{"id":"https://openalex.org/W7225198704","doi":"https://doi.org/10.20944/preprints202611.0124.v1","title":"Software Lip-Sync Metrics Do Not Predict Delivered Audio-Visual Synchronisation: A Photodiode and Line-Output Measurement of Talking-Head Video Playback Against ITU-R BT.1359-1","display_name":"Software Lip-Sync Metrics Do Not Predict Delivered Audio-Visual Synchronisation: A Photodiode and Line-Output Measurement of Talking-Head Video Playback Against ITU-R BT.1359-1","publication_year":2026,"publication_date":"2026-11-03","ids":{"openalex":"https://openalex.org/W7225198704","doi":"https://doi.org/10.20944/preprints202611.0124.v1"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202611.0124.v1","doi":"https://doi.org/10.20944/preprints202611.0124.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0124.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202611.0124.v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055764319","display_name":"Chien-ta Bruce Ho","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chien-Ta Bruce Ho","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5151559233","display_name":"XIYA LI","orcid":"https://orcid.org/0009-0004-4859-7907","observed_orcids":["https://orcid.org/0009-0004-4859-7907"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Xiya LI","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0004-4859-7907","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5151559233"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.4657999873161316,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12720","display_name":"Multimedia Communication and Technology","score":0.4657999873161316,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.4133000075817108,"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/T11165","display_name":"Image and Video Quality Assessment","score":0.07240000367164612,"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/photodiode-measurement","display_name":"photodiode measurement","score":0.6959999799728394},{"id":"https://openalex.org/keywords/video-playback","display_name":"video playback","score":0.3630000054836273}],"concepts":[{"id":"https://openalex.org/C175291020","wikidata":"https://www.wikidata.org/wiki/Q1156822","display_name":"Offset (computer science)","level":2,"score":0.631600022315979},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6189000010490417},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5295000076293945},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C751236","wikidata":"https://www.wikidata.org/wiki/Q175943","display_name":"Photodiode","level":2,"score":0.486299991607666},{"id":"https://openalex.org/C169345407","wikidata":"https://www.wikidata.org/wiki/Q8216221","display_name":"Uncorrelated","level":2,"score":0.4124000072479248},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37299999594688416},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.35569998621940613},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.33000001311302185},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3197999894618988},{"id":"https://openalex.org/C19619285","wikidata":"https://www.wikidata.org/wiki/Q196372","display_name":"Observational error","level":2,"score":0.31709998846054077},{"id":"https://openalex.org/C202799725","wikidata":"https://www.wikidata.org/wiki/Q272035","display_name":"Accuracy and precision","level":2,"score":0.299699991941452},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28299999237060547},{"id":"https://openalex.org/C2776962539","wikidata":"https://www.wikidata.org/wiki/Q6472078","display_name":"Lagging","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C2984499602","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Computer software","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C49319798","wikidata":"https://www.wikidata.org/wiki/Q5502874","display_name":"Frequency offset","level":4,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202611.0124.v1","doi":"https://doi.org/10.20944/preprints202611.0124.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0124.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202611.0124.v1","doi":"https://doi.org/10.20944/preprints202611.0124.v1","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202611.0124.v1","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2775105825","https://openalex.org/W2130694408","https://openalex.org/W7220964653","https://openalex.org/W1974789507","https://openalex.org/W3127899492","https://openalex.org/W1973667426","https://openalex.org/W2114654917","https://openalex.org/W1966708140","https://openalex.org/W4390872997","https://openalex.org/W2152716626"],"abstract_inverted_index":{"AI-generated":[0],"talking-head":[1],"video":[2],"is":[3,88],"certified":[4],"for":[5],"lip":[6],"synchronisation":[7],"with":[8,32,129,153,169],"file-based":[9],"metrics.":[10],"However,":[11],"the":[12,25,38,56,65,139,145,170,181,197],"governing":[13],"ITU-R":[14,140],"BT.1359-1":[15],"thresholds":[16,142],"derive":[17],"from":[18],"viewer":[19],"perception.":[20],"This":[21],"study":[22],"examined":[23],"whether":[24,42],"delivered":[26,122,190],"offset":[27,37,166],"can":[28,52],"be":[29,194],"measured":[30,195],"physically":[31],"a":[33,62,70],"stated":[34],"uncertainty,":[35],"what":[36],"systems":[39],"deliver,":[40],"and":[41,49,69,77,113,143,149],"SyncNet":[43],"lip-sync":[44],"error":[45],"scores,":[46],"distance":[47],"(LSE-D)":[48],"confidence":[50],"(LSE-C)":[51],"predict":[53,189],"it.":[54],"AOLSS,":[55],"Acoustic\u2013Optical":[57],"Latency":[58],"Sensing":[59],"System,":[60],"samples":[61],"photodiode":[63],"on":[64],"rendered":[66],"mouth":[67],"region":[68],"line-output":[71],"tap":[72],"simultaneously":[73],"at":[74,196],"20":[75],"kHz,":[76],"removes":[78],"calibrated":[79],"chain":[80],"latency":[81,98],"per":[82],"cell.":[83,134],"Inter-channel":[84],"uncertainty":[85],"(0.0144":[86],"ms)":[87],"negligible":[89],"beside":[90],"60":[91],"Hz":[92],"frame":[93],"quantisation":[94],"(4.81":[95],"ms).":[96],"Chain":[97],"spanned":[99],"\u221233.3":[100],"to":[101,126,163],"+31.3":[102],"ms,":[103,128,178],"changing":[104],"sign":[105],"between":[106],"players.":[107],"Over":[108],"four":[109],"systems,":[110],"three":[111],"players":[112],"two":[114],"resolutions":[115],"(24":[116],"cells,":[117],"3637":[118],"valid":[119],"trials),":[120],"median":[121],"offsets":[123],"were":[124,151],"\u2212210.9":[125],"\u221279.2":[127],"sound":[130],"lagging":[131],"in":[132,156],"every":[133,157],"60.9%\u201388.4%":[135],"of":[136,175],"trials":[137],"exceeded":[138],"detectability":[141],"31.6%\u201359.4%":[144],"acceptability":[146,183],"thresholds.":[147],"LSE-D":[148],"LSE-C":[150],"uncorrelated":[152],"delivered-offset":[154],"magnitude":[155],"player\u2013resolution":[158],"cell":[159],"(r":[160],"=":[161],"\u22120.066":[162],"+0.083).":[164],"SyncNet\u2019s":[165],"estimate":[167],"agreed":[168],"measurement":[171],"only":[172],"within":[173],"limits":[174],"half-width":[176],"282.2":[177],"1.5":[179],"times":[180],"wider":[182],"limit.":[184],"File-based":[185],"metrics":[186],"do":[187],"not":[188],"synchronisation,":[191],"which":[192],"must":[193],"output.":[198]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}
