{"id":"https://openalex.org/W2947151646","doi":"https://doi.org/10.1109/icdipc.2019.8723713","title":"Automatic Audio Event Recognition Schemes for Context-Aware Audio Computing Devices","display_name":"Automatic Audio Event Recognition Schemes for Context-Aware Audio Computing Devices","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2947151646","doi":"https://doi.org/10.1109/icdipc.2019.8723713","mag":"2947151646"},"language":"en","primary_location":{"id":"doi:10.1109/icdipc.2019.8723713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdipc.2019.8723713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Seventh International Conference on Digital Information Processing and Communications (ICDIPC)","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/A5112382571","display_name":"Shivam Soni","orcid":null},"institutions":[{"id":"https://openalex.org/I99729588","display_name":"Indian Institute of Technology Bhubaneswar","ror":"https://ror.org/04gx72j20","country_code":"IN","type":"education","lineage":["https://openalex.org/I99729588"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Shivam Soni","raw_affiliation_strings":["Real-time Embedded Signal Processing Lab, School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Jatani, Odisha, INDIA"],"affiliations":[{"raw_affiliation_string":"Real-time Embedded Signal Processing Lab, School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Jatani, Odisha, INDIA","institution_ids":["https://openalex.org/I99729588"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001968316","display_name":"Sudipta Dey","orcid":null},"institutions":[{"id":"https://openalex.org/I99729588","display_name":"Indian Institute of Technology Bhubaneswar","ror":"https://ror.org/04gx72j20","country_code":"IN","type":"education","lineage":["https://openalex.org/I99729588"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sudipta Dey","raw_affiliation_strings":["Real-time Embedded Signal Processing Lab, School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Jatani, Odisha, INDIA"],"affiliations":[{"raw_affiliation_string":"Real-time Embedded Signal Processing Lab, School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Jatani, Odisha, INDIA","institution_ids":["https://openalex.org/I99729588"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062664549","display_name":"M. Sabarimalai Manikandan","orcid":"https://orcid.org/0000-0001-6878-4911"},"institutions":[{"id":"https://openalex.org/I99729588","display_name":"Indian Institute of Technology Bhubaneswar","ror":"https://ror.org/04gx72j20","country_code":"IN","type":"education","lineage":["https://openalex.org/I99729588"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M. Sabarimalai Manikandan","raw_affiliation_strings":["Real-time Embedded Signal Processing Lab, School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Jatani, Odisha, INDIA"],"affiliations":[{"raw_affiliation_string":"Real-time Embedded Signal Processing Lab, School of Electrical Sciences, Indian Institute of Technology Bhubaneswar, Jatani, Odisha, INDIA","institution_ids":["https://openalex.org/I99729588"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112382571"],"corresponding_institution_ids":["https://openalex.org/I99729588"],"apc_list":null,"apc_paid":null,"fwci":0.9951,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.7575181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"23","last_page":"28"},"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":0.9976999759674072,"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":0.9860000014305115,"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":0.8207484483718872},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.7567065954208374},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6063603162765503},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5801492929458618},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.5739225745201111},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5505776405334473},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5302866101264954},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5236682295799255},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5102405548095703},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4805658161640167},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4517955780029297},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.425481915473938},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4112577438354492},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3758796453475952},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3647375702857971},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32684528827667236},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3146141767501831},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2922176420688629},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.21446752548217773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8207484483718872},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.7567065954208374},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6063603162765503},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5801492929458618},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5739225745201111},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5505776405334473},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5302866101264954},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5236682295799255},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5102405548095703},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4805658161640167},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4517955780029297},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.425481915473938},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4112577438354492},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3758796453475952},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3647375702857971},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32684528827667236},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3146141767501831},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2922176420688629},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.21446752548217773},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","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},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/icdipc.2019.8723713","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdipc.2019.8723713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 Seventh International Conference on Digital Information Processing and Communications (ICDIPC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.8399999737739563,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1978274651","https://openalex.org/W1981087263","https://openalex.org/W2116681922","https://openalex.org/W2162676242","https://openalex.org/W2170355566","https://openalex.org/W2398456099","https://openalex.org/W2487315868","https://openalex.org/W2566935005","https://openalex.org/W2591013610","https://openalex.org/W2617002574","https://openalex.org/W2761246525","https://openalex.org/W2793307691","https://openalex.org/W3100031071","https://openalex.org/W6684202924","https://openalex.org/W6712469065"],"related_works":["https://openalex.org/W2289868279","https://openalex.org/W2953493266","https://openalex.org/W2555630001","https://openalex.org/W1517805583","https://openalex.org/W2970176078","https://openalex.org/W4231351862","https://openalex.org/W4212794605","https://openalex.org/W1978274651","https://openalex.org/W1620668332","https://openalex.org/W2033602688"],"abstract_inverted_index":{"Automatic":[0],"audio":[1,19,21,49,110,129,171,202,222],"event":[2,50],"recognition":[3,51],"(AER)":[4,52],"plays":[5],"a":[6,140,194,214],"major":[7],"role":[8],"in":[9],"designing":[10],"and":[11,15,23,29,39,60,76,97,101,115,136,157,168],"building":[12],"intelligent":[13],"location":[14],"context-aware":[16],"applications":[17],"including":[18,91],"surveillance,":[20],"indexing":[22],"content":[24],"retrieval,":[25],"highlight":[26],"extraction,":[27],"drone":[28],"robotic":[30],"navigation,":[31],"machine":[32,61],"health":[33],"monitoring,":[34],"audio-aware":[35],"voice":[36],"processing":[37],"services,":[38],"urban":[40],"sound":[41,89],"pollution":[42],"monitoring.":[43],"In":[44,103],"this":[45,104],"paper,":[46],"we":[47,106],"present":[48],"schemes":[53,124,161],"using":[54,139,146],"the":[55,121,155,163,183,209,234,244],"Mel-frequency":[56],"cepstral":[57],"coefficients":[58],"(MFCC)":[59],"classifiers":[62],"such":[63],"as":[64],"multi-class":[65],"support":[66],"vectors":[67],"machines":[68],"(MC-SVM),":[69],"fully":[70],"connected":[71],"feed-forward":[72],"neural":[73,79],"networks":[74,80],"(FCFFNNs),":[75],"one-dimensional":[77],"convolutional":[78],"(1D-CNNs)":[81],"that":[82,154,233],"are":[83,125],"capable":[84],"of":[85,120,143,149,166,174,186,205,225,237],"automatically":[86],"recognizing":[87],"seven":[88],"classes":[90],"aircraft,":[92],"construction,":[93],"music,":[94],"nature":[95],"(wind":[96],"rain),":[98],"speech,":[99],"vehicle,":[100],"train.":[102],"study,":[105],"created":[107],"large":[108],"scale":[109],"database":[111],"for":[112,170,201,221],"both":[113],"training":[114],"testing":[116],"purposes.":[117],"The":[118,188,228],"performance":[119],"three":[122],"AER":[123,160,180,191,247],"evaluated":[126],"under":[127],"different":[128,147],"frame":[130,172,203,223],"sizes":[131],"(100":[132],"ms,":[133],"250":[134,175,206,226],"ms":[135,176,207],"500":[137],"ms)":[138],"wide":[141],"variety":[142],"sounds":[144],"recorded":[145],"kinds":[148],"recording":[150],"devices.":[151],"Results":[152],"show":[153,232],"FCFFNN":[156],"1D-CNN":[158,189,238],"based":[159,179,190,211,239,246],"had":[162,182,193,213],"F1-score":[164,184],"values":[165],"95.72%":[167],"96.34%":[169],"size":[173,204,224],"whereas":[177,208],"MC-SVM":[178],"scheme":[181,192,212,240],"value":[185],"85.84%.":[187],"class-wise":[195,215],"accuracy":[196,216],"is":[197,217,241],"greater":[198,218],"than":[199,219,243],"84%":[200],"FC-FFNN":[210,245],"80%":[220],"ms.":[227],"computational":[229],"analysis":[230],"results":[231],"prediction":[235],"time":[236],"faster":[242],"scheme.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-01-14T23:40:02.550235","created_date":"2025-10-10T00:00:00"}