{"id":"https://openalex.org/W4207040625","doi":"https://doi.org/10.1109/tale52509.2021.9678624","title":"An Algorithm for Correcting Video-Audio Asynchronization Based on Syncnet","display_name":"An Algorithm for Correcting Video-Audio Asynchronization Based on Syncnet","publication_year":2021,"publication_date":"2021-12-05","ids":{"openalex":"https://openalex.org/W4207040625","doi":"https://doi.org/10.1109/tale52509.2021.9678624"},"language":"en","primary_location":{"id":"doi:10.1109/tale52509.2021.9678624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tale52509.2021.9678624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Engineering, Technology & Education (TALE)","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/A5005974148","display_name":"Runze Huang","orcid":"https://orcid.org/0000-0001-6640-6271"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Runze Huang","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076070940","display_name":"Chuanzhi Yang","orcid":"https://orcid.org/0009-0003-5752-7647"},"institutions":[{"id":"https://openalex.org/I196699116","display_name":"Wuhan University of Technology","ror":"https://ror.org/03fe7t173","country_code":"CN","type":"education","lineage":["https://openalex.org/I196699116"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanzhi Yang","raw_affiliation_strings":["School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Wuhan University of Technology, Wuhan, China","institution_ids":["https://openalex.org/I196699116"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110150777","display_name":"Xinguo Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinguo Yu","raw_affiliation_strings":["National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China","institution_ids":["https://openalex.org/I40963666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000223389","display_name":"Rao Peng","orcid":"https://orcid.org/0000-0003-1208-3950"},"institutions":[{"id":"https://openalex.org/I40963666","display_name":"Central China Normal University","ror":"https://ror.org/03x1jna21","country_code":"CN","type":"education","lineage":["https://openalex.org/I40963666"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rao Peng","raw_affiliation_strings":["National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Engineering Research Center for E-Learning, Central China Normal University, Wuhan, China","institution_ids":["https://openalex.org/I40963666"]}]}],"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":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"01","last_page":"04"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9983000159263611,"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":0.9983000159263611,"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":0.9965000152587891,"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":0.9955999851226807,"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":0.8405879139900208},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5860368609428406},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.5451003313064575},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5234365463256836},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5146580338478088},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.46411070227622986},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3870469331741333},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32946568727493286},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.24541637301445007},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.10593509674072266}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8405879139900208},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5860368609428406},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.5451003313064575},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234365463256836},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5146580338478088},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.46411070227622986},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3870469331741333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32946568727493286},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.24541637301445007},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.10593509674072266},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tale52509.2021.9678624","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tale52509.2021.9678624","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Engineering, Technology & Education (TALE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8700000047683716,"display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3494989179","display_name":null,"funder_award_id":"61977029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W185079915","https://openalex.org/W1932997869","https://openalex.org/W1988910659","https://openalex.org/W2108172568","https://openalex.org/W2152568403","https://openalex.org/W2157364932","https://openalex.org/W2164899449","https://openalex.org/W2167709189","https://openalex.org/W2191779130","https://openalex.org/W2342662179","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2950864153","https://openalex.org/W2963173190","https://openalex.org/W2963307811","https://openalex.org/W4250020524","https://openalex.org/W6684193366","https://openalex.org/W6687152286"],"related_works":["https://openalex.org/W2736574136","https://openalex.org/W2038216521","https://openalex.org/W2120877146","https://openalex.org/W4399693842","https://openalex.org/W2399955410","https://openalex.org/W3126677997","https://openalex.org/W2565286512","https://openalex.org/W2097377227","https://openalex.org/W2933782699","https://openalex.org/W3129283347"],"abstract_inverted_index":{"The":[0,142],"research":[1],"on":[2,78,102],"video-audio":[3,38,124],"synchronization":[4,93,125],"has":[5],"attracted":[6],"much":[7],"attention":[8],"in":[9,40],"recent":[10],"years.":[11],"With":[12],"the":[13,18,25,44,50,57,68,79,84,92,103,110,114,118,140,147],"popularity":[14],"of":[15,27,71,87,122,130],"online":[16,41],"education,":[17],"asynchrony":[19],"between":[20],"video":[21,45],"and":[22,29,52,60,64,127],"audio":[23],"affects":[24],"quality":[26],"teaching":[28],"learning.":[30],"This":[31],"paper":[32],"introduces":[33],"a":[34,72,97,106],"correction":[35,107,153],"algorithm":[36,149],"for":[37],"asynchronization":[39],"education.":[42],"First,":[43],"data":[46],"were":[47,136],"preprocessed":[48,80],"using":[49,96],"S3FD":[51],"Librosa":[53],"package":[54],"to":[55,82,138],"extract":[56],"lip":[58],"images":[59],"MFCC":[61],"as":[62],"visual":[63],"auditory":[65],"features;":[66],"then,":[67],"Syncnet,":[69],"consisting":[70],"two-stream":[73],"neural":[74],"network,":[75],"was":[76],"retrained":[77],"dataset":[81,126,135],"obtain":[83],"semantic":[85],"similarity":[86],"video-audio.":[88],"Next,":[89],"it":[90],"calculated":[91],"error":[94],"by":[95],"sliding":[98],"window":[99],"method":[100],"based":[101],"similarity.":[104],"Finally,":[105],"program":[108],"adopting":[109],"FFmpeg":[111],"framework":[112],"fixed":[113],"asynchronous":[115],"problem.":[116],"In":[117],"experiment,":[119],"300":[120],"hours":[121,129],"Chinese":[123,131],"20":[128],"live":[132],"classroom":[133],"record":[134],"collected":[137],"test":[139],"algorithm.":[141],"experimental":[143],"results":[144],"show":[145],"that":[146],"proposed":[148],"can":[150],"achieve":[151],"94%":[152],"accuracy.":[154]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}