{"id":"https://openalex.org/W2547681274","doi":"https://doi.org/10.1109/icacci.2016.7732432","title":"Minimally supervised sound event detection using a neural network","display_name":"Minimally supervised sound event detection using a neural network","publication_year":2016,"publication_date":"2016-09-01","ids":{"openalex":"https://openalex.org/W2547681274","doi":"https://doi.org/10.1109/icacci.2016.7732432","mag":"2547681274"},"language":"en","primary_location":{"id":"doi:10.1109/icacci.2016.7732432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2016.7732432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","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/A5068033542","display_name":"Aditya Agarwal","orcid":"https://orcid.org/0000-0002-1141-0991"},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Aditya Agarwal","raw_affiliation_strings":["Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011715845","display_name":"Syed Munawwar Quadri","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Syed Munawwar Quadri","raw_affiliation_strings":["Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084244030","display_name":"Savitha Murthy","orcid":"https://orcid.org/0000-0001-7560-0420"},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Savitha Murthy","raw_affiliation_strings":["Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India","institution_ids":["https://openalex.org/I196608512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008942513","display_name":"Dinkar Sitaram","orcid":null},"institutions":[{"id":"https://openalex.org/I196608512","display_name":"PES University","ror":"https://ror.org/05m169e78","country_code":"IN","type":"education","lineage":["https://openalex.org/I196608512"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dinkar Sitaram","raw_affiliation_strings":["Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Cloud Computing and Big Data Computer Science Department PES University, Bangalore, India","institution_ids":["https://openalex.org/I196608512"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I196608512"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2495","last_page":"2500"},"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":0.9998000264167786,"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":0.9905999898910522,"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":0.7623684406280518},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7326444983482361},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6677344441413879},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.651793897151947},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6344413757324219},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5987436771392822},{"id":"https://openalex.org/keywords/non-negative-matrix-factorization","display_name":"Non-negative matrix factorization","score":0.5674933195114136},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5654383897781372},{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.5416096448898315},{"id":"https://openalex.org/keywords/polyphony","display_name":"Polyphony","score":0.5053587555885315},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5002760887145996},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44862180948257446},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4371872544288635},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4371034801006317},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3251914978027344},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.08526772260665894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7623684406280518},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7326444983482361},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6677344441413879},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.651793897151947},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6344413757324219},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5987436771392822},{"id":"https://openalex.org/C152671427","wikidata":"https://www.wikidata.org/wiki/Q10843505","display_name":"Non-negative matrix factorization","level":4,"score":0.5674933195114136},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5654383897781372},{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.5416096448898315},{"id":"https://openalex.org/C128979739","wikidata":"https://www.wikidata.org/wiki/Q179465","display_name":"Polyphony","level":2,"score":0.5053587555885315},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5002760887145996},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44862180948257446},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4371872544288635},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4371034801006317},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3251914978027344},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.08526772260665894},{"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/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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icacci.2016.7732432","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icacci.2016.7732432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI)","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":16,"referenced_works":["https://openalex.org/W1533561824","https://openalex.org/W1605026219","https://openalex.org/W1650531274","https://openalex.org/W1981755271","https://openalex.org/W2034215399","https://openalex.org/W2038484192","https://openalex.org/W2090777335","https://openalex.org/W2095640719","https://openalex.org/W2099242680","https://openalex.org/W2123843894","https://openalex.org/W2235761953","https://openalex.org/W2331166300","https://openalex.org/W2384495648","https://openalex.org/W2398456099","https://openalex.org/W6632323398","https://openalex.org/W6672893027"],"related_works":["https://openalex.org/W4390394189","https://openalex.org/W2037504162","https://openalex.org/W2539013788","https://openalex.org/W2792706544","https://openalex.org/W1568451138","https://openalex.org/W2156699640","https://openalex.org/W2045265907","https://openalex.org/W2972997031","https://openalex.org/W34555840","https://openalex.org/W2146544734"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,12,31,37,136],"sound":[4,95,138],"event":[5],"detection":[6,113,139],"system":[7,29,102,123],"that":[8,41],"is":[9,42,103,124],"trained":[10],"using":[11,44,65,72,97],"minimally":[13],"annotated":[14],"data":[15,129],"set":[16],"of":[17,25,109,121],"single":[18,38],"sounds":[19,69,90,133],"to":[20,60,82,105,125,135],"identify":[21],"and":[22,77,112,130],"separate":[23],"components":[24],"polyphonic":[26],"sounds.":[27,86],"The":[28,118],"uses":[30],"Feed":[32],"Forward":[33],"Neural":[34],"Network":[35],"with":[36,114],"hidden":[39],"layer":[40],"pre-trained":[43],"an":[45],"autoencoder.":[46],"Single":[47],"sounds,":[48],"represented":[49],"as":[50],"Mel":[51],"Frequency":[52],"Cepstral":[53],"Coefficient":[54],"(MFCC)":[55],"feature":[56],"vectors,":[57],"are":[58,70,91],"used":[59],"train":[61],"the":[62,98],"neural":[63],"network":[64],"back":[66],"propagation.":[67],"Polyphonic":[68],"pre-processed":[71],"Principal":[73],"Component":[74],"Analysis":[75],"(PCA)":[76],"Nonnegative":[78],"Matrix":[79],"Factorization":[80],"(NMF)":[81],"obtain":[83],"source":[84,88,110],"separated":[85,89],"These":[87],"then":[92],"tested":[93],"for":[94],"classification":[96],"feed-forward":[99],"algorithm.":[100],"Our":[101],"able":[104],"achieve":[106],"reasonable":[107],"accuracy":[108],"separation":[111],"minimal":[115,128],"training":[116],"set.":[117],"ultimate":[119],"goal":[120],"our":[122],"bootstrap":[126],"from":[127],"learn":[131],"new":[132],"leading":[134],"better":[137],"system.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}