{"id":"https://openalex.org/W2092216166","doi":"https://doi.org/10.1109/icassp.2014.6854293","title":"A Bag-of-Features approach to acoustic event detection","display_name":"A Bag-of-Features approach to acoustic event detection","publication_year":2014,"publication_date":"2014-05-01","ids":{"openalex":"https://openalex.org/W2092216166","doi":"https://doi.org/10.1109/icassp.2014.6854293","mag":"2092216166"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2014.6854293","doi":"https://doi.org/10.1109/icassp.2014.6854293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854293","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5005165731","display_name":"Axel Plinge","orcid":"https://orcid.org/0000-0001-7757-2953","observed_orcids":["https://orcid.org/0000-0001-7757-2953"]},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Axel Plinge","raw_affiliation_strings":["Department of Computer Science, TU Dortmund University, Dortmund, Germany","Dept. of Comput. Sci., Tech. Univ. Dortmund, Dortmund, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, TU Dortmund University, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Tech. Univ. Dortmund, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048238299","display_name":"Ren\u00e9 Grzeszick","orcid":"https://orcid.org/0000-0001-7934-7469","observed_orcids":["https://orcid.org/0000-0001-7934-7469"]},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rene Grzeszick","raw_affiliation_strings":["Department of Computer Science, TU Dortmund University, Dortmund, Germany","Dept. of Comput. Sci., Tech. Univ. Dortmund, Dortmund, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, TU Dortmund University, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Tech. Univ. Dortmund, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048407937","display_name":"Gernot A. Fink","orcid":"https://orcid.org/0000-0002-7446-7813","observed_orcids":["https://orcid.org/0000-0002-7446-7813"]},"institutions":[{"id":"https://openalex.org/I200332995","display_name":"TU Dortmund University","ror":"https://ror.org/01k97gp34","country_code":"DE","type":"education","lineage":["https://openalex.org/I200332995"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Gernot A. Fink","raw_affiliation_strings":["Department of Computer Science, TU Dortmund University, Dortmund, Germany","Dept. of Comput. Sci., Tech. Univ. Dortmund, Dortmund, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, TU Dortmund University, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Tech. Univ. Dortmund, Dortmund, Germany","institution_ids":["https://openalex.org/I200332995"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I200332995"],"apc_list":null,"apc_paid":null,"fwci":12.3984,"has_fulltext":false,"cited_by_count":76,"citation_normalized_percentile":{"value":0.99522749,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3704","last_page":"3708"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T10860","display_name":"Speech and Audio Processing","score":0.00019999999494757503,"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/T10201","display_name":"Speech Recognition and Synthesis","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/sound-event-detection","display_name":"sound event detection","score":0.972000002861023},{"id":"https://openalex.org/keywords/bag-of-visual-words","display_name":"bag of visual words","score":0.8799999952316284},{"id":"https://openalex.org/keywords/mel-frequency-cepstral-coefficients","display_name":"Mel-frequency cepstral coefficients","score":0.8220000267028809},{"id":"https://openalex.org/keywords/gammatone-frequency-cepstral-coefficients","display_name":"gammatone frequency cepstral coefficients","score":0.9480000138282776},{"id":"https://openalex.org/keywords/psychoacoustic-model","display_name":"psychoacoustic model","score":0.8769999742507935},{"id":"https://openalex.org/keywords/background-noise-modeling","display_name":"background noise modeling","score":0.5239999890327454},{"id":"https://openalex.org/keywords/codebook-learning","display_name":"codebook learning","score":0.9169999957084656},{"id":"https://openalex.org/keywords/temporal-coding","display_name":"temporal coding","score":0.9890000224113464},{"id":"https://openalex.org/keywords/smart-environments","display_name":"smart environments","score":0.8700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562079429626465},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5684459805488586},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5575253367424011},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5500343441963196},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.544614315032959},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4799678325653076},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47873470187187195},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4666072726249695},{"id":"https://openalex.org/C9940772","wikidata":"https://www.wikidata.org/wiki/Q557399","display_name":"Psychoacoustics","level":3,"score":0.46419987082481384},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4383726119995117},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.43650922179222107},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2014.6854293","doi":"https://doi.org/10.1109/icassp.2014.6854293","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2014.6854293","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["jufo-2","norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W659304222","https://openalex.org/W1533561824","https://openalex.org/W1660390307","https://openalex.org/W1787683252","https://openalex.org/W1837649128","https://openalex.org/W1902027874","https://openalex.org/W1976921161","https://openalex.org/W2046972719","https://openalex.org/W2048174296","https://openalex.org/W2087914438","https://openalex.org/W2093926188","https://openalex.org/W2105068979","https://openalex.org/W2120478181","https://openalex.org/W2126941448","https://openalex.org/W2148374980","https://openalex.org/W2162915993","https://openalex.org/W2164432048","https://openalex.org/W2164996087","https://openalex.org/W2408491073","https://openalex.org/W3215500402","https://openalex.org/W4233392025"],"related_works":["https://openalex.org/W2619771377","https://openalex.org/W2727756476","https://openalex.org/W2285774199","https://openalex.org/W3214993354","https://openalex.org/W2801558044","https://openalex.org/W2358123637","https://openalex.org/W2979507862","https://openalex.org/W2919849250","https://openalex.org/W2788310755","https://openalex.org/W2566526893"],"abstract_inverted_index":{"The":[0],"classification":[1,63],"of":[2,83,116],"acoustic":[3,27],"events":[4,28],"in":[5,16],"indoor":[6],"environments":[7],"is":[8,30,36],"an":[9],"important":[10],"task":[11],"for":[12,25,54,77,100],"many":[13],"practical":[14],"applications":[15],"smart":[17,117],"environments.":[18],"In":[19],"this":[20],"paper":[21],"a":[22,33,61,78,113],"novel":[23],"approach":[24,35],"classifying":[26],"that":[29,44],"based":[31],"on":[32],"Bag-of-Features":[34,73],"proposed.":[37],"Mel":[38],"and":[39,70,85,112],"gammatone":[40],"frequency":[41],"cepstral":[42],"coefficients":[43],"originate":[45],"from":[46],"psychoacoustic":[47],"models":[48],"are":[49,75,88,98],"used":[50,99],"as":[51],"input":[52],"features":[53],"the":[55,92,101,103,108],"Bag-of":[56],"representation.":[57],"Rather":[58],"than":[59],"using":[60],"prior":[62],"or":[64],"segmentation":[65],"step":[66],"to":[67,90],"eliminate":[68],"silence":[69],"background":[71,79],"noise,":[72],"representations":[74],"learned":[76],"class.":[80],"Supervised":[81],"learning":[82],"codebooks":[84],"temporal":[86],"coding":[87],"shown":[89],"improve":[91],"recognition":[93],"rates.":[94],"Three":[95],"different":[96],"databases":[97],"experiments:":[102],"CLEAR":[104],"sound":[105],"event":[106,110],"dataset,":[107],"D-CASE":[109],"dataset":[111],"new":[114],"set":[115],"room":[118],"recordings.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":14},{"year":2014,"cited_by_count":2}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}