{"id":"https://openalex.org/W4391454452","doi":"https://doi.org/10.1109/taslp.2024.3361376","title":"Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement","display_name":"Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4391454452","doi":"https://doi.org/10.1109/taslp.2024.3361376"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3361376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3361376","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Audio, Speech, and Language Processing","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/A5066498315","display_name":"Rui-Chen Zheng","orcid":"https://orcid.org/0009-0000-8074-9553"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui-Chen Zheng","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0009-0000-8074-9553","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-6668-022X","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059767940","display_name":"Zhen-Hua Ling","orcid":"https://orcid.org/0000-0001-7853-5273"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen-Hua Ling","raw_affiliation_strings":["National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0001-7853-5273","affiliations":[{"raw_affiliation_string":"National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":3.0403,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.9202542,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"32","issue":null,"first_page":"1430","last_page":"1444"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11448","display_name":"Face recognition and analysis","score":0.9868000149726868,"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/computer-science","display_name":"Computer science","score":0.7934476137161255},{"id":"https://openalex.org/keywords/tongue","display_name":"Tongue","score":0.7544970512390137},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7237324118614197},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.523850679397583},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4954291582107544},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.42434513568878174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4079045057296753},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07024958729743958}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7934476137161255},{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.7544970512390137},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7237324118614197},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.523850679397583},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4954291582107544},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.42434513568878174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4079045057296753},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07024958729743958},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3361376","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3361376","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8399999737739563}],"awards":[{"id":"https://openalex.org/G1080972157","display_name":null,"funder_award_id":"WK2100000033","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G2545034164","display_name":null,"funder_award_id":"2308085QF200","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G5861301885","display_name":null,"funder_award_id":"62301521","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1987337335","https://openalex.org/W1995440941","https://openalex.org/W2015143272","https://openalex.org/W2042407743","https://openalex.org/W2044893557","https://openalex.org/W2078528584","https://openalex.org/W2089240210","https://openalex.org/W2096779346","https://openalex.org/W2137400100","https://openalex.org/W2593268422","https://openalex.org/W2603597171","https://openalex.org/W2623570296","https://openalex.org/W2746109435","https://openalex.org/W2747874407","https://openalex.org/W2788241093","https://openalex.org/W2801554275","https://openalex.org/W2804093409","https://openalex.org/W2886232760","https://openalex.org/W2889413431","https://openalex.org/W2901702433","https://openalex.org/W2939800755","https://openalex.org/W2941048526","https://openalex.org/W2962780374","https://openalex.org/W2962946126","https://openalex.org/W2963082324","https://openalex.org/W2963272864","https://openalex.org/W2963341071","https://openalex.org/W2964171275","https://openalex.org/W2964207404","https://openalex.org/W2971630540","https://openalex.org/W2973016613","https://openalex.org/W2973231102","https://openalex.org/W2979074722","https://openalex.org/W2982242214","https://openalex.org/W2982624843","https://openalex.org/W3011424113","https://openalex.org/W3015219411","https://openalex.org/W3015785290","https://openalex.org/W3097945073","https://openalex.org/W3120762558","https://openalex.org/W3121016465","https://openalex.org/W3126260881","https://openalex.org/W3136499730","https://openalex.org/W3143787022","https://openalex.org/W3174954176","https://openalex.org/W3182657421","https://openalex.org/W3196749493","https://openalex.org/W3203789665","https://openalex.org/W4232282348","https://openalex.org/W4233392025","https://openalex.org/W4253928870","https://openalex.org/W4283782204","https://openalex.org/W4283818626","https://openalex.org/W4289665794","https://openalex.org/W4296068808","https://openalex.org/W4312337341","https://openalex.org/W4372346132","https://openalex.org/W4385822856","https://openalex.org/W4385823193","https://openalex.org/W6631190155","https://openalex.org/W6766978945","https://openalex.org/W6803607871"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W3096184950","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Audio-visual":[0],"speech":[1,8,28,87,97,149,167,200],"enhancement":[2,88,98,150],"(AV-SE)":[3],"aims":[4],"to":[5,22,39,62,68,91,169],"enhance":[6],"degraded":[7],"along":[9],"with":[10],"extra":[11],"visual":[12],"information":[13,75],"such":[14],"as":[15],"lip":[16,112,143],"videos,":[17],"and":[18,113,162,185,215],"has":[19],"been":[20],"shown":[21],"be":[23],"more":[24],"effective":[25],"than":[26],"audio-only":[27],"enhancement.":[29],"This":[30,131],"paper":[31],"proposes":[32],"the":[33,41,50,70,108,111,119,128,134,147,160,165,187],"incorporation":[34],"of":[35,43,52,72,121,136,164,189,198],"ultrasound":[36,54,79,211],"tongue":[37,55,80,114,137,212],"images":[38,56],"improve":[40,159],"performance":[42,181],"lip-based":[44,171],"AV-SE":[45,129,172],"systems":[46],"further.":[47],"To":[48,105],"address":[49],"challenge":[51],"acquiring":[53],"during":[57,66],"inference,":[58],"we":[59,83,116],"first":[60],"propose":[61,118],"employ":[63],"knowledge":[64],"distillation":[65],"training":[67],"investigate":[69],"feasibility":[71],"leveraging":[73],"tongue-related":[74,103],"without":[76],"directly":[77],"inputting":[78],"images.":[81],"Specifically,":[82],"guide":[84],"an":[85],"audio-lip":[86],"student":[89],"model":[90,107],"learn":[92],"from":[93,209],"a":[94,122],"pre-trained":[95],"audio-lip-tongue":[96],"teacher":[99],"model,":[100],"thus":[101],"transferring":[102],"knowledge.":[104],"better":[106],"alignment":[109],"between":[110],"modalities,":[115],"further":[117],"introduction":[120],"lip-tongue":[123],"key-value":[124],"memory":[125],"network":[126,132],"into":[127],"model.":[130],"enables":[133],"retrieval":[135],"features":[138],"based":[139],"on":[140,182],"readily":[141],"available":[142],"features,":[144],"thereby":[145],"assisting":[146],"subsequent":[148],"task.":[151],"Experimental":[152],"results":[153],"demonstrate":[154],"that":[155,204],"both":[156,175],"methods":[157,177],"significantly":[158],"quality":[161],"intelligibility":[163],"enhanced":[166],"compared":[168],"traditional":[170],"baselines.":[173],"Moreover,":[174],"proposed":[176],"exhibit":[178],"strong":[179],"generalization":[180],"unseen":[183,190],"speakers":[184],"in":[186],"presence":[188],"noises.":[191],"Furthermore,":[192],"phone":[193],"error":[194],"rate":[195],"(PER)":[196],"analysis":[197],"automatic":[199],"recognition":[201],"(ASR)":[202],"reveals":[203],"while":[205],"all":[206],"phonemes":[207],"benefit":[208,218],"introducing":[210],"images,":[213],"palatal":[214],"velar":[216],"consonants":[217],"most.":[219]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}