{"id":"https://openalex.org/W4384080302","doi":"https://doi.org/10.1109/tmc.2023.3294416","title":"Acoustic-Based Lip Reading for Mobile Devices: Dataset, Benchmark and a Self Distillation-Based Approach","display_name":"Acoustic-Based Lip Reading for Mobile Devices: Dataset, Benchmark and a Self Distillation-Based Approach","publication_year":2023,"publication_date":"2023-07-12","ids":{"openalex":"https://openalex.org/W4384080302","doi":"https://doi.org/10.1109/tmc.2023.3294416"},"language":"en","primary_location":{"id":"doi:10.1109/tmc.2023.3294416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3294416","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-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/A5087888694","display_name":"Yafeng Yin","orcid":"https://orcid.org/0000-0002-9497-6244"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yafeng Yin","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-9497-6244","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401181","display_name":"Zheng Wang","orcid":"https://orcid.org/0009-0003-4930-6254"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0009-0003-4930-6254","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100333950","display_name":"Kang Xia","orcid":"https://orcid.org/0000-0002-5453-0643"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Xia","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-5453-0643","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365442","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0002-2994-6743"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0002-2994-6743","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043533769","display_name":"Sanglu Lu","orcid":"https://orcid.org/0000-0003-1467-4519"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sanglu Lu","raw_affiliation_strings":["State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China"],"raw_orcid":"https://orcid.org/0000-0003-1467-4519","affiliations":[{"raw_affiliation_string":"State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, Jiangsu, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":2.0082,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.8749149,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"23","issue":"5","first_page":"4548","last_page":"4565"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9381999969482422,"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/T13289","display_name":"Infant Health and Development","score":0.9046000242233276,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6989350318908691},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.6950733065605164},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6841389536857605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5180192589759827},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5053958892822266},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33495837450027466}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6989350318908691},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.6950733065605164},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6841389536857605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5180192589759827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5053958892822266},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33495837450027466},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","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/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmc.2023.3294416","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmc.2023.3294416","pdf_url":null,"source":{"id":"https://openalex.org/S69141925","display_name":"IEEE Transactions on Mobile Computing","issn_l":"1536-1233","issn":["1536-1233","1558-0660","2161-9875"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Mobile Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G2637000964","display_name":null,"funder_award_id":"62272216","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3267722479","display_name":"\u81ea\u4e3b\u534f\u540c\u7684\u591a\u6a21\u6001\u611f\u77e5\u53ca\u878d\u5408\u673a\u5236\u7814\u7a76","funder_award_id":"61832008","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3757583711","display_name":null,"funder_award_id":"62172208","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5242701248","display_name":null,"funder_award_id":"BE2020001-4","funder_id":"https://openalex.org/F4320327777","funder_display_name":"Jiangsu Provincial Key Research and Development Program"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327777","display_name":"Jiangsu Provincial Key Research and Development Program","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W36949327","https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W2008208523","https://openalex.org/W2015143272","https://openalex.org/W2029199293","https://openalex.org/W2115144768","https://openalex.org/W2153200718","https://openalex.org/W2194775991","https://openalex.org/W2267805933","https://openalex.org/W2344757691","https://openalex.org/W2508345357","https://openalex.org/W2509287561","https://openalex.org/W2551572271","https://openalex.org/W2561238782","https://openalex.org/W2565622304","https://openalex.org/W2570575067","https://openalex.org/W2594690981","https://openalex.org/W2764166175","https://openalex.org/W2768061942","https://openalex.org/W2769004781","https://openalex.org/W2791862028","https://openalex.org/W2793257307","https://openalex.org/W2895165153","https://openalex.org/W2897318954","https://openalex.org/W2905699130","https://openalex.org/W2935290040","https://openalex.org/W2964283370","https://openalex.org/W2972418643","https://openalex.org/W2981441441","https://openalex.org/W2987861506","https://openalex.org/W3004196347","https://openalex.org/W3010673682","https://openalex.org/W3083703874","https://openalex.org/W3087417110","https://openalex.org/W3144915432","https://openalex.org/W3174422325","https://openalex.org/W4226050909","https://openalex.org/W4226072813","https://openalex.org/W4296473379","https://openalex.org/W4298112588","https://openalex.org/W4312771235","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638523607","https://openalex.org/W6684191040","https://openalex.org/W6730179637","https://openalex.org/W6732872814"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W972276598","https://openalex.org/W4246352526","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W2087343574","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Speech":[0],"is":[1],"a":[2,9,91,144,201],"natural":[3],"communication":[4],"way":[5,11],"between":[6],"people":[7],"and":[8,70,89,127,158,177,214],"good":[10,202],"for":[12,74,139,166,205],"human-computer":[13],"interaction.":[14],"However,":[15],"speech":[16,40,50],"with":[17,99],"audible":[18],"voices":[19],"often":[20],"faces":[21],"the":[22,32,78,105,155],"following":[23],"problems,":[24],"e.g.,":[25],"being":[26],"affected":[27],"by":[28],"surrounding":[29],"noises,":[30],"breaking":[31],"quiet":[33],"environment,":[34],"leaking":[35],"privacy,":[36],"etc.":[37],"Therefore,":[38],"silent":[39],"was":[41],"proposed,":[42],"especially":[43],"lip":[44,54,72,75,85,109,140,206],"reading,":[45,86,110,141,207],"which":[46,153],"aims":[47],"to":[48,68],"recognize":[49,71,133],"content":[51],"based":[52,147],"on":[53,115,175,180],"movements.":[55],"In":[56],"this":[57],"paper,":[58],"we":[59,87,111,142,170],"utilize":[60],"inaudible":[61],"acoustic":[62,135],"signals":[63,136],"generated":[64],"from":[65],"mobile":[66],"device":[67],"sense":[69],"movements":[73],"reading.":[76],"Considering":[77],"lack":[79],"of":[80],"public":[81],"dataset":[82,94,185],"in":[83,108,161],"acoustic-based":[84,101],"propose":[88,143],"release":[90],"large-scale":[92],"lip-reading":[93],"<inline-formula":[95,116,181],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[96,117,150,173,182,197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math>${\\sf":[97,118,183],"LIPCMD}$</tex-math></inline-formula>":[98,119,184],"30000":[100],"recordings.":[102],"To":[103,132],"advance":[104],"further":[106],"research":[107],"provide":[112],"benchmark":[113],"evaluation":[114],",":[120,152],"while":[121,210],"using":[122],"traditional":[123],"machine":[124],"learning":[125,130],"solutions":[126,213],"recent":[128],"deep":[129],"approaches.":[131],"weak":[134],"as":[137,186,188],"words":[138],"self":[145],"distillation":[146],"approach":[148],"<italic":[149,172,196],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">LipReader</i>":[151,174,198],"distills":[154],"probability":[156],"distribution":[157],"attention":[159],"map":[160],"convolutional":[162],"neural":[163],"network":[164],"itself":[165],"better":[167],"classification.":[168],"Finally,":[169],"implement":[171],"smartphone":[176],"evaluate":[178],"it":[179],"well":[187],"under":[189],"complex":[190],"scenarios.":[191],"Experimental":[192],"results":[193],"show":[194],"that":[195],"can":[199],"achieve":[200],"recognition":[203],"accuracy":[204],"i.e.,":[208],"91.58%,":[209],"outperforming":[211],"baseline":[212],"existing":[215],"work.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":4}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}