{"id":"https://openalex.org/W7148582461","doi":"https://doi.org/10.1109/asru65441.2025.11434749","title":"Interpreting the Role of Visemes in Audio-Visual Speech Recognition","display_name":"Interpreting the Role of Visemes in Audio-Visual Speech Recognition","publication_year":2025,"publication_date":"2025-12-06","ids":{"openalex":"https://openalex.org/W7148582461","doi":"https://doi.org/10.1109/asru65441.2025.11434749"},"language":null,"primary_location":{"id":"doi:10.1109/asru65441.2025.11434749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":null,"display_name":"Aristeidis Papadopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":true,"raw_author_name":"Aristeidis Papadopoulos","raw_affiliation_strings":["Trinity College Dublin,Sigmedia Group, School of Engineering,Dublin,Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin,Sigmedia Group, School of Engineering,Dublin,Ireland","institution_ids":["https://openalex.org/I205274468"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042231269","display_name":"Naomi Harte","orcid":"https://orcid.org/0000-0002-9274-209X"},"institutions":[{"id":"https://openalex.org/I205274468","display_name":"Trinity College Dublin","ror":"https://ror.org/02tyrky19","country_code":"IE","type":"education","lineage":["https://openalex.org/I205274468"]}],"countries":["IE"],"is_corresponding":false,"raw_author_name":"Naomi Harte","raw_affiliation_strings":["Trinity College Dublin,Sigmedia Group, School of Engineering,Dublin,Ireland"],"affiliations":[{"raw_affiliation_string":"Trinity College Dublin,Sigmedia Group, School of Engineering,Dublin,Ireland","institution_ids":["https://openalex.org/I205274468"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205274468"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74256615,"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":0.9061999917030334,"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":0.9061999917030334,"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/T11309","display_name":"Music and Audio Processing","score":0.04839999973773956,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.009100000374019146,"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/interpretability","display_name":"Interpretability","score":0.8258000016212463},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5938000082969666},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5570999979972839},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4505999982357025},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.37279999256134033},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.36399999260902405},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33970001339912415}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8258000016212463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6840000152587891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6116999983787537},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5570999979972839},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46209999918937683},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4505999982357025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37459999322891235},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.37279999256134033},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.36399999260902405},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33970001339912415},{"id":"https://openalex.org/C2776608160","wikidata":"https://www.wikidata.org/wiki/Q4785462","display_name":"Natural (archaeology)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.29809999465942383},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2842000126838684},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28380000591278076},{"id":"https://openalex.org/C165297611","wikidata":"https://www.wikidata.org/wiki/Q43249","display_name":"Morpheme","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.26429998874664307},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2635999917984009}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru65441.2025.11434749","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru65441.2025.11434749","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1483072991","https://openalex.org/W1578725541","https://openalex.org/W2071096833","https://openalex.org/W2101013379","https://openalex.org/W2155765376","https://openalex.org/W2165533158","https://openalex.org/W2365880764","https://openalex.org/W2397233148","https://openalex.org/W2542768043","https://openalex.org/W2747874407","https://openalex.org/W2789304371","https://openalex.org/W2963528589","https://openalex.org/W3014988774","https://openalex.org/W3096017728","https://openalex.org/W3097777922","https://openalex.org/W3163596720","https://openalex.org/W3209059054","https://openalex.org/W4225726571","https://openalex.org/W4226380987","https://openalex.org/W4287854494","https://openalex.org/W4293363567","https://openalex.org/W4297841641","https://openalex.org/W4297841864","https://openalex.org/W4319586625","https://openalex.org/W4372346152","https://openalex.org/W4375869259","https://openalex.org/W4376481237","https://openalex.org/W4385245566","https://openalex.org/W4385822832","https://openalex.org/W4385823329","https://openalex.org/W4391021811","https://openalex.org/W4394773771","https://openalex.org/W4402111514","https://openalex.org/W4402112198","https://openalex.org/W4402112360","https://openalex.org/W4402684056","https://openalex.org/W4408355725"],"related_works":[],"abstract_inverted_index":{"Audio-Visual":[0],"Speech":[1],"Recognition":[2],"(AVSR)":[3],"models":[4],"have":[5],"surpassed":[6],"their":[7],"audio-only":[8],"counterparts":[9],"in":[10,43,108],"terms":[11],"of":[12,17,23,75],"performance.":[13,123],"However,":[14],"the":[15,21,24,73,104],"interpretability":[16,35],"AVSR":[18,47,109,122],"systems,":[19],"particularly":[20,90],"role":[22],"visual":[25,66,118],"modality,":[26],"remains":[27],"under-explored.":[28],"In":[29],"this":[30],"paper,":[31],"we":[32,50,78],"apply":[33],"several":[34],"techniques":[36],"to":[37,57,81,86,113,120],"examine":[38],"how":[39,83],"visemes":[40,92],"are":[41,94],"encoded":[42],"AV-HuBERT":[44],"a":[45],"state-of-the-art":[46],"model.":[48],"First,":[49],"use":[51],"t-distributed":[52],"Stochastic":[53],"Neighbour":[54],"Embedding":[55],"(t-SNE)":[56],"visualize":[58],"learned":[59],"features,":[60],"revealing":[61],"natural":[62],"clustering":[63],"driven":[64],"by":[65,72],"cues,":[67],"which":[68],"is":[69],"further":[70],"refined":[71],"presence":[74],"audio.":[76],"Then,":[77],"employ":[79],"probing":[80],"show":[82],"audio":[84],"contributes":[85],"refining":[87],"feature":[88],"representations,":[89],"for":[91,116],"that":[93],"visually":[95],"ambiguous":[96],"or":[97],"under-represented.":[98],"Our":[99],"findings":[100],"shed":[101],"light":[102],"on":[103],"interplay":[105],"between":[106],"modalities":[107],"and":[110],"could":[111],"point":[112],"new":[114],"strategies":[115],"leveraging":[117],"information":[119],"improve":[121]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2026-04-03T00:00:00"}