{"id":"https://openalex.org/W2147704751","doi":"https://doi.org/10.1145/2647868.2654936","title":"What's Making that Sound?","display_name":"What's Making that Sound?","publication_year":2014,"publication_date":"2014-10-31","ids":{"openalex":"https://openalex.org/W2147704751","doi":"https://doi.org/10.1145/2647868.2654936","mag":"2147704751"},"language":"en","primary_location":{"id":"doi:10.1145/2647868.2654936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://stars.library.ucf.edu/scopus2010/8229","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100399972","display_name":"Kai Li","orcid":"https://orcid.org/0000-0003-1560-0853"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Li","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100382930","display_name":"Jun Ye","orcid":"https://orcid.org/0000-0003-2841-6529"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Ye","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110083332","display_name":"Kien A. Hua","orcid":null},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kien A. Hua","raw_affiliation_strings":["University of Central Florida, Orlando, FL, USA"],"affiliations":[{"raw_affiliation_string":"University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100399972"],"corresponding_institution_ids":["https://openalex.org/I106165777"],"apc_list":null,"apc_paid":null,"fwci":2.0596,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.87946861,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"147","last_page":"156"},"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":0.9959999918937683,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9909999966621399,"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":0.7469602227210999},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6372746229171753},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.6030395030975342},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.5039307475090027},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33705371618270874},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3131023943424225}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469602227210999},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6372746229171753},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.6030395030975342},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.5039307475090027},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33705371618270874},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3131023943424225}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2647868.2654936","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2647868.2654936","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:stars.library.ucf.edu:scopus2010-9228","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2010/8229","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2010-2014","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:stars.library.ucf.edu:scopus2010-9228","is_oa":true,"landing_page_url":"https://stars.library.ucf.edu/scopus2010/8229","pdf_url":null,"source":{"id":"https://openalex.org/S4210172555","display_name":"Journal of International Crisis and Risk Communication Research","issn_l":"2576-0017","issn":["2576-0017","2576-0025"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus Export 2010-2014","raw_type":"text"},"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W65124300","https://openalex.org/W1507500984","https://openalex.org/W1511045106","https://openalex.org/W1989883299","https://openalex.org/W2009616550","https://openalex.org/W2020997493","https://openalex.org/W2025954386","https://openalex.org/W2065274193","https://openalex.org/W2065428732","https://openalex.org/W2067191022","https://openalex.org/W2090994663","https://openalex.org/W2093111229","https://openalex.org/W2095901148","https://openalex.org/W2099151709","https://openalex.org/W2100152238","https://openalex.org/W2109124605","https://openalex.org/W2110990863","https://openalex.org/W2122146326","https://openalex.org/W2129510504","https://openalex.org/W2140647972","https://openalex.org/W2144282867","https://openalex.org/W2168010845","https://openalex.org/W2170502958","https://openalex.org/W2171819471","https://openalex.org/W4238118210"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0,175,256],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"techniques":[5],"to":[6,48,93,97,118],"localize":[7],"the":[8,23,31,50,61,74,94,103,120,132,138,146,150,161,177,192,196,208,213,219,227,231,242,258,273,277,289],"sound":[9,24],"source":[10,186,267],"in":[11,84,125,156,199,207,237,280,288],"video":[12,51],"made":[13],"using":[14,168,249],"one":[15],"microphone.":[16],"The":[17,189,270],"visual":[18,116,123,153,209,234,290],"object":[19,35,79,136,217],"whose":[20],"motion":[21,36,75],"generates":[22],"is":[25,91,141,180,222,261],"located":[26],"and":[27,37,115,122,137,152,166,202,218,233,247,283],"segmented":[28],"based":[29],"on":[30,112],"synchronization":[32],"analysis":[33],"of":[34,55,64,77,171,195,204,252,276,285],"audio":[38,95,99,104,114,121,139,151,205,220,232,286],"energy.":[39],"We":[40,71,106,159,240],"first":[41],"apply":[42],"an":[43,65,135,216],"effective":[44],"region":[45,57],"tracking":[46],"algorithm":[47,198,279],"segment":[49],"into":[52],"a":[53,109,126,169,183,250,264],"number":[54,170,251],"spatial-temporal":[56,200,281],"tracks,":[58],"each":[59,78,85],"representing":[60],"temporal":[62],"evolution":[63],"appearance-coherent":[66],"image":[67],"structure":[68],"(i.e.,":[69],"object).":[70],"then":[72],"extract":[73,98],"features":[76],"as":[80,102],"its":[81],"average":[82],"acceleration":[83],"frame.":[86],"Meanwhile,":[87],"Short-term":[88],"Fourier":[89],"Transform":[90],"applied":[92],"signal":[96,140,221],"energy":[100],"feature":[101],"descriptor.":[105],"further":[107],"impose":[108],"nonlinear":[110],"transformation":[111],"both":[113,164,245],"descriptors":[117],"obtain":[119],"codes":[124,154,235],"common":[127],"rank":[128],"correlation":[129,133,214],"space.":[130,211],"Finally,":[131,212],"between":[134,149,215,230],"simply":[142,223],"evaluated":[143,224],"by":[144,225],"computing":[145,226],"Hamming":[147,228],"distance":[148,229],"generated":[155,236],"previous":[157,238],"steps.":[158,239],"evaluate":[160,241],"proposed":[162,178,197,243,259,278],"method":[163,179,244,260],"qualitatively":[165,246],"quantitatively":[167,248],"challenging":[172,253],"test":[173,254],"videos.":[174,255],"particular,":[176,257],"compared":[181,262],"with":[182,263],"state-of-the-art":[184,265],"audiovisual":[185,266],"localization":[187,201,268,282],"algorithm.":[188,269],"results":[190,271],"demonstrate":[191,272],"superior":[193,274],"performance":[194,275],"segmentation":[203,284],"sources":[206,287],"domain.correlation":[210],"domain.":[291]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
