{"id":"https://openalex.org/W2128468130","doi":"https://doi.org/10.1109/icassp.2009.4959912","title":"A semi-supervised learning approach to online audio background detection","display_name":"A semi-supervised learning approach to online audio background detection","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2128468130","doi":"https://doi.org/10.1109/icassp.2009.4959912","mag":"2128468130"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4959912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5112776516","display_name":"Selina Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Selina Chu","raw_affiliation_strings":["Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, 90089-2564, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, 90089-2564, USA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010028928","display_name":"Shrikanth Narayanan","orcid":"https://orcid.org/0000-0002-1052-6204"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, 90089-2564, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, 90089-2564, USA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001082656","display_name":"C.\u2010C. Jay Kuo","orcid":"https://orcid.org/0000-0001-9474-5035"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C.-C. Jay Kuo","raw_affiliation_strings":["Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, 90089-2564, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212"]},{"raw_affiliation_string":"Department of Computer Science and Signal and Image Processing Institute, University of Southern California, Los Angeles, 90089-2564, USA#TAB#","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112776516"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":1.4099,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.81396293,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1629","last_page":"1632"},"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":0.9994999766349792,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9829000234603882,"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":0.828637957572937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6114270687103271},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.607052743434906},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.605230450630188},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5374065041542053},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.5339257717132568},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5030807852745056},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4966910481452942},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.4625178575515747},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4597568213939667},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.4480420649051666},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.4397454857826233},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4333544373512268},{"id":"https://openalex.org/keywords/online-learning","display_name":"Online learning","score":0.4155523180961609},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.4069482982158661},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4051859974861145},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3488786220550537},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.28604966402053833},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.14905428886413574},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.13822680711746216},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12400636076927185},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0938546359539032}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.828637957572937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6114270687103271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.607052743434906},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.605230450630188},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5374065041542053},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.5339257717132568},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5030807852745056},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4966910481452942},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.4625178575515747},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4597568213939667},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.4480420649051666},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.4397454857826233},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4333544373512268},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.4155523180961609},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.4069482982158661},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4051859974861145},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3488786220550537},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.28604966402053833},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.14905428886413574},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.13822680711746216},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12400636076927185},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0938546359539032},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"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/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/icassp.2009.4959912","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4959912","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1509840103","https://openalex.org/W1822987211","https://openalex.org/W2057746219","https://openalex.org/W2073295754","https://openalex.org/W2097089247","https://openalex.org/W2102625004","https://openalex.org/W2104680684","https://openalex.org/W2130640900","https://openalex.org/W2137343183","https://openalex.org/W2161755617","https://openalex.org/W6630686022","https://openalex.org/W6675656709","https://openalex.org/W6675827131"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W3004352674","https://openalex.org/W1975359510","https://openalex.org/W3110605476","https://openalex.org/W1803351015","https://openalex.org/W2363106653"],"abstract_inverted_index":{"We":[0,52,86],"present":[1],"a":[2,54,63,81],"framework":[3],"for":[4,21,56],"audio":[5,12,18,99],"background":[6,17,50,60,75,84,114],"modeling":[7],"of":[8,16,128],"complex":[9],"and":[10,23,33,94],"unstructured":[11],"environments.":[13],"The":[14],"determination":[15,76,108],"is":[19,69],"important":[20],"understanding":[22],"predicting":[24],"the":[25,38,49,58,73,107,113,126],"ambient":[26],"context":[27],"surrounding":[28],"an":[29],"agent,":[30],"both":[31,92],"human":[32],"machine.":[34],"Our":[35],"method":[36,55],"extends":[37],"online":[39,74],"adaptive":[40],"Gaussian":[41],"Mixture":[42],"model":[43,46,61],"technique":[44],"to":[45,97],"variations":[47],"in":[48,106],"audio.":[51],"propose":[53],"learning":[57,65],"initial":[59],"using":[62],"semi-supervised":[64],"approach.":[66],"This":[67],"information":[68],"then":[70],"integrated":[71],"into":[72],"process,":[77,109],"providing":[78],"us":[79],"with":[80],"more":[82],"complete":[83],"model.":[85],"show":[87],"that":[88],"we":[89,110],"can":[90,111],"utilize":[91],"labeled":[93],"unlabeled":[95],"data":[96,123],"improve":[98,112],"classification":[100],"performance.":[101],"By":[102],"incorporating":[103],"prediction":[104],"models":[105],"detection":[115],"performance":[116],"even":[117],"further.":[118],"Experimental":[119],"results":[120],"on":[121],"real":[122],"sets":[124],"demonstrate":[125],"effectiveness":[127],"our":[129],"proposed":[130],"method.":[131]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}