{"id":"https://openalex.org/W2152909444","doi":"https://doi.org/10.1109/mmsp.2009.5293267","title":"Saliency-driven unstructured acoustic scene classification using latent perceptual indexing","display_name":"Saliency-driven unstructured acoustic scene classification using latent perceptual indexing","publication_year":2009,"publication_date":"2009-10-01","ids":{"openalex":"https://openalex.org/W2152909444","doi":"https://doi.org/10.1109/mmsp.2009.5293267","mag":"2152909444"},"language":"en","primary_location":{"id":"doi:10.1109/mmsp.2009.5293267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2009.5293267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Workshop on Multimedia 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/A5066166549","display_name":"Ozlem Kalinli","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"]},{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ozlem Kalinli","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory (SAIL), Department of Electrical Engineering-Systems, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory (SAIL), Department of Electrical Engineering-Systems, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113697636","display_name":"Shiva Sundaram","orcid":null},"institutions":[{"id":"https://openalex.org/I4210093367","display_name":"Deutsche Telekom (Germany)","ror":"https://ror.org/00m8prc86","country_code":"DE","type":"company","lineage":["https://openalex.org/I4210093367"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Shiva Sundaram","raw_affiliation_strings":["Deutsche Telekom Laboratoryoratories, Quality and Usability Laboratory, Technical University Berlin, Berlin, Germany"],"affiliations":[{"raw_affiliation_string":"Deutsche Telekom Laboratoryoratories, Quality and Usability Laboratory, Technical University Berlin, Berlin, Germany","institution_ids":["https://openalex.org/I4210093367"]}]},{"author_position":"last","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"]},{"id":"https://openalex.org/I4210116219","display_name":"Engineering Systems (United States)","ror":"https://ror.org/02qg60849","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shrikanth Narayanan","raw_affiliation_strings":["Speech Analysis and Interpretation Laboratory (SAIL), Department of Electrical Engineering-Systems, University of Southern California, Los Angeles, CA, USA"],"affiliations":[{"raw_affiliation_string":"Speech Analysis and Interpretation Laboratory (SAIL), Department of Electrical Engineering-Systems, University of Southern California, Los Angeles, CA, USA","institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116219"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5066166549"],"corresponding_institution_ids":["https://openalex.org/I1174212","https://openalex.org/I4210116219"],"apc_list":null,"apc_paid":null,"fwci":0.7157,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.71660674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"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":1.0,"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":1.0,"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":0.9990000128746033,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.9908000230789185,"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":0.8242179155349731},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7820894718170166},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6965972185134888},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5595267415046692},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5348941683769226},{"id":"https://openalex.org/keywords/acoustic-space","display_name":"Acoustic space","score":0.5268971920013428},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5160569548606873},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.47495317459106445},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4522460401058197},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4268597960472107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41882458329200745},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.29770100116729736},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.18704569339752197},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12900763750076294}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242179155349731},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7820894718170166},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6965972185134888},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5595267415046692},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5348941683769226},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.5268971920013428},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5160569548606873},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.47495317459106445},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4522460401058197},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4268597960472107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41882458329200745},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.29770100116729736},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.18704569339752197},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12900763750076294},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mmsp.2009.5293267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mmsp.2009.5293267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Workshop on Multimedia Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W395014823","https://openalex.org/W1510226565","https://openalex.org/W1967197178","https://openalex.org/W1990014053","https://openalex.org/W2018844855","https://openalex.org/W2058189943","https://openalex.org/W2074188409","https://openalex.org/W2122832694","https://openalex.org/W2127877627","https://openalex.org/W2128272608","https://openalex.org/W2131981197","https://openalex.org/W2137337354","https://openalex.org/W2137561966","https://openalex.org/W2141841802","https://openalex.org/W2142524229","https://openalex.org/W2147152072","https://openalex.org/W2154016477","https://openalex.org/W2159277110","https://openalex.org/W2168441989","https://openalex.org/W3146177989","https://openalex.org/W3146463283","https://openalex.org/W4214591285","https://openalex.org/W6613633810","https://openalex.org/W6681067464"],"related_works":["https://openalex.org/W2726222394","https://openalex.org/W2008638795","https://openalex.org/W2539985974","https://openalex.org/W67997247","https://openalex.org/W2763080223","https://openalex.org/W1516342924","https://openalex.org/W2150570379","https://openalex.org/W1969975883","https://openalex.org/W1830938247","https://openalex.org/W2152909444"],"abstract_inverted_index":{"Automatic":[0],"acoustic":[1,10,20,45],"scene":[2],"classification":[3,42,74,85,139],"of":[4,19,53,60,81],"real":[5],"life,":[6],"complex":[7],"and":[8,29,70,140],"unstructured":[9,44],"scenes":[11],"is":[12],"a":[13,38,96,104],"challenging":[14],"task":[15],"as":[16],"the":[17,24,49,54,73,84,93,114,122,148],"number":[18],"sources":[21],"present":[22,37],"in":[23,31,66,95,128,137],"audio":[25,62,109,150],"stream":[26],"are":[27,64],"unknown":[28],"overlapping":[30],"time.":[32],"In":[33],"this":[34,129],"work,":[35],"we":[36],"novel":[39],"approach":[40,107,126],"to":[41,72,77,91,108],"such":[43],"scenes.":[46],"Motivated":[47],"by":[48],"bottom-up":[50],"attention":[51,124],"model":[52],"human":[55],"auditory":[56],"system,":[57],"salient":[58],"events":[59],"an":[61,67],"clip":[63,94],"extracted":[65],"unsupervised":[68],"manner":[69],"presented":[71,127],"system.":[75],"Similar":[76],"latent":[78,98,149],"semantic":[79],"indexing":[80,151],"text":[82],"documents,":[83],"system":[86],"uses":[87],"unit-document":[88],"frequency":[89],"measure":[90],"index":[92],"continuous,":[97],"space.":[99],"This":[100],"allows":[101],"for":[102],"developing":[103],"completely":[105],"class-independent":[106],"classification.":[110],"Our":[111],"results":[112],"on":[113],"BBC":[115],"sound":[116],"effects":[117],"library":[118],"indicates":[119],"that":[120],"using":[121,147],"saliency-driven":[123],"selection":[125],"paper,":[130],"17.5%":[131],"relative":[132,142],"improvement":[133,143],"can":[134,144],"be":[135,145],"obtained":[136,146],"frame-based":[138],"25%":[141],"approach.":[152]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2013,"cited_by_count":6}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}