{"id":"https://openalex.org/W2108815700","doi":"https://doi.org/10.1109/icassp.2011.5946412","title":"Improving acoustic event detection using generalizable visual features and multi-modality modeling","display_name":"Improving acoustic event detection using generalizable visual features and multi-modality modeling","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2108815700","doi":"https://doi.org/10.1109/icassp.2011.5946412","mag":"2108815700"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5946412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 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/A5076474156","display_name":"Po-Sen Huang","orcid":"https://orcid.org/0000-0003-1470-0991"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Po-Sen Huang","raw_affiliation_strings":["Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, U.S.A"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, U.S.A","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, U.S.A"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, U.S.A","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004778663","display_name":"Mark Hasegawa\u2010Johnson","orcid":"https://orcid.org/0000-0002-5631-2893"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mark Hasegawa-Johnson","raw_affiliation_strings":["Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, U.S.A"],"affiliations":[{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois at Urbana-Champaign, U.S.A","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5076474156"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":2.4944,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89923893,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"349","last_page":"352"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11309","display_name":"Music 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/T11439","display_name":"Video Analysis and Summarization","score":0.9901000261306763,"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":0.8192836046218872},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8117808103561401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5959406495094299},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5349605679512024},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.5304346084594727},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.512817919254303},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.4901159703731537},{"id":"https://openalex.org/keywords/modality","display_name":"Modality (human\u2013computer interaction)","score":0.45797061920166016},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.389312744140625}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192836046218872},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8117808103561401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5959406495094299},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5349605679512024},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.5304346084594727},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.512817919254303},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.4901159703731537},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.45797061920166016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.389312744140625},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"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/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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2011.5946412","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5946412","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.294.5032","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.294.5032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.ifp.illinois.edu/speech/pubs/2011/huang11icassp.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1529401398","https://openalex.org/W1578985305","https://openalex.org/W1600134093","https://openalex.org/W2101294471","https://openalex.org/W2115447976","https://openalex.org/W2116418373","https://openalex.org/W2118230268","https://openalex.org/W2118977726","https://openalex.org/W2137611207","https://openalex.org/W2142674578","https://openalex.org/W2146570360","https://openalex.org/W2146614494","https://openalex.org/W2146792684","https://openalex.org/W2158762315","https://openalex.org/W2159505975","https://openalex.org/W2162915993","https://openalex.org/W2487271655","https://openalex.org/W3143122312","https://openalex.org/W6677158943","https://openalex.org/W6683181420"],"related_works":["https://openalex.org/W2990278625","https://openalex.org/W1993499045","https://openalex.org/W1604595447","https://openalex.org/W4200613756","https://openalex.org/W2983489261","https://openalex.org/W2988239832","https://openalex.org/W2075885261","https://openalex.org/W2174601236","https://openalex.org/W3036714870","https://openalex.org/W2157423375"],"abstract_inverted_index":{"Acoustic":[0],"event":[1,130],"detection":[2,46,133],"(AED)":[3],"aims":[4],"to":[5,18,166],"identify":[6],"both":[7,31,55],"timestamps":[8],"and":[9,14,33,47,88,120,132,175],"types":[10,142],"of":[11,49,105,143],"multiple":[12,180],"events":[13,26,51,146],"has":[15],"been":[16],"found":[17],"be":[19],"very":[20],"challenging.":[21],"The":[22,124],"cues":[23,53],"for":[24,85,97],"these":[25],"often":[27],"times":[28],"exist":[29],"in":[30,38],"audio":[32,159],"vision,":[34],"but":[35],"not":[36,72],"necessarily":[37],"a":[39,66,135],"synchronized":[40],"fashion.":[41],"We":[42,57],"study":[43],"improving":[44],"the":[45,50,103,154,158],"classification":[48,131],"using":[52,148],"from":[54,179],"modalities.":[56],"propose":[58],"optical":[59],"flow":[60],"based":[61],"spatial":[62],"pyramid":[63],"histograms":[64],"as":[65],"generalizable":[67],"visual":[68,172],"representation":[69],"that":[70],"does":[71],"require":[73],"training":[74,113],"on":[75,134],"labeled":[76],"video":[77,155],"data.":[78],"Hidden":[79],"Markov":[80],"models":[81],"(HMMs)":[82],"are":[83,95],"used":[84,96],"audio-only":[86],"modeling,":[87],"multi-stream":[89],"HMMs":[90,93],"or":[91],"coupled":[92],"(CHMM)":[94],"audio-visual":[98,106],"joint":[99],"modeling.":[100],"To":[101],"allow":[102],"flexibility":[104],"state":[107],"asynchrony,":[108],"we":[109],"explore":[110],"effective":[111],"CHMM":[112],"via":[114],"HMM":[115],"state-space":[116],"mapping,":[117],"parameter":[118],"tying":[119],"different":[121],"initialization":[122],"schemes.":[123],"proposed":[125],"methods":[126],"successfully":[127],"improve":[128],"acoustic":[129],"multimedia":[136],"meeting":[137],"room":[138],"dataset":[139],"containing":[140],"eleven":[141],"general":[144],"non-speech":[145],"without":[147],"extra":[149],"data":[150],"resource":[151],"other":[152],"than":[153],"stream":[156],"accompanying":[157],"observations.":[160],"Our":[161],"systems":[162,169],"perform":[163],"favorably":[164],"compared":[165],"previously":[167],"reported":[168],"leveraging":[170],"ad-hoc":[171],"cue":[173],"detectors":[174],"localization":[176],"information":[177],"obtained":[178],"microphones.":[181]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}