{"id":"https://openalex.org/W3212264559","doi":"https://doi.org/10.1109/icccnt51525.2021.9579677","title":"Polyphonic Sound Event Detection and Classification using Convolutional Recurrent Neural Network with Mean Teacher","display_name":"Polyphonic Sound Event Detection and Classification using Convolutional Recurrent Neural Network with Mean Teacher","publication_year":2021,"publication_date":"2021-07-06","ids":{"openalex":"https://openalex.org/W3212264559","doi":"https://doi.org/10.1109/icccnt51525.2021.9579677","mag":"3212264559"},"language":"en","primary_location":{"id":"doi:10.1109/icccnt51525.2021.9579677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt51525.2021.9579677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)","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/A5024439452","display_name":"Uday Singh","orcid":null},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Uday Singh","raw_affiliation_strings":["SRM Institute of Science and Technology, Kattankulathur, India"],"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology, Kattankulathur, India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011561331","display_name":"Dibya Debayan Dash","orcid":null},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dibya Debayan Dash","raw_affiliation_strings":["SRM Institute of Science and Technology, Kattankulathur, India"],"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology, Kattankulathur, India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042908738","display_name":"Manas Sharma","orcid":"https://orcid.org/0000-0003-0947-1282"},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Manas Sharma","raw_affiliation_strings":["SRM Institute of Science and Technology, Kattankulathur, India"],"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology, Kattankulathur, India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006947752","display_name":"Sarthak Mishra","orcid":"https://orcid.org/0000-0002-6613-0997"},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sarthak Mishra","raw_affiliation_strings":["SRM Institute of Science and Technology, Kattankulathur, India"],"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology, Kattankulathur, India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085534994","display_name":"S. Malarvizhi","orcid":"https://orcid.org/0000-0002-0794-3170"},"institutions":[{"id":"https://openalex.org/I145286018","display_name":"SRM Institute of Science and Technology","ror":"https://ror.org/050113w36","country_code":"IN","type":"education","lineage":["https://openalex.org/I145286018"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"S. Malarvizhi","raw_affiliation_strings":["SRM Institute of Science and Technology, Kattankulathur, India"],"affiliations":[{"raw_affiliation_string":"SRM Institute of Science and Technology, Kattankulathur, India","institution_ids":["https://openalex.org/I145286018"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082694737","display_name":"Sourabh Tiwari","orcid":"https://orcid.org/0000-0001-7641-2149"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sourabh Tiwari","raw_affiliation_strings":["Samsung R&D Institute, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063903476","display_name":"Rashmi T Shankarappa","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rashmi T Shankarappa","raw_affiliation_strings":["Samsung R&D Institute, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute, Bangalore, India","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5024439452"],"corresponding_institution_ids":["https://openalex.org/I145286018"],"apc_list":null,"apc_paid":null,"fwci":0.6094,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67768763,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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":0.9990000128746033,"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":0.991100013256073,"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/spectrogram","display_name":"Spectrogram","score":0.8470813035964966},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6479426622390747},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6191965341567993},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5313730239868164},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5293213725090027},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.49242958426475525},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.4754697382450104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46568360924720764},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46461427211761475},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4618804156780243},{"id":"https://openalex.org/keywords/f1-score","display_name":"F1 score","score":0.43762117624282837},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4212481677532196},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4192691743373871},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07627928256988525}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8470813035964966},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6479426622390747},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6191965341567993},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5313730239868164},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5293213725090027},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.49242958426475525},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.4754697382450104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46568360924720764},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46461427211761475},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4618804156780243},{"id":"https://openalex.org/C148524875","wikidata":"https://www.wikidata.org/wiki/Q6975395","display_name":"F1 score","level":2,"score":0.43762117624282837},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4212481677532196},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4192691743373871},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07627928256988525},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icccnt51525.2021.9579677","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icccnt51525.2021.9579677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1650531274","https://openalex.org/W2341412280","https://openalex.org/W2591013610","https://openalex.org/W2592691248","https://openalex.org/W2775794021","https://openalex.org/W2884011836","https://openalex.org/W2953070460","https://openalex.org/W2959539607","https://openalex.org/W2963099423","https://openalex.org/W3129056539","https://openalex.org/W4289329167","https://openalex.org/W6753516609","https://openalex.org/W6790417576"],"related_works":["https://openalex.org/W2411659965","https://openalex.org/W2387677326","https://openalex.org/W4200063482","https://openalex.org/W2357575019","https://openalex.org/W2370117122","https://openalex.org/W2530685530","https://openalex.org/W2360603947","https://openalex.org/W4375868962","https://openalex.org/W2371528275","https://openalex.org/W2375454309"],"abstract_inverted_index":{"Polyphonic":[0],"sound":[1,52],"event":[2],"detection":[3],"(SED)":[4],"is":[5,54,77,112,124,137,163],"research":[6],"field":[7],"which":[8,25,37,69,162],"finds":[9],"usefulness":[10],"in":[11,79],"cognitive":[12],"IoT,":[13],"security":[14],"systems,":[15],"voice":[16],"assistants":[17],"etc.":[18],"This":[19],"paper":[20],"proposes":[21],"a":[22],"SED":[23,83,110,149],"system,":[24],"makes":[26],"use":[27],"of":[28,45,82,159],"semi":[29],"supervised":[30],"mean":[31,95,154],"teacher":[32,96,155],"approach,":[33],"for":[34],"DESED":[35,119],"dataset,":[36],"has":[38],"confined":[39],"strongly":[40],"classified":[41,103],"data,":[42],"and":[43,48,104],"plethora":[44],"weakly":[46,102],"labeled":[47],"unlabeled":[49,105],"data.":[50,107],"The":[51,108,143],"data":[53],"processed":[55],"by":[56,92,98],"extracting":[57],"the":[58,71,86,94,101,118,147],"log":[59,72],"mel":[60,73],"spectrograms.":[61],"A":[62],"convolutional":[63],"recurrent":[64],"neural":[65],"network":[66],"(CRNN)":[67],"model,":[68],"takes":[70],"spectrograms":[74],"as":[75,128,130,139],"input,":[76],"used":[78],"first":[80],"level":[81,88],"system.":[84,168],"Then,":[85],"second":[87],"updates":[89],"it":[90],"further":[91],"using":[93,153],"approach":[97,156],"learning":[99],"from":[100],"audio":[106],"proposed":[109,148],"system":[111,150],"proved":[113],"to":[114],"be":[115],"effective":[116],"on":[117],"dataset.":[120],"Overall":[121],"performance":[122,140],"assessment":[123],"made":[125],"with":[126,151],"baseline":[127,167],"well":[129],"different":[131],"top-ranked":[132],"solutions.":[133],"Event":[134],"based":[135],"F1-score":[136,158],"considered":[138],"evaluation":[141],"metric.":[142],"experiments":[144],"display":[145],"that":[146],"CRNN":[152],"achieves":[157],"around":[160],"48.3%,":[161],"significant":[164],"improvement":[165],"over":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
