{"id":"https://openalex.org/W4400113230","doi":"https://doi.org/10.1109/mipro60963.2024.10569239","title":"Application of Audio Fingerprinting Techniques for Real-Time Scalable Speech Retrieval and Speech Clusterization","display_name":"Application of Audio Fingerprinting Techniques for Real-Time Scalable Speech Retrieval and Speech Clusterization","publication_year":2024,"publication_date":"2024-05-20","ids":{"openalex":"https://openalex.org/W4400113230","doi":"https://doi.org/10.1109/mipro60963.2024.10569239"},"language":"en","primary_location":{"id":"doi:10.1109/mipro60963.2024.10569239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mipro60963.2024.10569239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 47th MIPRO ICT and Electronics Convention (MIPRO)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2410.21876","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069779706","display_name":"Kemal Altwlkany","orcid":"https://orcid.org/0000-0002-7313-2800"},"institutions":[{"id":"https://openalex.org/I104817121","display_name":"University of Sarajevo","ror":"https://ror.org/02hhwgd43","country_code":"BA","type":"education","lineage":["https://openalex.org/I104817121"]}],"countries":["BA"],"is_corresponding":true,"raw_author_name":"Kemal Altwlkany","raw_affiliation_strings":["University of Sarajevo,Faculty of Science,Bosnia and Herzegovina"],"affiliations":[{"raw_affiliation_string":"University of Sarajevo,Faculty of Science,Bosnia and Herzegovina","institution_ids":["https://openalex.org/I104817121"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016897347","display_name":"Sead Delali\u0107","orcid":"https://orcid.org/0000-0002-3720-191X"},"institutions":[{"id":"https://openalex.org/I104817121","display_name":"University of Sarajevo","ror":"https://ror.org/02hhwgd43","country_code":"BA","type":"education","lineage":["https://openalex.org/I104817121"]}],"countries":["BA"],"is_corresponding":false,"raw_author_name":"Sead Delali\u0107","raw_affiliation_strings":["University of Sarajevo,Faculty of Science,Bosnia and Herzegovina"],"affiliations":[{"raw_affiliation_string":"University of Sarajevo,Faculty of Science,Bosnia and Herzegovina","institution_ids":["https://openalex.org/I104817121"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035328178","display_name":"Adis Alihod\u017ei\u0107","orcid":"https://orcid.org/0000-0003-0761-1667"},"institutions":[{"id":"https://openalex.org/I104817121","display_name":"University of Sarajevo","ror":"https://ror.org/02hhwgd43","country_code":"BA","type":"education","lineage":["https://openalex.org/I104817121"]}],"countries":["BA"],"is_corresponding":false,"raw_author_name":"Adis Alihod\u017ei\u0107","raw_affiliation_strings":["University of Sarajevo,Faculty of Science,Bosnia and Herzegovina"],"affiliations":[{"raw_affiliation_string":"University of Sarajevo,Faculty of Science,Bosnia and Herzegovina","institution_ids":["https://openalex.org/I104817121"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030349012","display_name":"Elmedin Selmanovi\u0107","orcid":"https://orcid.org/0000-0003-4245-3588"},"institutions":[{"id":"https://openalex.org/I104817121","display_name":"University of Sarajevo","ror":"https://ror.org/02hhwgd43","country_code":"BA","type":"education","lineage":["https://openalex.org/I104817121"]}],"countries":["BA"],"is_corresponding":false,"raw_author_name":"Elmedin Selmanovi\u0107","raw_affiliation_strings":["University of Sarajevo,Faculty of Science,Bosnia and Herzegovina"],"affiliations":[{"raw_affiliation_string":"University of Sarajevo,Faculty of Science,Bosnia and Herzegovina","institution_ids":["https://openalex.org/I104817121"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030122767","display_name":"Damir Hasi\u0107","orcid":"https://orcid.org/0000-0002-4756-3092"},"institutions":[{"id":"https://openalex.org/I104817121","display_name":"University of Sarajevo","ror":"https://ror.org/02hhwgd43","country_code":"BA","type":"education","lineage":["https://openalex.org/I104817121"]}],"countries":["BA"],"is_corresponding":false,"raw_author_name":"Damir Hasi\u0107","raw_affiliation_strings":["University of Sarajevo,Faculty of Science,Bosnia and Herzegovina"],"affiliations":[{"raw_affiliation_string":"University of Sarajevo,Faculty of Science,Bosnia and Herzegovina","institution_ids":["https://openalex.org/I104817121"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5069779706"],"corresponding_institution_ids":["https://openalex.org/I104817121"],"apc_list":null,"apc_paid":null,"fwci":0.366,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.52592358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"2003","issue":null,"first_page":"91","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9970999956130981,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8292615413665771},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7119567394256592},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6230776906013489},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.5479710698127747},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.4674243628978729},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.46490490436553955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41308867931365967},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.37865203619003296},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3465481996536255},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09214568138122559}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8292615413665771},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7119567394256592},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6230776906013489},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.5479710698127747},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.4674243628978729},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.46490490436553955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41308867931365967},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.37865203619003296},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3465481996536255},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09214568138122559}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mipro60963.2024.10569239","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/mipro60963.2024.10569239","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 47th MIPRO ICT and Electronics Convention (MIPRO)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2410.21876","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.21876","pdf_url":"https://arxiv.org/pdf/2410.21876","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2410.21876","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2410.21876","pdf_url":"https://arxiv.org/pdf/2410.21876","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4400113230.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W83334756","https://openalex.org/W1494198834","https://openalex.org/W1502916507","https://openalex.org/W1673310716","https://openalex.org/W1973746598","https://openalex.org/W1980372924","https://openalex.org/W1984076147","https://openalex.org/W2023854218","https://openalex.org/W2026609075","https://openalex.org/W2048779798","https://openalex.org/W2068272887","https://openalex.org/W2070597833","https://openalex.org/W2104160358","https://openalex.org/W2132984323","https://openalex.org/W2166442947","https://openalex.org/W2290143097","https://openalex.org/W2299467264","https://openalex.org/W2559809918","https://openalex.org/W2770078645","https://openalex.org/W2964227577","https://openalex.org/W2998702515","https://openalex.org/W3021908862","https://openalex.org/W3096032230","https://openalex.org/W4210847411","https://openalex.org/W4242138061","https://openalex.org/W4319862635","https://openalex.org/W4372189025","https://openalex.org/W4378105483","https://openalex.org/W4385245566","https://openalex.org/W6601916772","https://openalex.org/W6602935006","https://openalex.org/W6603388714","https://openalex.org/W6604987197","https://openalex.org/W6626419732","https://openalex.org/W6629956336","https://openalex.org/W6631362777","https://openalex.org/W6637131181","https://openalex.org/W6653477362","https://openalex.org/W6678914141","https://openalex.org/W6746315785","https://openalex.org/W6847363464","https://openalex.org/W6852909395"],"related_works":["https://openalex.org/W2496295964","https://openalex.org/W642007152","https://openalex.org/W1911859126","https://openalex.org/W46679383","https://openalex.org/W2056066842","https://openalex.org/W2131711534","https://openalex.org/W2184127972","https://openalex.org/W2343205865","https://openalex.org/W2341426843","https://openalex.org/W2009814707"],"abstract_inverted_index":{"Audio":[0],"fingerprinting":[1,80],"techniques":[2,90],"have":[3],"seen":[4],"great":[5],"advances":[6],"in":[7,17,30,99,115],"recent":[8],"years,":[9],"enabling":[10],"accurate":[11,112],"and":[12,101,111],"fast":[13],"audio":[14,22,59,79,113,140],"retrieval":[15,98,114],"even":[16],"conditions":[18],"when":[19],"the":[20,36,65,93,129,158],"queried":[21],"sample":[23],"has":[24],"been":[25],"highly":[26],"deteriorated":[27],"or":[28,52],"recorded":[29],"noisy":[31],"conditions.":[32],"Expectedly,":[33],"most":[34],"of":[35,68,73,96,119],"existing":[37,89],"work":[38],"is":[39,107,169],"centered":[40],"around":[41],"music,":[42,74],"with":[43,172],"popular":[44],"music":[45],"identification":[46],"services":[47],"such":[48],"as":[49],"Apple\u2019s":[50],"Shazam":[51],"Google\u2019s":[53],"Now":[54],"Playing":[55],"designed":[56],"for":[57,160,165],"individual":[58],"recognition":[60],"on":[61,108,124,143],"mobile":[62],"devices.":[63],"However,":[64],"spectral":[66],"content":[67],"speech":[69,97,144],"differs":[70],"from":[71],"that":[72,168],"necessitating":[75],"modifications":[76],"to":[77,91,138],"current":[78],"approaches.":[81],"This":[82,151],"paper":[83,130],"offers":[84],"fresh":[85],"insights":[86],"into":[87],"adapting":[88],"address":[92],"specialized":[94],"challenge":[95],"telecommunications":[100],"cloud":[102],"communications":[103],"platforms.":[104],"The":[105],"focus":[106],"achieving":[109],"rapid":[110],"batch":[116],"processing":[117,156],"instead":[118],"facilitating":[120],"single":[121],"requests,":[122],"typically":[123,170],"a":[125,163],"centralized":[126],"server.":[127],"Moreover,":[128],"demonstrates":[131],"how":[132],"this":[133],"approach":[134],"can":[135],"be":[136],"utilized":[137],"support":[139],"clustering":[141],"based":[142],"transcripts":[145],"without":[146,157],"undergoing":[147],"actual":[148],"speech-to-text":[149,174],"conversion.":[150],"optimization":[152],"enables":[153],"significantly":[154],"faster":[155],"need":[159],"GPU":[161],"computing,":[162],"requirement":[164],"real-time":[166],"operation":[167],"associated":[171],"state-of-the-art":[173],"tools.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-03-11T14:59:36.786465","created_date":"2025-10-10T00:00:00"}