{"id":"https://openalex.org/W4239247292","doi":"https://doi.org/10.1109/mmsp53017.2021.9733701","title":"Evaluating Spectral Magnitude Representation and Spectral Energy for Audio-based Activity Detection","display_name":"Evaluating Spectral Magnitude Representation and Spectral Energy for Audio-based Activity Detection","publication_year":2021,"publication_date":"2021-10-06","ids":{"openalex":"https://openalex.org/W4239247292","doi":"https://doi.org/10.1109/mmsp53017.2021.9733701"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp53017.2021.9733701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp53017.2021.9733701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)","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/A5007136125","display_name":"Anastasios Vafeiadis","orcid":"https://orcid.org/0000-0003-1102-5708"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Anastasios Vafeiadis","raw_affiliation_strings":["Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007384302","display_name":"Ioannis Papadimitriou","orcid":"https://orcid.org/0000-0002-1570-0419"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ioannis Papadimitriou","raw_affiliation_strings":["Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034968601","display_name":"Anastasios Papanagnou","orcid":"https://orcid.org/0000-0002-8991-7629"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Anastasis Papanagnou","raw_affiliation_strings":["Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000523843","display_name":"Dimitrios Giakoumis","orcid":"https://orcid.org/0000-0003-1844-186X"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Giakoumis","raw_affiliation_strings":["Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064307246","display_name":"Konstantinos Votis","orcid":"https://orcid.org/0000-0001-6381-8326"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Konstantinos Votis","raw_affiliation_strings":["Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087452615","display_name":"Dimitrios Tzovaras","orcid":"https://orcid.org/0000-0001-6915-6722"},"institutions":[{"id":"https://openalex.org/I4210093649","display_name":"Information Technologies Institute","ror":"https://ror.org/0069akp70","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210093649"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Dimitrios Tzovaras","raw_affiliation_strings":["Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece"],"affiliations":[{"raw_affiliation_string":"Center for Research & Technology Hellas,Information Technologies Institute,Thessaloniki,Greece","institution_ids":["https://openalex.org/I4210093649"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007136125"],"corresponding_institution_ids":["https://openalex.org/I4210093649"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20413942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9905999898910522,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.9033724069595337},{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.7746326327323914},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7460303902626038},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5964852571487427},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.551075279712677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.510513186454773},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5080986022949219},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5062023997306824},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.49753573536872864},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.46368589997291565},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.35564157366752625},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15088465809822083},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.10646677017211914}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9033724069595337},{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.7746326327323914},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7460303902626038},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5964852571487427},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.551075279712677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.510513186454773},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5080986022949219},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5062023997306824},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.49753573536872864},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.46368589997291565},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.35564157366752625},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15088465809822083},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.10646677017211914},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp53017.2021.9733701","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp53017.2021.9733701","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5699999928474426}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327859","display_name":"Hellenic Foundation for Research and Innovation","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1501987291","https://openalex.org/W1585610923","https://openalex.org/W1606768424","https://openalex.org/W1989804777","https://openalex.org/W1997888319","https://openalex.org/W2003637680","https://openalex.org/W2004099281","https://openalex.org/W2009504845","https://openalex.org/W2059732136","https://openalex.org/W2074783809","https://openalex.org/W2091746061","https://openalex.org/W2101603727","https://openalex.org/W2103151433","https://openalex.org/W2107430826","https://openalex.org/W2191779130","https://openalex.org/W2290243020","https://openalex.org/W2343758848","https://openalex.org/W2509065397","https://openalex.org/W2570915410","https://openalex.org/W2728972335","https://openalex.org/W2729018917","https://openalex.org/W2766087987","https://openalex.org/W2775794021","https://openalex.org/W2883618873","https://openalex.org/W2936721683","https://openalex.org/W2955425717","https://openalex.org/W2963041956","https://openalex.org/W2979507862","https://openalex.org/W2990614474","https://openalex.org/W3003257820","https://openalex.org/W3024840775","https://openalex.org/W3036237438","https://openalex.org/W3090169026","https://openalex.org/W3096725570","https://openalex.org/W3098357269","https://openalex.org/W4234816175","https://openalex.org/W4287198224","https://openalex.org/W6753158756","https://openalex.org/W6762718338","https://openalex.org/W6779574021","https://openalex.org/W6794778545"],"related_works":["https://openalex.org/W2120540196","https://openalex.org/W3095343173","https://openalex.org/W2381036744","https://openalex.org/W2288135719","https://openalex.org/W2323749021","https://openalex.org/W2533590149","https://openalex.org/W2901989338","https://openalex.org/W82005754","https://openalex.org/W2334448276","https://openalex.org/W3034641760"],"abstract_inverted_index":{"Acoustics":[0],"has":[1],"received":[2],"a":[3,23,30,80,91,137,177,186],"great":[4],"research":[5],"interest":[6],"for":[7,180],"human":[8],"activity":[9,43],"detection":[10,44,181],"in":[11,29,86,185],"indoor":[12],"and":[13,65,84,112,128,134,155,169],"outdoor":[14],"environments.":[15],"Compared":[16],"to":[17,59],"vision-based":[18],"approaches,":[19],"microphones":[20],"can":[21,45,78],"achieve":[22,79],"high":[24,81],"percentage":[25],"of":[26,32,98,145,182],"recognition":[27,82,194],"accuracy":[28,83,195],"variety":[31],"activities,":[33],"while":[34,151],"not":[35,57],"being":[36],"affected":[37],"by":[38,198],"lighting":[39],"conditions.":[40],"Furthermore,":[41],"audio-based":[42],"be":[46],"considered":[47],"an":[48],"unobtrusive":[49],"method,":[50],"as":[51,53],"long":[52],"the":[54,73,99,113,121,126,129,152,156,163,167,170,191,199],"data":[55,67],"is":[56,68,90,196],"related":[58],"speech":[60],"or":[61],"other":[62],"sensitive":[63],"information":[64],"no":[66],"sent":[69],"on":[70,108,136,176],"cloud.":[71],"Selecting":[72],"appropriate":[74],"audio":[75,119],"features":[76],"that":[77,190],"generalize":[85],"multiple":[87],"domestic":[88],"environments":[89],"challenging":[92],"task.":[93],"In":[94],"this":[95],"work,":[96],"three":[97],"most":[100],"commonly":[101],"used":[102],"spectrogram":[103],"representations":[104],"are":[105,132,149],"evaluated,":[106],"based":[107],"their":[109],"spectral":[110,114],"magnitude":[111,168,201],"energies.":[115],"Specifically,":[116],"using":[117],"multi-channel":[118],"data,":[120],"Short-time":[122],"Fourier":[123],"Transform":[124],"(STFT),":[125],"Mel":[127],"Gammatone":[130],"spectrograms":[131],"extracted":[133],"trained":[135],"2D":[138],"Convolutional":[139],"Neural":[140],"Network":[141],"(CNN).":[142],"The":[143],"F1-Scores":[144],"each":[146],"feature":[147],"representation":[148],"computed,":[150],"McNemar":[153],"tests":[154],"Receiver":[157],"Operating":[158],"Characteristic":[159],"(ROC)":[160],"curves":[161],"ensure":[162],"statistical":[164],"independence":[165],"between":[166],"energy":[171],"representations.":[172,202],"Extensive":[173],"experimental":[174],"results":[175],"public":[178],"database":[179],"daily":[183],"activities":[184],"home":[187],"environment,":[188],"show":[189],"overall":[192],"highest":[193],"achieved":[197],"STFT":[200]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}