{"id":"https://openalex.org/W4394782978","doi":"https://doi.org/10.1145/3639592.3639623","title":"Multi-stage Multi-modalities Fusion of Lip, Tongue and Acoustics Information for Speech Recognition","display_name":"Multi-stage Multi-modalities Fusion of Lip, Tongue and Acoustics Information for Speech Recognition","publication_year":2023,"publication_date":"2023-12-16","ids":{"openalex":"https://openalex.org/W4394782978","doi":"https://doi.org/10.1145/3639592.3639623"},"language":"en","primary_location":{"id":"doi:10.1145/3639592.3639623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639592.3639623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th Artificial Intelligence and Cloud Computing Conference (AICCC)","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/A5101857376","display_name":"Xuening Wang","orcid":"https://orcid.org/0009-0009-5266-6115"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuening Wang","raw_affiliation_strings":["School of Computer and Artificial Intelligence of Beijing Technology and Business University, China"],"raw_orcid":"https://orcid.org/0009-0009-5266-6115","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence of Beijing Technology and Business University, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074188184","display_name":"Zhaopeng Qian","orcid":"https://orcid.org/0000-0003-0743-0700"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaopeng Qian","raw_affiliation_strings":["School of Computer and Artificial Intelligence of Beijing Technology and Business University, China"],"raw_orcid":"https://orcid.org/0000-0003-0743-0700","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence of Beijing Technology and Business University, China","institution_ids":["https://openalex.org/I179026463"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075985115","display_name":"Chongchong Yu","orcid":"https://orcid.org/0000-0003-4234-1260"},"institutions":[{"id":"https://openalex.org/I179026463","display_name":"Beijing Technology and Business University","ror":"https://ror.org/013e0zm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I179026463"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chongchong Yu","raw_affiliation_strings":["School of Computer and Artificial Intelligence of Beijing Technology and Business University, China"],"raw_orcid":"https://orcid.org/0000-0003-4234-1260","affiliations":[{"raw_affiliation_string":"School of Computer and Artificial Intelligence of Beijing Technology and Business University, China","institution_ids":["https://openalex.org/I179026463"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I179026463"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.28976341,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"231"},"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/T11448","display_name":"Face recognition and analysis","score":0.9959999918937683,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9733999967575073,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/pronunciation","display_name":"Pronunciation","score":0.815231442451477},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8072685599327087},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7916291952133179},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.6190015077590942},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5628580451011658},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5594073534011841},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49617800116539},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4451886713504791},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4389582872390747},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.43131422996520996},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.42708820104599}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.815231442451477},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8072685599327087},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7916291952133179},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.6190015077590942},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5628580451011658},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5594073534011841},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49617800116539},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4451886713504791},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4389582872390747},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.43131422996520996},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.42708820104599},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3639592.3639623","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3639592.3639623","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 6th Artificial Intelligence and Cloud Computing Conference (AICCC)","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":33,"referenced_works":["https://openalex.org/W1967225830","https://openalex.org/W1987337335","https://openalex.org/W1995735739","https://openalex.org/W2008120082","https://openalex.org/W2009357672","https://openalex.org/W2087681821","https://openalex.org/W2109272898","https://openalex.org/W2295119550","https://openalex.org/W2397670449","https://openalex.org/W2401960014","https://openalex.org/W2427345690","https://openalex.org/W2768153200","https://openalex.org/W2769531941","https://openalex.org/W2905699130","https://openalex.org/W2941048526","https://openalex.org/W2963272864","https://openalex.org/W2963522845","https://openalex.org/W2963787388","https://openalex.org/W2963979492","https://openalex.org/W2964172053","https://openalex.org/W2996970093","https://openalex.org/W3016011581","https://openalex.org/W3112616666","https://openalex.org/W3122100772","https://openalex.org/W3143787022","https://openalex.org/W3160799772","https://openalex.org/W3196749493","https://openalex.org/W3198275944","https://openalex.org/W4206963459","https://openalex.org/W4299508085","https://openalex.org/W4310348293","https://openalex.org/W4360993686","https://openalex.org/W4375869379"],"related_works":["https://openalex.org/W3000097931","https://openalex.org/W2354322770","https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W4237547500","https://openalex.org/W2355751417","https://openalex.org/W1570848052","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2373192430"],"abstract_inverted_index":{"The":[0,117,138,162],"ultrasound":[1],"tongue":[2,58],"imaging":[3],"(UTI)":[4],"and":[5,57,83,108],"lip":[6,30,56],"video":[7,31],"are":[8],"commonly":[9],"used":[10],"to":[11,16,45,53,61,77],"capture":[12],"the":[13,18,35,47,55,63,72,79,84,89,98,103,109,121,159,173,176],"acoustic":[14,85],"clue":[15],"obtain":[17],"visual":[19,81],"articulatory":[20],"information":[21,60,82],"of":[22,27,38,66,127,141,175],"speakers.":[23,39,67],"However,":[24],"single":[25],"signal":[26],"UTI":[28],"or":[29],"cannot":[32],"completely":[33],"represent":[34,62],"pronunciation":[36,64],"process":[37,65],"In":[40,68],"this":[41],"paper,":[42],"we":[43,70,96],"proposed":[44,94,129,143,167],"use":[46],"convolutional":[48],"neural":[49],"network":[50],"(CNN)-based":[51],"framework":[52,75],"fuse":[54,78],"movement":[59],"addition,":[69],"designed":[71,97],"multi-stage":[73],"fusion":[74,178],"(MF-SR)":[76],"lip-tongue":[80],"features":[86],"extracted":[87],"from":[88],"speech.":[90],"To":[91],"evaluate":[92],"our":[93,128,142,166],"method,":[95],"data":[99,110],"stream":[100],"comparative":[101,106],"experiments,":[102,107],"speech":[104,133,147,179],"pattern":[105],"increment":[111],"experiments":[112],"based":[113],"on":[114,131,145],"TAL1":[115],"dataset.":[116],"results":[118,163],"show":[119],"that":[120,165],"best":[122,139],"word":[123],"error":[124],"rate":[125],"(WER)":[126],"method":[130,168],"audio-visual":[132],"recognition":[134,148],"task":[135,149],"is":[136,150,153],"20.03%.":[137],"WER":[140],"model":[144],"visual-only":[146],"23.34%,":[151],"which":[152],"reduced":[154],"by":[155],"1.75%":[156],"compared":[157],"with":[158],"baseline":[160],"method.":[161],"illustrate":[164],"can":[169],"effectively":[170],"further":[171],"improve":[172],"performance":[174],"lip-tongue-audio":[177],"recognition.":[180]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}