform,":[41],"with":[42],"its":[43],"center":[44],"frequencies":[45],"filterbanks":[47],"geometrically":[48],"spaced.":[49],"different":[55],"acoustic":[56,65],"scales,":[57],"and":[58,99,112],"it":[59],"can":[60],"better":[61],"capture":[62],"low":[63],"frequency":[64],"information":[66],"that":[67,96],"sensitive":[69],"human":[71],"perception":[73],"than":[74],"features":[75,84],"such":[76],"as":[77,89],"Mel-frequency":[78],"spectral":[79],"coefficients":[80],"(MFSC).":[81],"extracted":[85],"by":[86],"input":[90],"classifiers.":[92],"Experimental":[93],"results":[94],"show":[95],"Recurrent":[100],"Neural":[101],"Networks":[102],"(RNN)":[103],"achieve":[104],"state-of-the-art":[105],"performance":[106],"in":[107,117],"bird":[108],"song":[109],"classification":[110],"rate,":[111],"improve":[113],"artist":[114],"identification":[115],"accuracy":[116],"music":[118],"data.":[119],"They":[120],"demonstrate":[121],"A-DCTNet's":[122],"applicability":[123],"processing":[126],"problems.":[127]},"abstract_inverted_index_v3":null,"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W2567461233","counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-04-21T06:36:35.475849","created_date":"2017-01-06"}