{"id":"https://openalex.org/W1496168202","doi":"https://doi.org/10.1109/icassp.2015.7178279","title":"Efficient spectrogram-based binary image feature for audio copy detection","display_name":"Efficient spectrogram-based binary image feature for audio copy detection","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1496168202","doi":"https://doi.org/10.1109/icassp.2015.7178279","mag":"1496168202"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5031518818","display_name":"Chahid Ouali","orcid":null},"institutions":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chahid Ouali","raw_affiliation_strings":["\u00c9ts (\u00c9cole de Technologie Sup\u00e9rieure, Montreal), Canada","ETS (\u00c9cole de technologie sup\u00e9rieure), Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9ts (\u00c9cole de Technologie Sup\u00e9rieure, Montreal), Canada","institution_ids":["https://openalex.org/I9736820"]},{"raw_affiliation_string":"ETS (\u00c9cole de technologie sup\u00e9rieure), Montreal, Canada","institution_ids":["https://openalex.org/I9736820"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034083532","display_name":"Pierre Dumouchel","orcid":"https://orcid.org/0000-0001-5584-4428"},"institutions":[{"id":"https://openalex.org/I9736820","display_name":"\u00c9cole de Technologie Sup\u00e9rieure","ror":"https://ror.org/0020snb74","country_code":"CA","type":"education","lineage":["https://openalex.org/I49663120","https://openalex.org/I9736820"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Pierre Dumouchel","raw_affiliation_strings":["\u00c9ts (\u00c9cole de Technologie Sup\u00e9rieure, Montreal), Canada","ETS (\u00c9cole de technologie sup\u00e9rieure), Montreal, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9ts (\u00c9cole de Technologie Sup\u00e9rieure, Montreal), Canada","institution_ids":["https://openalex.org/I9736820"]},{"raw_affiliation_string":"ETS (\u00c9cole de technologie sup\u00e9rieure), Montreal, Canada","institution_ids":["https://openalex.org/I9736820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114009216","display_name":"Vishwa Gupta","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111842","display_name":"Computer Research Institute of Montr\u00e9al","ror":"https://ror.org/0279d5115","country_code":"CA","type":"nonprofit","lineage":["https://openalex.org/I4210111842"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Vishwa Gupta","raw_affiliation_strings":["CRIM (Computer Research Institute of Montreal), Montreal, Canada","CRIM (Computer Research Institute of Montreal), Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CRIM (Computer Research Institute of Montreal), Montreal, Canada","institution_ids":["https://openalex.org/I4210111842"]},{"raw_affiliation_string":"CRIM (Computer Research Institute of Montreal), Canada","institution_ids":["https://openalex.org/I4210111842"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0297,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.86554719,"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":"1792","last_page":"1796"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music 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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music 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/T12357","display_name":"Digital Media Forensic Detection","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11439","display_name":"Video Analysis and Summarization","score":0.9980000257492065,"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/spectrogram","display_name":"Spectrogram","score":0.9270886182785034},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.7184290885925293},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.709938108921051},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.687868595123291},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5887353420257568},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5784130692481995},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.561432957649231},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4610615670681},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.42274153232574463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3739352226257324},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3367431163787842},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1790032982826233}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.9270886182785034},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.7184290885925293},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709938108921051},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.687868595123291},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5887353420257568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5784130692481995},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.561432957649231},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4610615670681},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.42274153232574463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3739352226257324},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3367431163787842},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1790032982826233},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178279","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178279","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":21,"referenced_works":["https://openalex.org/W83334756","https://openalex.org/W166806076","https://openalex.org/W1557167465","https://openalex.org/W1968090956","https://openalex.org/W1974418584","https://openalex.org/W2023854218","https://openalex.org/W2032913923","https://openalex.org/W2062903088","https://openalex.org/W2080470053","https://openalex.org/W2096598726","https://openalex.org/W2097387583","https://openalex.org/W2104160358","https://openalex.org/W2161647295","https://openalex.org/W2162916741","https://openalex.org/W2233753722","https://openalex.org/W2527334262","https://openalex.org/W3021680550","https://openalex.org/W3021908862","https://openalex.org/W6603388714","https://openalex.org/W6604987197","https://openalex.org/W6606722388"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2016904525"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"the":[3,34,37,54,61,69,72,88,98,107,111],"latest":[4],"improvements":[5],"on":[6,33,76],"our":[7],"Spectro":[8,89],"system":[9,90],"that":[10,82,93],"detects":[11],"transformed":[12],"duplicate":[13],"audio":[14,104],"content.":[15],"We":[16,40],"propose":[17],"a":[18,25,30,47,102],"new":[19,84],"binary":[20,43,66],"image":[21,44,67],"feature":[22,85],"derived":[23],"from":[24],"spectrogram":[26],"matrix":[27],"by":[28,45,119,124],"using":[29],"threshold":[31],"based":[32],"average":[35],"of":[36,49,56,64,71],"spectral":[38],"values.":[39],"quantize":[41],"this":[42,83],"applying":[46],"tile":[48],"fixed":[50],"size":[51],"and":[52,126],"computing":[53],"sum":[55],"each":[57,65],"small":[58],"square":[59],"in":[60,128],"tile.":[62],"Fingerprints":[63],"encode":[68],"positions":[70],"selected":[73],"tiles.":[74],"Evaluation":[75],"TRECVID":[77],"2010":[78],"CBCD":[79],"data":[80],"shows":[81],"improves":[86,121],"significantly":[87],"for":[91],"transformations":[92],"add":[94],"irrelevant":[95],"speech":[96],"to":[97,101],"audio.":[99],"Compared":[100],"state-of-the-art":[103],"fingerprinting":[105],"system,":[106],"proposed":[108],"method":[109],"reduces":[110],"minimal":[112],"Normalized":[113],"Detection":[114],"Cost":[115],"Rate":[116],"(min":[117],"NDCR)":[118],"33%,":[120],"localization":[122],"accuracy":[123],"28%":[125],"results":[127],"40%":[129],"fewer":[130],"missed":[131],"queries.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}