{"id":"https://openalex.org/W2128083002","doi":"https://doi.org/10.1109/icassp.2012.6288868","title":"A tandem connectionist model using combination of multi-scale spectro-temporal features for acoustic event detection","display_name":"A tandem connectionist model using combination of multi-scale spectro-temporal features for acoustic event detection","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2128083002","doi":"https://doi.org/10.1109/icassp.2012.6288868","mag":"2128083002"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2012.6288868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5039277089","display_name":"Miquel Espi","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Miquel Espi","raw_affiliation_strings":["Graduate School of Informations Science and Technology, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informations Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109368288","display_name":"Masakiyo Fujimoto","orcid":null},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masakiyo Fujimoto","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan","NTT Communication Science Labs, NTT Corp., Japan#TAB#"],"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Communication Science Labs, NTT Corp., Japan#TAB#","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010841595","display_name":"Daisuke Saito","orcid":"https://orcid.org/0000-0003-3200-579X"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Saito","raw_affiliation_strings":["Graduate School of Informations Science and Technology, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informations Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056281759","display_name":"Nobutaka Ono","orcid":"https://orcid.org/0000-0003-4242-2773"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nobutaka Ono","raw_affiliation_strings":["National Institute of Information, Japan","National institute of informatics, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"National institute of informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003450550","display_name":"Shigeki Sagayama","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shigeki Sagayama","raw_affiliation_strings":["Graduate School of Informations Science and Technology, University of Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Informations Science and Technology, University of Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5039277089"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.9588,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.89631011,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"4625","issue":null,"first_page":"4293","last_page":"4296"},"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":0.9991999864578247,"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":0.998199999332428,"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/computer-science","display_name":"Computer science","score":0.7745700478553772},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6656134724617004},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.6565101146697998},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5365993976593018},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5120163559913635},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5103709101676941},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4787668287754059},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.47546857595443726},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46209636330604553},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4211781620979309},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24820482730865479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745700478553772},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6656134724617004},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.6565101146697998},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5365993976593018},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5120163559913635},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5103709101676941},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4787668287754059},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.47546857595443726},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46209636330604553},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4211781620979309},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24820482730865479},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/icassp.2012.6288868","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2012.6288868","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":12,"referenced_works":["https://openalex.org/W1504129048","https://openalex.org/W2100772705","https://openalex.org/W2115447976","https://openalex.org/W2158275940","https://openalex.org/W2160767978","https://openalex.org/W2165712214","https://openalex.org/W2327970305","https://openalex.org/W2403700470","https://openalex.org/W6629978730","https://openalex.org/W6674917984","https://openalex.org/W6684249834","https://openalex.org/W6713311455"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645","https://openalex.org/W1024498263","https://openalex.org/W2157423375"],"abstract_inverted_index":{"Acoustic":[0],"event":[1,34,94,127],"detection":[2,128],"systems":[3],"supporting":[4],"heterogeneous":[5],"sets":[6],"of":[7,12,46,57],"events":[8],"face":[9],"the":[10,32,47,55,79,107,111,120],"problem":[11],"having":[13],"to":[14,67,81,84],"characterize":[15],"them":[16],"when":[17],"they":[18],"have":[19],"different":[20,44,100],"acoustic":[21,33,126],"properties":[22,45],"(transient,":[23],"stationary,":[24],"both,":[25],"etc.),":[26],"observing":[27],"this":[28],"fact":[29],"even":[30],"within":[31],"itself.":[35],"Moreover,":[36],"managing":[37],"large":[38],"feature":[39],"vectors":[40],"with":[41],"features":[42,60,70],"characterizing":[43],"signal":[48],"is":[49],"always":[50],"difficult.":[51],"This":[52],"paper":[53],"introduces":[54],"usage":[56],"spectro-temporal":[58],"fluctuation":[59,74],"in":[61,119],"a":[62,85],"tandem":[63],"connectionist":[64],"approach,":[65],"modified":[66],"generate":[68],"posterior":[69],"separately":[71],"for":[72],"each":[73],"scale":[75,92],"and":[76,93,104],"then":[77],"combine":[78],"streams":[80],"be":[82],"fed":[83],"classic":[86],"GMM-HMM":[87,112],"model.":[88],"The":[89],"experiments":[90],"explore":[91],"wise":[95],"performance,":[96],"as":[97,99,114,116],"well":[98,115],"stream":[101],"combination":[102],"methods,":[103],"show":[105],"that":[106],"proposed":[108],"method":[109],"outperforms":[110],"baseline":[113],"recent":[117],"proposals":[118],"CHIL":[121],"2007":[122],"evaluation":[123],"campaign's":[124],"related":[125],"tasks.":[129]},"counts_by_year":[{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}