{"id":"https://openalex.org/W4415524539","doi":"https://doi.org/10.1109/mlsp62443.2025.11204267","title":"Efficient Mouth Alignment for Visual Speech Recognition","display_name":"Efficient Mouth Alignment for Visual Speech Recognition","publication_year":2025,"publication_date":"2025-08-31","ids":{"openalex":"https://openalex.org/W4415524539","doi":"https://doi.org/10.1109/mlsp62443.2025.11204267"},"language":"en","primary_location":{"id":"doi:10.1109/mlsp62443.2025.11204267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","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/A5031380432","display_name":"Zhe Niu","orcid":"https://orcid.org/0000-0001-5833-1142"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhe Niu","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059141717","display_name":"Brian Mak","orcid":"https://orcid.org/0000-0001-6787-5555"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Brian Mak","raw_affiliation_strings":["The Hong Kong University of Science and Technology,Department of Computer Science and Engineering"],"affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology,Department of Computer Science and Engineering","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5031380432"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41248097,"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":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9926000237464905,"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":0.9926000237464905,"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":0.9578999876976013,"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":0.957099974155426,"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/landmark","display_name":"Landmark","score":0.6836000084877014},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.6535999774932861},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5149999856948853},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39010000228881836},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.3418000042438507},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.325300008058548}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860000133514404},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.6836000084877014},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.6535999774932861},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6225000023841858},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5473999977111816},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5149999856948853},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47029998898506165},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.3418000042438507},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3188000023365021},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.304500013589859},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/mlsp62443.2025.11204267","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mlsp62443.2025.11204267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 35th International Workshop on Machine Learning for Signal Processing (MLSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167060","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167060","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2022406968","https://openalex.org/W2194775991","https://openalex.org/W2302255633","https://openalex.org/W2307770531","https://openalex.org/W2763110165","https://openalex.org/W2808631503","https://openalex.org/W2890952074","https://openalex.org/W2949662773","https://openalex.org/W4250482878","https://openalex.org/W4372346152","https://openalex.org/W4402112118","https://openalex.org/W4404792841","https://openalex.org/W4408354236"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"Speech":[1],"Recognition":[2],"(VSR),":[3],"also":[4,69],"known":[5],"as":[6],"lip-reading,":[7],"requires":[8],"accurate":[9],"mouth":[10],"tracking":[11],"and":[12,34,97,114,122],"alignment":[13,89,120],"to":[14],"achieve":[15],"high":[16],"performance.":[17],"Conventional":[18],"approaches":[19],"rely":[20],"on":[21,92],"complex":[22],"pipelines":[23],"involving":[24],"facial":[25,28],"landmark":[26,29],"detection,":[27],"smoothing,":[30],"affine":[31,53],"transformation":[32,54],"estimation":[33],"warping.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"a":[41,44,57,60,71],"streamlined":[42],"solution:":[43],"fast":[45],"Mouth":[46,73],"Alignment":[47],"Network":[48,75],"(MAN)":[49],"that":[50,77,100],"directly":[51],"estimates":[52],"parameters":[55],"from":[56],"video":[58],"of":[59],"talking":[61],"face,":[62],"significantly":[63],"simplifying":[64],"the":[65,84,104,119],"process.":[66],"Our":[67],"approach":[68],"incorporates":[70],"complementary":[72],"Scoring":[74],"(MSN)":[76],"injects":[78],"knowledge":[79],"about":[80],"adversarial":[81],"perturbations":[82],"into":[83],"training":[85],"process,":[86],"further":[87],"improving":[88,118],"quality.":[90],"Experiments":[91],"standard":[93],"lip-reading":[94],"benchmarks":[95],"(LRS2":[96],"LRS3)":[98],"demonstrate":[99],"our":[101],"method":[102],"maintains":[103],"performance":[105],"when":[106],"integrated":[107],"with":[108],"state-of-the-art":[109],"VSR":[110],"systems,":[111],"including":[112],"Auto-AVSR":[113],"USR,":[115],"while":[116],"substantially":[117],"quality":[121],"computational":[123],"efficiency.":[124]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-24T00:00:00"}