{"id":"https://openalex.org/W4392903590","doi":"https://doi.org/10.1109/icassp48485.2024.10446453","title":"The Collaboration of 3D Convolutions and CRO-TSM in Lipreading","display_name":"The Collaboration of 3D Convolutions and CRO-TSM in Lipreading","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903590","doi":"https://doi.org/10.1109/icassp48485.2024.10446453"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446453","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":["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/A5057733954","display_name":"Yangzhao Xiang","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yangzhao Xiang","raw_affiliation_strings":["School of Software, Xinjiang University,Ürümqi,China,830046"],"affiliations":[{"raw_affiliation_string":"School of Software, Xinjiang University,Ürümqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017734892","display_name":"Mutellip Mamut","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mutellip Mamut","raw_affiliation_strings":["Library of Xinjiang University,Ürümqi,China,830046"],"affiliations":[{"raw_affiliation_string":"Library of Xinjiang University,Ürümqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000215170","display_name":"Nurbiya Yadikar","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Nurbiya Yadikar","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Ürümqi,China,830046"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Ürümqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033270442","display_name":"Ghalipjan Ibrahim","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ghalipjan Ibrahim","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Ürümqi,China,830046"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Ürümqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066506917","display_name":"Kurban Ubul","orcid":"https://orcid.org/0000-0002-7566-6494"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kurban Ubul","raw_affiliation_strings":["School of Computer Science and Technology, Xinjiang University,Ürümqi,China,830046"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology, Xinjiang University,Ürümqi,China,830046","institution_ids":["https://openalex.org/I96908189"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5057733954"],"corresponding_institution_ids":["https://openalex.org/I96908189"],"apc_list":null,"apc_paid":null,"fwci":1.884,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85040424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4890","last_page":"4894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech 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/T10860","display_name":"Speech 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/T10326","display_name":"Indoor and Outdoor Localization Technologies","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"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/T11309","display_name":"Music and Audio Processing","score":0.977400004863739,"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/pooling","display_name":"Pooling","score":0.8516141176223755},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853622436523438},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6501202583312988},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5237169861793518},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.48528334498405457},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4812309741973877},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45037898421287537},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42143484950065613},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06993389129638672}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.8516141176223755},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853622436523438},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6501202583312988},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5237169861793518},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.48528334498405457},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4812309741973877},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45037898421287537},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42143484950065613},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06993389129638672},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446453","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446453","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2096391593","https://openalex.org/W2121486117","https://openalex.org/W2194775991","https://openalex.org/W2594690981","https://openalex.org/W2604379605","https://openalex.org/W2605246626","https://openalex.org/W2893436174","https://openalex.org/W2898926657","https://openalex.org/W2963528589","https://openalex.org/W2963654155","https://openalex.org/W2990152177","https://openalex.org/W3016011581","https://openalex.org/W3035042697","https://openalex.org/W3119418740","https://openalex.org/W3128564814","https://openalex.org/W3128750130","https://openalex.org/W3162707322","https://openalex.org/W3163064317","https://openalex.org/W4225299282"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Lip":[0],"reading":[1,25],"refers":[2],"to":[3,94,104],"the":[4,11,15,49,70,78,83,105,116],"recognition":[5],"of":[6,14,82,113],"speech":[7],"solely":[8],"based":[9,68],"on":[10,69,115],"subtle":[12],"movements":[13],"lips":[16],"without":[17],"audio":[18],"information.":[19,45,98],"Extracting":[20],"temporal":[21,44,66,97],"information":[22],"in":[23,31,90,133],"lip":[24],"has":[26],"always":[27],"been":[28],"a":[29,55,110,129],"challenge":[30],"this":[32,35,102],"field.":[33],"In":[34],"work,":[36],"we":[37,47,76,100],"propose":[38,54],"an":[39],"effective":[40],"method":[41,103],"for":[42,65],"extracting":[43],"Specifically,":[46],"make":[48],"following":[50],"contributions:":[51],"Firstly,":[52],"We":[53],"new":[56,130],"approach":[57,122],"called":[58],"cro-TSM,":[59],"which":[60,88],"utilizes":[61],"different":[62],"channel":[63],"ratios":[64],"shifting":[67],"existing":[71],"TSM(Temporal":[72],"Shift":[73],"Module).":[74],"Secondly,":[75],"replace":[77],"global":[79],"average":[80],"pooling":[81],"ResNet":[84],"with":[85,92],"3D":[86],"convolutions,":[87],"work":[89],"collaboration":[91],"cro-TSM":[93],"extract":[95],"additional":[96],"Lastly,":[99],"apply":[101],"state-of-the-art":[106,131],"models":[107],"and":[108,127],"achieve":[109],"remarkable":[111],"accuracy":[112],"92.4%":[114],"Lipreading":[117],"In-The-Wild":[118],"(LRW)":[119],"dataset.":[120],"Our":[121],"surpasses":[123],"all":[124],"baseline":[125],"methods":[126],"achieves":[128],"performance":[132],"Lipreading.":[134]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}