{"id":"https://openalex.org/W4414231584","doi":"https://doi.org/10.1109/ialp68296.2024.11156289","title":"Robust Speech Recognition for Visual Acuity Testing in Multi-Speaker Clinical Environments","display_name":"Robust Speech Recognition for Visual Acuity Testing in Multi-Speaker Clinical Environments","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4414231584","doi":"https://doi.org/10.1109/ialp68296.2024.11156289"},"language":"en","primary_location":{"id":"doi:10.1109/ialp68296.2024.11156289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","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,Infocomm Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Infocomm 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,Infocomm Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Infocomm 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,Department of Ophthalmology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tan Tock Seng Hospital,Department of Ophthalmology,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,Infocomm Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Infocomm 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,Infocomm Technology,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Institute of Technology,Infocomm Technology,Singapore","institution_ids":["https://openalex.org/I168639165"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.11533059,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"266","last_page":"271"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7835000157356262,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7835000157356262,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.7746000289916992,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5555999875068665},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.48559999465942383},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.40619999170303345},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.3610000014305115},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.31349998712539673},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31029999256134033},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.3093000054359436}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737500011920929},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7329999804496765},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5555999875068665},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.48559999465942383},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42480000853538513},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3610000014305115},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.31349998712539673},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31029999256134033},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.3093000054359436},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2985000014305115},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.28600001335144043},{"id":"https://openalex.org/C178009071","wikidata":"https://www.wikidata.org/wiki/Q93344","display_name":"Trigonometric functions","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2574999928474426}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp68296.2024.11156289","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp68296.2024.11156289","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Asian Language Processing (IALP)","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":14,"referenced_works":["https://openalex.org/W2127851351","https://openalex.org/W2221409856","https://openalex.org/W2889418727","https://openalex.org/W2962935966","https://openalex.org/W2969916503","https://openalex.org/W3045521984","https://openalex.org/W3047154986","https://openalex.org/W3163652268","https://openalex.org/W3202976789","https://openalex.org/W3204830808","https://openalex.org/W4284883478","https://openalex.org/W4372266552","https://openalex.org/W4391486999","https://openalex.org/W4392903251"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"Speech":[1],"Recognition":[2],"(ASR)":[3],"in":[4,147,159],"multispeaker":[5],"clinical":[6,56,103,148],"environments":[7,162],"remains":[8],"a":[9,30,54,153],"significant":[10],"challenge":[11],"due":[12],"to":[13,58,142],"overlapping":[14,69],"speech,":[15,70],"ambient":[16],"noise,":[17],"and":[18,62,68,79,81,94,101,115,138],"the":[19,50,107,120,132],"lack":[20],"of":[21,43,134],"reference":[22],"audio":[23],"for":[24,36,156],"speaker":[25,139],"identification.":[26],"This":[27],"paper":[28],"presents":[29],"robust,":[31],"target-aware":[32],"ASR":[33,146],"system":[34,151],"tailored":[35],"visual":[37],"acuity":[38],"testing,":[39],"where":[40],"accurate":[41],"transcription":[42,60],"patient":[44],"responses":[45],"is":[46],"critical.":[47],"We":[48],"finetune":[49],"Whisper":[51,109],"model":[52],"on":[53,90,99],"domain-specific":[55],"dataset":[57],"improve":[59],"accuracy":[61],"reduce":[63],"latency.":[64],"To":[65],"address":[66],"crosstalk":[67],"we":[71],"evaluate":[72],"two":[73],"state-of-the-art":[74],"speech":[75],"separation":[76,137],"models,":[77],"MossFormer2":[78,114],"SepFormer,":[80],"integrate":[82],"reference-free":[83],"Target":[84],"Talker":[85],"Identification":[86],"(TTI)":[87],"strategies":[88],"based":[89],"signal-to-noise":[91],"ratio":[92],"(SNR)":[93],"cosine":[95,116],"similarity.":[96],"Our":[97],"evaluation":[98],"synthetic":[100],"real":[102],"datasets":[104],"demonstrates":[105],"that":[106],"fine-tuned":[108],"model,":[110],"when":[111],"combined":[112],"with":[113,163],"similarity-based":[117],"TTI,":[118],"achieves":[119],"lowest":[121],"Word":[122],"Error":[123],"Rate":[124],"(WER)":[125],"across":[126],"two-speaker":[127],"scenarios.":[128],"These":[129],"results":[130],"highlight":[131],"importance":[133],"integrating":[135],"robust":[136],"identification":[140],"methods":[141],"enable":[143],"accurate,":[144],"efficient":[145],"settings.":[149],"The":[150],"provides":[152],"scalable":[154],"foundation":[155],"future":[157],"work":[158],"more":[160,166],"complex":[161],"three":[164],"or":[165],"speakers.":[167]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}