{"id":"https://openalex.org/W2096686458","doi":"https://doi.org/10.1109/icassp.2005.1416332","title":"SOLAR: Sound Object Localization and Retrieval in Complex Audio Environments","display_name":"SOLAR: Sound Object Localization and Retrieval in Complex Audio Environments","publication_year":2006,"publication_date":"2006-10-04","ids":{"openalex":"https://openalex.org/W2096686458","doi":"https://doi.org/10.1109/icassp.2005.1416332","mag":"2096686458"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1416332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1416332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"},"type":"conference-paper","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/A5009682734","display_name":"Derek Hoiem","orcid":"https://orcid.org/0000-0001-6260-5708"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D. Hoiem","raw_affiliation_strings":["[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103532185","display_name":"Yan Ke","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yan Ke","raw_affiliation_strings":["School of Computer Science, Carnegie Mellon University, USA","[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066107323","display_name":"Rahul Sukthankar","orcid":null},"institutions":[{"id":"https://openalex.org/I1343180700","display_name":"Intel (United States)","ror":"https://ror.org/01ek73717","country_code":"US","type":"company","lineage":["https://openalex.org/I1343180700"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"R. Sukthankar","raw_affiliation_strings":["Intel Research Pittsburgh, USA","School of Computer Science, Carnegie Mellon University, USA","[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intel Research Pittsburgh, USA","institution_ids":["https://openalex.org/I1343180700"]},{"raw_affiliation_string":"School of Computer Science, Carnegie Mellon University, USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"[Sch. of Comput. Sci., Carnegie, Mellon Univ., Pittsburgh, PA, USA]","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"429","last_page":"432"},"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":0.9975000023841858,"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":0.7973759770393372},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6150164604187012},{"id":"https://openalex.org/keywords/sound","display_name":"Sound (geography)","score":0.5529520511627197},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.54939204454422},{"id":"https://openalex.org/keywords/window","display_name":"Window (computing)","score":0.5187228322029114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093380212783813},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.4980509281158447},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.46149739623069763},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.41454142332077026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.35386723279953003},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.25036272406578064},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2354739010334015},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.10192805528640747}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7973759770393372},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6150164604187012},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.5529520511627197},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.54939204454422},{"id":"https://openalex.org/C2778751112","wikidata":"https://www.wikidata.org/wiki/Q835016","display_name":"Window (computing)","level":2,"score":0.5187228322029114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093380212783813},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.4980509281158447},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.46149739623069763},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.41454142332077026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.35386723279953003},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25036272406578064},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2354739010334015},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.10192805528640747},{"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/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.2005.1416332","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1416332","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"},{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1504694836","https://openalex.org/W1954587310","https://openalex.org/W2032210760","https://openalex.org/W2039275978","https://openalex.org/W2057613716","https://openalex.org/W2074188409","https://openalex.org/W2091181450","https://openalex.org/W2097419036","https://openalex.org/W2110458017","https://openalex.org/W2125055259","https://openalex.org/W2149054612","https://openalex.org/W2159761515","https://openalex.org/W2164598857","https://openalex.org/W2168441989","https://openalex.org/W2343867458","https://openalex.org/W2575922621","https://openalex.org/W6640934164","https://openalex.org/W6664934753","https://openalex.org/W6681810270","https://openalex.org/W6683343296","https://openalex.org/W6684548678","https://openalex.org/W6732521411"],"related_works":["https://openalex.org/W2271369634","https://openalex.org/W2350550760","https://openalex.org/W578794879","https://openalex.org/W2625296515","https://openalex.org/W2109115373","https://openalex.org/W2390901981","https://openalex.org/W3137890128","https://openalex.org/W4245955731","https://openalex.org/W2393726419","https://openalex.org/W2380912101"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,85,95],"identify":[3],"sounds":[4],"in":[5,28,50,69],"complex":[6,51],"audio":[7,52,67,76,132],"environments":[8],"is":[9],"highly":[10],"useful":[11],"for":[12,61,89],"multimedia":[13],"retrieval,":[14],"security,":[15],"and":[16,72,94,102,127],"many":[17],"mobile":[18],"robotic":[19],"applications,":[20],"but":[21],"very":[22],"little":[23],"work":[24],"has":[25],"been":[26],"done":[27],"this":[29],"area.":[30],"We":[31,106],"present":[32],"the":[33,59,66,98,108],"SOLAR":[34,57,79],"system,":[35],"a":[36],"system":[37],"capable":[38],"of":[39,100,110,124,131],"finding":[40],"sound":[41,92,117],"objects,":[42],"such":[43],"as":[44],"dog":[45],"barks":[46],"or":[47],"car":[48],"horns,":[49],"data":[53,68,133],"extracted":[54,134],"from":[55,135],"movies.":[56,137],"avoids":[58],"need":[60],"segmentation":[62],"by":[63],"scanning":[64],"over":[65],"fixed":[70],"increments":[71],"classifying":[73],"each":[74,91],"short":[75],"window":[77],"separately.":[78],"employs":[80],"boosted":[81],"decision":[82],"tree":[83],"classifiers":[84],"select":[86],"suitable":[87],"features":[88],"modeling":[90],"object":[93,99,118],"discriminate":[96],"between":[97],"interest":[101],"all":[103],"other":[104],"sounds.":[105],"demonstrate":[107],"effectiveness":[109],"our":[111],"approach":[112],"with":[113],"experiments":[114],"on":[115,129],"thirteen":[116],"classes":[119],"trained":[120],"using":[121],"only":[122],"tens":[123],"positive":[125],"examples":[126],"tested":[128],"hours":[130],"popular":[136]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}