{"id":"https://openalex.org/W4416799857","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249018","title":"Robust Audio-Visual Speech Recognition in Noisy Clinical Environments","display_name":"Robust Audio-Visual Speech Recognition in Noisy Clinical Environments","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799857","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249018"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5030750073","display_name":"Akshita Abrol","orcid":"https://orcid.org/0000-0002-8187-8987"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Akshita Abrol","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119631093","display_name":"Ridwan Arefeen","orcid":null},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ridwan Arefeen","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100695381","display_name":"Honggang Yu","orcid":"https://orcid.org/0000-0002-3553-637X"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haotong Yu","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020608299","display_name":"A. Shaji George","orcid":"https://orcid.org/0000-0002-8677-3682"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Alexi George","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056996128","display_name":"Kelvin Zhenghao Li","orcid":"https://orcid.org/0000-0002-9993-5118"},"institutions":[{"id":"https://openalex.org/I2802408685","display_name":"Tan Tock Seng Hospital","ror":"https://ror.org/032d59j24","country_code":"SG","type":"healthcare","lineage":["https://openalex.org/I2802408685"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Kelvin Zhenghao Li","raw_affiliation_strings":["Tan Tock Seng Hospital,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tan Tock Seng Hospital,Singapore","institution_ids":["https://openalex.org/I2802408685"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020485549","display_name":"Zhengkui Wang","orcid":"https://orcid.org/0000-0003-4554-0791"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zhengkui Wang","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047323439","display_name":"Rong Tong","orcid":"https://orcid.org/0000-0002-2034-9272"},"institutions":[{"id":"https://openalex.org/I168639165","display_name":"Singapore Institute of Technology","ror":"https://ror.org/01v2c2791","country_code":"SG","type":"education","lineage":["https://openalex.org/I168639165"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rong Tong","raw_affiliation_strings":["Singapore Institute of Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39579649,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2400","last_page":"2405"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6482999920845032,"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":0.6482999920845032,"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.27090001106262207,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.013899999670684338,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/microphone","display_name":"Microphone","score":0.6037999987602234},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5156999826431274},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4927000105381012},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.423799991607666},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3846000134944916},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.37119999527931213},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.3555000126361847},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3447999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7591999769210815},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6973999738693237},{"id":"https://openalex.org/C2778263558","wikidata":"https://www.wikidata.org/wiki/Q46384","display_name":"Microphone","level":3,"score":0.6037999987602234},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5156999826431274},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4927000105381012},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.448199987411499},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3846000134944916},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.37119999527931213},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3555000126361847},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3458000123500824},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C169822122","wikidata":"https://www.wikidata.org/wiki/Q230187","display_name":"Crosstalk","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.33309999108314514},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C2776817677","wikidata":"https://www.wikidata.org/wiki/Q4839818","display_name":"Backward masking","level":3,"score":0.2831999957561493},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.2732999920845032},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.27000001072883606},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.26460000872612},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.25619998574256897},{"id":"https://openalex.org/C173552908","wikidata":"https://www.wikidata.org/wiki/Q1366289","display_name":"Graphics pipeline","level":4,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249018","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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":11,"referenced_works":["https://openalex.org/W2905356507","https://openalex.org/W2965390715","https://openalex.org/W3163652268","https://openalex.org/W3196475561","https://openalex.org/W3204830808","https://openalex.org/W4284883478","https://openalex.org/W4297841411","https://openalex.org/W4304775708","https://openalex.org/W4372346152","https://openalex.org/W4385822353","https://openalex.org/W4392903251"],"related_works":[],"abstract_inverted_index":{"Visual":[0],"acuity":[1,204],"(VA)":[2],"testing":[3,15],"is":[4,147],"a":[5,23,53,66,106,133,154,181],"foundational":[6],"clinical":[7,59],"procedure":[8],"for":[9,157],"assessing":[10],"vision":[11,159],"clarity.":[12],"Traditionally,":[13],"VA":[14,83],"requires":[16],"patients":[17],"to":[18,29,44,78,110,193],"read":[19],"optotypes":[20],"aloud":[21],"from":[22,47],"distance,":[24],"with":[25],"an":[26],"assistant":[27],"present":[28],"record":[30],"the":[31,145,176,194,198],"responses.":[32],"Speech-enabled":[33],"automation":[34],"has":[35],"been":[36],"explored,":[37],"however":[38],"these":[39],"solutions":[40],"are":[41],"highly":[42],"susceptible":[43],"performance":[45],"degradation":[46],"ambient":[48],"noise":[49,100],"and":[50,74,81,93,101,104,116,165,183,200],"speech":[51,76,141],"crosstalk:":[52],"common":[54],"challenge":[55],"in":[56,187],"real-world,":[57],"multilane":[58],"environments.":[60],"In":[61],"this":[62],"work,":[63],"we":[64,131],"introduce":[65,132],"novel":[67],"multimodal":[68,151],"pipeline":[69,152],"system":[70],"that":[71,138,175],"combines":[72],"audio":[73,135],"visual":[75,203],"recognition":[77],"enable":[79],"robust":[80],"accurate":[82],"transcription":[84,163],"even":[85],"under":[86,128],"noisy":[87],"conditions.":[88],"By":[89],"integrating":[90],"synchronized":[91],"microphone":[92],"camera":[94],"inputs,":[95],"our":[96],"architecture":[97],"employs":[98],"advanced":[99],"crosstalk":[102,129,202],"detection,":[103],"utilizes":[105],"dynamic":[107],"decision":[108],"module":[109],"intelligently":[111],"select":[112],"between":[113],"audio-based":[114],"ASR":[115],"lip-reading":[117,179],"outputs":[118],"based":[119],"on":[120,197],"real-time":[121],"environmental":[122],"analysis.":[123],"To":[124],"further":[125],"improve":[126],"accuracy":[127,164],"conditions,":[130],"lip-guided":[134],"masking":[136],"mechanism":[137],"suppresses":[139],"non-target":[140],"by":[142],"detecting":[143],"when":[144],"patient":[146],"actively":[148],"speaking.":[149],"This":[150],"represents":[153],"significant":[155],"advancement":[156],"automated":[158],"screening,":[160],"offering":[161],"enhanced":[162],"reliability":[166],"where":[167],"single":[168],"modality":[169],"systems":[170],"fail.":[171],"Preliminary":[172],"results":[173],"demonstrate":[174],"addition":[177],"of":[178],"achieves":[180],"33%":[182],"16%":[184],"relative":[185],"reduction":[186],"word":[188],"error":[189],"rate":[190],"(WER)":[191],"compared":[192],"audio-only":[195],"baseline":[196],"three-speaker":[199],"two-speaker":[201],"test":[205],"sets,":[206],"respectively.":[207]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}
