{"id":"https://openalex.org/W4372260200","doi":"https://doi.org/10.1109/icassp49357.2023.10096621","title":"NAS-DYMC: NAS-Based Dynamic Multi-Scale Convolutional Neural Network for Sound Event Detection","display_name":"NAS-DYMC: NAS-Based Dynamic Multi-Scale Convolutional Neural Network for Sound Event Detection","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260200","doi":"https://doi.org/10.1109/icassp49357.2023.10096621"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091181562","display_name":"Peng Yao","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Yao","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021569445","display_name":"Feng Deng","orcid":"https://orcid.org/0000-0002-1381-0243"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Deng","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033210057","display_name":"Jianchao Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianchao Tan","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088728073","display_name":"Chengru Song","orcid":null},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengru Song","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":null,"type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Kuaishou Technology,Beijing,China","Kuaishou Technology, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology,Beijing,China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Kuaishou Technology, Beijing, China","institution_ids":["https://openalex.org/I4401726859"]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4401726859"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"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":0.996399998664856,"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":0.9866999983787537,"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/convolution","display_name":"Convolution (computer science)","score":0.7911809682846069},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7808754444122314},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7574195861816406},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6430005431175232},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5013303756713867},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4853293001651764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4642442464828491},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44027936458587646},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4281913638114929},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3425951600074768},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09244173765182495}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7911809682846069},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7808754444122314},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7574195861816406},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6430005431175232},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5013303756713867},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4853293001651764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4642442464828491},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44027936458587646},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4281913638114929},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3425951600074768},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09244173765182495},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096621","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096621","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1844944916","https://openalex.org/W2126105956","https://openalex.org/W2306394264","https://openalex.org/W2526050071","https://openalex.org/W2591013610","https://openalex.org/W2746554716","https://openalex.org/W2791956393","https://openalex.org/W2798350598","https://openalex.org/W2922509574","https://openalex.org/W2953604046","https://openalex.org/W3179917056","https://openalex.org/W3203468141","https://openalex.org/W4221149441","https://openalex.org/W4224932888","https://openalex.org/W4225331914","https://openalex.org/W4294620492","https://openalex.org/W6698169118","https://openalex.org/W6749158954","https://openalex.org/W6798556726"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4321487865","https://openalex.org/W4313906399","https://openalex.org/W4391266461","https://openalex.org/W2590798552","https://openalex.org/W2811106690","https://openalex.org/W4239306820","https://openalex.org/W2947043951","https://openalex.org/W4312417841","https://openalex.org/W2964954556"],"abstract_inverted_index":{"CNN+RNN":[0],"models":[1],"have":[2],"become":[3],"the":[4,13,27,30,53,80,93,117,122,132,140],"mainstream":[5],"approach":[6],"for":[7,131],"semi-supervised":[8],"sound":[9,83],"event":[10],"detection,":[11],"and":[12,89],"CNN":[14],"part":[15],"is":[16,37,113],"mainly":[17],"a":[18,61,70,107],"stack":[19],"of":[20,29,38,56,82,96,126,142],"several":[21],"2D":[22,35],"convolutional":[23,65],"layers":[24],"to":[25,51,68,115],"capture":[26,79],"representations":[28],"time-frequency":[31,87],"features.":[32],"However,":[33],"conventional":[34,97],"convolution":[36,77,91,98],"limited":[39],"ability":[40,55],"in":[41],"capturing":[42],"detailed":[43],"information":[44],"about":[45],"acoustic":[46,73],"events.":[47],"In":[48],"this":[49],"paper,":[50],"enhance":[52],"representation":[54,94],"CNN,":[57],"we":[58],"propose":[59],"NAS-DYMC,":[60],"NAS-based":[62],"dynamic":[63,90,128],"multi-scale":[64,76,129],"neural":[66,108],"network":[67,119],"extract":[69],"more":[71],"effective":[72],"representation.":[74],"Specifically,":[75],"can":[78],"characteristics":[81],"events":[84],"with":[85],"different":[86],"distributions":[88],"enhances":[92],"capability":[95],"by":[99],"adapting":[100],"attention":[101],"weights":[102],"onto":[103],"basis":[104],"kernels.":[105],"Furthermore,":[106],"architecture":[109,120],"search":[110,123],"(NAS)":[111],"method":[112],"adopted":[114],"find":[116],"optimal":[118],"from":[121],"space":[124],"consisting":[125],"various":[127],"convolutions":[130],"DCASE":[133],"2021":[134],"Task4":[135],"dataset.":[136],"Experimental":[137],"results":[138],"demonstrate":[139],"superiority":[141],"our":[143],"proposed":[144],"method.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}