{"id":"https://openalex.org/W3017333212","doi":"https://doi.org/10.1109/icaiic48513.2020.9064985","title":"Waveform-based End-to-end Deep Convolutional Neural Network with Multi-scale Sliding Windows for Weakly Labeled Sound Event Detection","display_name":"Waveform-based End-to-end Deep Convolutional Neural Network with Multi-scale Sliding Windows for Weakly Labeled Sound Event Detection","publication_year":2020,"publication_date":"2020-02-01","ids":{"openalex":"https://openalex.org/W3017333212","doi":"https://doi.org/10.1109/icaiic48513.2020.9064985","mag":"3017333212"},"language":"en","primary_location":{"id":"doi:10.1109/icaiic48513.2020.9064985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic48513.2020.9064985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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/A5062101749","display_name":"Seokjin Lee","orcid":"https://orcid.org/0000-0001-8220-192X"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokjin Lee","raw_affiliation_strings":["School of Electronics Engineering, Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5041153116","display_name":"Minhan Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Minhan Kim","raw_affiliation_strings":["School of Electronics Engineering, Kyungpook National University, Daegu, Republic of Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronics Engineering, Kyungpook National University, Daegu, Republic of Korea","institution_ids":["https://openalex.org/I31419693"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":null,"apc_paid":null,"fwci":0.3041,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.52299263,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"182","last_page":"186"},"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":0.9994999766349792,"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":0.9912999868392944,"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":0.7279752492904663},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7269853353500366},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6379812955856323},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6027073264122009},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5925572514533997},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5830299258232117},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5632421374320984},{"id":"https://openalex.org/keywords/thresholding","display_name":"Thresholding","score":0.47180691361427307},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4654600918292999},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4479786157608032},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4176775813102722},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.34347397089004517},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1149144172668457}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7279752492904663},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7269853353500366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6379812955856323},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6027073264122009},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5925572514533997},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5830299258232117},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5632421374320984},{"id":"https://openalex.org/C191178318","wikidata":"https://www.wikidata.org/wiki/Q2256906","display_name":"Thresholding","level":3,"score":0.47180691361427307},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4654600918292999},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4479786157608032},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4176775813102722},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.34347397089004517},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1149144172668457},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaiic48513.2020.9064985","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaiic48513.2020.9064985","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","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":14,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1650531274","https://openalex.org/W2048174296","https://openalex.org/W2103235956","https://openalex.org/W2137561966","https://openalex.org/W2194775991","https://openalex.org/W2342840547","https://openalex.org/W2509065397","https://openalex.org/W2794150026","https://openalex.org/W2884585870","https://openalex.org/W2889467522","https://openalex.org/W2936774411","https://openalex.org/W2964121744","https://openalex.org/W3098357269"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"In":[0,133],"this":[1],"paper,":[2],"a":[3,17,96,115,190],"waveform-based":[4],"end-to-end":[5,39,59],"sound":[6,14,62,130],"event":[7,63],"detection":[8,64],"algorithm":[9,188],"that":[10,80,185],"detects":[11],"and":[12,78,84,127,155,181,209],"classifies":[13],"events":[15],"using":[16,144,160],"deep":[18],"convolutional":[19,67,111],"neural":[20,68,112],"network":[21,102],"architecture":[22,60],"is":[23,150],"proposed.":[24],"While":[25],"most":[26],"machine-learning-based":[27],"acoustic":[28],"signal":[29,86],"processing":[30],"systems":[31],"utilize":[32,42],"hand-crafted":[33],"feature":[34],"vectors":[35],"e.g.":[36],"log-Mel":[37],"spectrogram,":[38],"methods,":[40],"which":[41],"raw":[43],"input":[44],"data,":[45,138],"have":[46],"recently":[47],"been":[48],"investigated":[49],"for":[50,61,103,196,203,211],"use":[51],"in":[52],"various":[53],"applications.":[54],"Therefore,":[55],"we":[56],"develop":[57],"an":[58],"tasks":[65],"with":[66,114,173],"networks.":[69],"The":[70,100,119],"proposed":[71,168,187],"model":[72],"consists":[73,107],"of":[74,108,121,194],"multi-scale":[75],"time":[76,105],"frames":[77],"networks":[79,113,124,141],"handle":[81,136],"both":[82],"short":[83],"long":[85],"characteristics;":[87],"the":[88,122,139,145,156,182,186,197,204,212],"frame":[89,106],"slides":[90],"by":[91,129],"0.1":[92],"second":[93],"to":[94,135],"provide":[95],"sufficiently":[97],"fine":[98],"resolution.":[99],"element":[101,123],"each":[104],"several":[109],"one-dimensional":[110],"deeply":[116],"stacked":[117],"structure.":[118],"results":[120,157,183],"are":[125,142,158,171],"averaged":[126],"gated":[128],"activity":[131],"detection.":[132],"order":[134],"unlabeled":[137],"trained":[140],"enhanced":[143,159],"mean-teacher":[146],"model.":[147],"A":[148],"decision":[149],"made":[151],"via":[152],"double":[153],"thresholding,":[154],"class-wise":[161],"minimum":[162],"gap/length":[163],"compensation.":[164],"To":[165],"evaluate":[166],"our":[167],"approach,":[169],"simulations":[170],"performed":[172],"development":[174,200],"data":[175],"from":[176],"DCASE":[177,198,205,213],"2019":[178,199,214],"Task":[179],"4,":[180],"show":[184],"had":[189],"macro-averaged":[191],"F1":[192],"score":[193],"31.7%":[195],"dataset,":[201,208],"30.2%":[202],"2018":[206],"evaluation":[207,215],"26.7%":[210],"dataset.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}