{"id":"https://openalex.org/W4392904125","doi":"https://doi.org/10.1109/icassp48485.2024.10447306","title":"Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos","display_name":"Audio Match Cutting: Finding and Creating Matching Audio Transitions in Movies and Videos","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904125","doi":"https://doi.org/10.1109/icassp48485.2024.10447306"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447306","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.10998","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029784779","display_name":"Dennis Fedorishin","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]},{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["NL","US"],"is_corresponding":true,"raw_author_name":"Dennis Fedorishin","raw_affiliation_strings":["Dolby Laboratories","University at Buffalo"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]},{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110491600","display_name":"Lie Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I116121188","display_name":"Dolby (Netherlands)","ror":"https://ror.org/02kb3q578","country_code":"NL","type":"company","lineage":["https://openalex.org/I116121188","https://openalex.org/I4210093996"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lie Lu","raw_affiliation_strings":["Dolby Laboratories"],"affiliations":[{"raw_affiliation_string":"Dolby Laboratories","institution_ids":["https://openalex.org/I116121188"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036052557","display_name":"Srirangaraj Setlur","orcid":"https://orcid.org/0000-0002-7118-9280"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srirangaraj Setlur","raw_affiliation_strings":["University at Buffalo"],"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020354604","display_name":"Venu Govindaraju","orcid":"https://orcid.org/0000-0002-5318-7409"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Venu Govindaraju","raw_affiliation_strings":["University at Buffalo"],"affiliations":[{"raw_affiliation_string":"University at Buffalo","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5029784779"],"corresponding_institution_ids":["https://openalex.org/I116121188","https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.029063,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6200","last_page":"6204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9987000226974487,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.8496173024177551},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.814087986946106},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6282267570495605},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.5844233632087708},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.5678029656410217},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5489374995231628},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5257003307342529},{"id":"https://openalex.org/keywords/audio-mining","display_name":"Audio mining","score":0.5215437412261963},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.47319790720939636},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45411136746406555},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4470420479774475},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4283186197280884},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3786906599998474},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34491994976997375},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.33337581157684326},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.2240085005760193},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.17356964945793152},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.15284177660942078},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.11478018760681152}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8496173024177551},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.814087986946106},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6282267570495605},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.5844233632087708},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.5678029656410217},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5489374995231628},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5257003307342529},{"id":"https://openalex.org/C157968479","wikidata":"https://www.wikidata.org/wiki/Q3079876","display_name":"Audio mining","level":4,"score":0.5215437412261963},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.47319790720939636},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45411136746406555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4470420479774475},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4283186197280884},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3786906599998474},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34491994976997375},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.33337581157684326},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2240085005760193},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.17356964945793152},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.15284177660942078},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.11478018760681152},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447306","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp48485.2024.10447306","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.10998","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.10998","pdf_url":"https://arxiv.org/pdf/2408.10998","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.10998","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.10998","pdf_url":"https://arxiv.org/pdf/2408.10998","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":null,"license_id":null,"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/W4392904125.pdf"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W192605086","https://openalex.org/W1482507670","https://openalex.org/W1522301498","https://openalex.org/W2064469569","https://openalex.org/W2184630260","https://openalex.org/W2199613604","https://openalex.org/W2295559688","https://openalex.org/W2555897561","https://openalex.org/W2567701164","https://openalex.org/W2593116425","https://openalex.org/W2842511635","https://openalex.org/W2894398294","https://openalex.org/W2970491383","https://openalex.org/W3097567798","https://openalex.org/W3162472933","https://openalex.org/W3201594678","https://openalex.org/W3207894480","https://openalex.org/W4214771157","https://openalex.org/W4226442948","https://openalex.org/W4297808394","https://openalex.org/W4312300358","https://openalex.org/W4313179528","https://openalex.org/W4319299823","https://openalex.org/W4320517409","https://openalex.org/W4323323114","https://openalex.org/W4372260310","https://openalex.org/W4386071707","https://openalex.org/W6631190155","https://openalex.org/W6687722484","https://openalex.org/W6690107225","https://openalex.org/W6697348743","https://openalex.org/W6730323794","https://openalex.org/W6850721663"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W2494533082","https://openalex.org/W4214771044","https://openalex.org/W4382560817","https://openalex.org/W4387698063","https://openalex.org/W1975359510","https://openalex.org/W1611900921","https://openalex.org/W1969715806","https://openalex.org/W3004352674","https://openalex.org/W1620668332"],"abstract_inverted_index":{"A":[0],"\"match":[1],"cut\"":[2],"is":[3],"a":[4,10,16,74,84,101,140],"common":[5],"video":[6],"editing":[7],"technique":[8],"where":[9,40],"pair":[11],"of":[12,38,114,138],"shots":[13,92],"that":[14,89],"have":[15],"similar":[17],"composition":[18],"transition":[19,37,49],"fluidly":[20],"from":[21,42],"one":[22,47],"to":[23,60,118,129],"another.":[24],"Although":[25],"match":[26,32,66,80,87,107,121],"cuts":[27,33],"are":[28,147],"often":[29],"visual,":[30],"certain":[31],"involve":[34],"the":[35,58,95,104,112,136],"fluid":[36],"audio,":[39],"sounds":[41],"different":[43],"sources":[44],"merge":[45],"into":[46],"indistinguishable":[48],"between":[50],"two":[51,131],"shots.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56,125],"explore":[57],"ability":[59,113],"automatically":[61],"find":[62,119],"and":[63,70,82,93,110,145],"create":[64,73],"\"audio":[65],"cuts\"":[67],"within":[68],"videos":[69],"movies.":[71],"We":[72,98],"self-supervised":[75],"audio":[76,79,86,106,116,120,133],"representation":[77],"for":[78,103],"cutting":[81],"develop":[83],"coarse-to-fine":[85],"pipeline":[88],"recommends":[90],"matching":[91,132],"creates":[94],"blended":[96],"audio.":[97],"further":[99],"annotate":[100],"dataset":[102],"proposed":[105],"cut":[108,122],"task":[109],"compare":[111],"multiple":[115,127],"representations":[117],"candidates.":[123],"Finally,":[124],"evaluate":[126],"methods":[128],"blend":[130],"candidates":[134],"with":[135],"goal":[137],"creating":[139],"smooth":[141],"transition.":[142],"Project":[143],"page":[144],"examples":[146],"available":[148],"at:":[149],"https://denfed.github.io/audiomatchcut/":[150]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}
