{"id":"https://openalex.org/W2018234130","doi":"https://doi.org/10.1109/icassp.2010.5495934","title":"Spatial audio cues based surveillance audio attention model","display_name":"Spatial audio cues based surveillance audio attention model","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2018234130","doi":"https://doi.org/10.1109/icassp.2010.5495934","mag":"2018234130"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5001059154","display_name":"Bo Hang","orcid":"https://orcid.org/0000-0003-1554-4388"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Hang","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, Wuhan University of China, Wuhan, China","National Engineering Research Center for Multimedia Software, Wuhan University, 430072, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, Wuhan University of China, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, Wuhan University, 430072, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008406199","display_name":"Ruimin Hu","orcid":"https://orcid.org/0000-0002-5872-3872"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruimin Hu","raw_affiliation_strings":["National Engineering Research Center for Multimedia Software, Wuhan University of China, Wuhan, China","National Engineering Research Center for Multimedia Software, Wuhan University, 430072, China"],"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, Wuhan University of China, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]},{"raw_affiliation_string":"National Engineering Research Center for Multimedia Software, Wuhan University, 430072, China","institution_ids":["https://openalex.org/I37461747"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5001059154"],"corresponding_institution_ids":["https://openalex.org/I37461747"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.09894955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"289","last_page":"292"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9929999709129333,"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/T12032","display_name":"Multisensory perception and integration","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7938199043273926},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6812518835067749},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.5845706462860107},{"id":"https://openalex.org/keywords/stereophonic-sound","display_name":"Stereophonic sound","score":0.5578088164329529},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5209037661552429},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.47805291414260864},{"id":"https://openalex.org/keywords/event","display_name":"Event (particle physics)","score":0.47424429655075073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4335755407810211},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3953566551208496},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2928125262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7938199043273926},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6812518835067749},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.5845706462860107},{"id":"https://openalex.org/C140631703","wikidata":"https://www.wikidata.org/wiki/Q34678","display_name":"Stereophonic sound","level":3,"score":0.5578088164329529},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5209037661552429},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.47805291414260864},{"id":"https://openalex.org/C2779662365","wikidata":"https://www.wikidata.org/wiki/Q5416694","display_name":"Event (particle physics)","level":2,"score":0.47424429655075073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4335755407810211},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3953566551208496},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2928125262260437},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","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/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2010.5495934","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495934","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1634277956","https://openalex.org/W1969556630","https://openalex.org/W1970563292","https://openalex.org/W1973746598","https://openalex.org/W2013020033","https://openalex.org/W2098041937","https://openalex.org/W2114324224","https://openalex.org/W2124000984","https://openalex.org/W2126532873","https://openalex.org/W2139990098","https://openalex.org/W2148611654","https://openalex.org/W2149095485","https://openalex.org/W2154558866","https://openalex.org/W2156761163","https://openalex.org/W2158058159","https://openalex.org/W2276275925","https://openalex.org/W2751379301","https://openalex.org/W4388387870","https://openalex.org/W6636771270"],"related_works":["https://openalex.org/W4253879301","https://openalex.org/W2098934641","https://openalex.org/W4205884140","https://openalex.org/W2020952589","https://openalex.org/W2026093479","https://openalex.org/W1975359510","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4387698063","https://openalex.org/W4382560817"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5],"bottom-up":[6],"audio":[7,13,21,26,68,74],"attention":[8,39,60,69],"model":[9,70],"based":[10],"on":[11],"spatial":[12,25],"cues":[14],"for":[15,73],"unsupervised":[16],"event":[17,76],"detecting":[18],"in":[19],"stereo":[20],"surveillance.":[22],"Firstly,":[23],"the":[24,38,58],"parameter":[27],"Interaural":[28],"Level":[29],"Difference":[30],"(ILD)":[31],"is":[32,54,71],"extracted":[33],"to":[34,56],"calculate":[35],"and":[36],"represent":[37],"events,":[40],"which":[41],"are":[42],"caused":[43],"by":[44],"rapid":[45],"moving":[46],"sound":[47],"source.":[48],"Then":[49],"an":[50],"environment":[51],"adaptive":[52],"normalization":[53],"used":[55],"assess":[57],"normalized":[59],"level.":[61],"Experimental":[62],"results":[63],"demonstrate":[64],"that":[65],"our":[66],"proposed":[67],"effective":[72],"surveillance":[75],"detection.":[77]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}