{"id":"https://openalex.org/W4416252255","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228396","title":"InfoSyncNet: Information Synchronization Temporal Convolutional Network for Visual Speech Recognition","display_name":"InfoSyncNet: Information Synchronization Temporal Convolutional Network for Visual Speech Recognition","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4416252255","doi":"https://doi.org/10.1109/ijcnn64981.2025.11228396"},"language":null,"primary_location":{"id":"doi:10.1109/ijcnn64981.2025.11228396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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/A5051556369","display_name":"Junxiao Xue","orcid":"https://orcid.org/0000-0003-1569-5362"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Junxiao Xue","raw_affiliation_strings":["Zhengzhou University,School of Cyber Science and Engineering,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhengzhou University,School of Cyber Science and Engineering,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101914049","display_name":"Xiaozhen Liu","orcid":"https://orcid.org/0000-0001-8901-5804"},"institutions":[{"id":"https://openalex.org/I38877650","display_name":"Zhengzhou University","ror":"https://ror.org/04ypx8c21","country_code":"CN","type":"education","lineage":["https://openalex.org/I38877650"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaozhen Liu","raw_affiliation_strings":["Zhengzhou University,School of Cyber Science and Engineering,Zhengzhou,China"],"affiliations":[{"raw_affiliation_string":"Zhengzhou University,School of Cyber Science and Engineering,Zhengzhou,China","institution_ids":["https://openalex.org/I38877650"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053734709","display_name":"Xuecheng Wu","orcid":"https://orcid.org/0000-0001-9897-8776"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuecheng Wu","raw_affiliation_strings":["Xi&#x2019;an Jiaotong University,School of Computer Science and Technology,Xi&#x2019;an,China"],"affiliations":[{"raw_affiliation_string":"Xi&#x2019;an Jiaotong University,School of Computer Science and Technology,Xi&#x2019;an,China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420016","display_name":"F. Richard Yu","orcid":"https://orcid.org/0000-0003-1006-7594"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yu","raw_affiliation_strings":["Research Center for Space Computing System,Zhejiang Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Research Center for Space Computing System,Zhejiang Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100712167","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-9548-0411"},"institutions":[{"id":"https://openalex.org/I4210123185","display_name":"Zhejiang Lab","ror":"https://ror.org/02m2h7991","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210123185"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Research Center for Space Computing System,Zhejiang Lab,Hangzhou,China"],"affiliations":[{"raw_affiliation_string":"Research Center for Space Computing System,Zhejiang Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210123185"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5051556369"],"corresponding_institution_ids":["https://openalex.org/I38877650"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.4559387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.963100016117096,"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/T10860","display_name":"Speech and Audio Processing","score":0.963100016117096,"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/T11448","display_name":"Face recognition and analysis","score":0.016899999231100082,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.004100000020116568,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6280999779701233},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5533999800682068},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5194000005722046},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.49160000681877136},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4408000111579895},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.42879998683929443},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.3718000054359436},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3580000102519989},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3384999930858612}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022000193595886},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6280999779701233},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5878000259399414},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5533999800682068},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5194000005722046},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5031999945640564},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.49160000681877136},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3718000054359436},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3285999894142151},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3199000060558319},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3190000057220459},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.30140000581741333},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C153715457","wikidata":"https://www.wikidata.org/wiki/Q254183","display_name":"Augmented reality","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2696000039577484},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C108734733","wikidata":"https://www.wikidata.org/wiki/Q1172333","display_name":"Data synchronization","level":3,"score":0.25679999589920044}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn64981.2025.11228396","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn64981.2025.11228396","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Joint Conference on Neural Networks (IJCNN)","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":34,"referenced_works":["https://openalex.org/W1983364832","https://openalex.org/W2117539524","https://openalex.org/W2129360799","https://openalex.org/W2550143307","https://openalex.org/W2594690981","https://openalex.org/W2752782242","https://openalex.org/W2883780447","https://openalex.org/W2890952074","https://openalex.org/W2897318954","https://openalex.org/W2897492880","https://openalex.org/W2963446712","https://openalex.org/W2963616706","https://openalex.org/W2963654155","https://openalex.org/W2981501041","https://openalex.org/W3015689952","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3119418740","https://openalex.org/W3128564814","https://openalex.org/W3149793578","https://openalex.org/W3162707322","https://openalex.org/W4224319127","https://openalex.org/W4224931249","https://openalex.org/W4225299282","https://openalex.org/W4225305629","https://openalex.org/W4246193833","https://openalex.org/W4308222710","https://openalex.org/W4312975593","https://openalex.org/W4319300051","https://openalex.org/W4322707285","https://openalex.org/W4372260478","https://openalex.org/W4375869361","https://openalex.org/W4396768628","https://openalex.org/W4402351619"],"related_works":[],"abstract_inverted_index":{"Estimating":[0],"spoken":[1],"content":[2],"from":[3],"silent":[4],"videos":[5,25],"is":[6,65],"crucial":[7],"for":[8],"applications":[9],"in":[10,24,89,107],"Assistive":[11],"Technology":[12],"(AT)":[13],"and":[14,36,74,83,109,118,132],"Augmented":[15],"Reality":[16],"(AR).":[17],"However,":[18],"accurately":[19],"mapping":[20],"lip":[21],"movement":[22],"sequences":[23,35],"to":[26,32,63,79,99,104],"words":[27],"poses":[28],"significant":[29],"challenges":[30],"due":[31],"variability":[33],"across":[34],"the":[37,72,80,86,101,110,116,122],"uneven":[38],"distribution":[39],"of":[40,124,130],"information":[41],"within":[42],"each":[43],"sequence.":[44],"To":[45],"tackle":[46],"this,":[47],"we":[48],"introduce":[49],"InfoSyncNet,":[50,125],"a":[51,66],"non-uniform":[52,67],"sequence":[53],"modeling":[54],"network":[55],"enhanced":[56],"by":[57],"tailored":[58],"data":[59],"augmentation":[60],"techniques.":[61],"Central":[62],"InfoSyncNet":[64],"quantization":[68],"module":[69],"positioned":[70],"between":[71],"encoder":[73],"decoder,":[75],"enabling":[76],"dynamic":[77],"adjustment":[78],"network\u2019s":[81],"focus":[82],"effectively":[84],"handling":[85],"natural":[87],"inconsistencies":[88],"visual":[90],"speech":[91],"data.":[92],"Additionally,":[93],"multiple":[94],"training":[95],"strategies":[96],"are":[97],"incorporated":[98],"enhance":[100],"model\u2019s":[102],"capability":[103],"handle":[105],"variations":[106],"lighting":[108],"speaker\u2019s":[111],"orientation.":[112],"Comprehensive":[113],"experiments":[114],"on":[115],"LRW":[117],"LRW1000":[119],"datasets":[120],"confirm":[121],"superiority":[123],"achieving":[126],"new":[127],"state-of-the-art":[128],"accuracies":[129],"92.0%":[131],"60.7%":[133],"Top-1":[134],"ACC":[135],"<sup":[136],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[137],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[138]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-14T00:00:00"}