{"id":"https://openalex.org/W4416798974","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249198","title":"Probabilistic Language-Aware Speech Recognition","display_name":"Probabilistic Language-Aware Speech Recognition","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416798974","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249198"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249198","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/A5061908942","display_name":"Jen\u2010Tzung Chien","orcid":"https://orcid.org/0000-0003-3466-8941"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Jen-Tzung Chien","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120390128","display_name":"Willianto Sulaiman","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Willianto Sulaiman","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026192663","display_name":"Chung-Hsuan Wang","orcid":"https://orcid.org/0000-0002-5076-918X"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chung-Hsuan Wang","raw_affiliation_strings":["Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Electrical and Computer Engineering, National Yang Ming Chiao Tung University,Hsinchu,Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061908942"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20713705,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1028","last_page":"1032"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7942000031471252,"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":0.7942000031471252,"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":0.0364999994635582,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.014999999664723873,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.6061000227928162},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.589900016784668},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.5174000263214111},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4652999937534332},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4348999857902527},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.41449999809265137},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4025999903678894},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.39399999380111694}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7735999822616577},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7319999933242798},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6061000227928162},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.589900016784668},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.5174000263214111},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4652999937534332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.447299987077713},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4348999857902527},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.43140000104904175},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.41449999809265137},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4025999903678894},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.39399999380111694},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.38940000534057617},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3564999997615814},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C54953205","wikidata":"https://www.wikidata.org/wiki/Q4142201","display_name":"Speech analytics","level":4,"score":0.3001999855041504},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2831000089645386},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.28110000491142273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249198","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249198","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":24,"referenced_works":["https://openalex.org/W197277712","https://openalex.org/W2405331948","https://openalex.org/W2962780374","https://openalex.org/W3097777922","https://openalex.org/W3198429080","https://openalex.org/W4220758154","https://openalex.org/W4297841499","https://openalex.org/W4319862255","https://openalex.org/W4375869049","https://openalex.org/W4385822890","https://openalex.org/W4385823060","https://openalex.org/W4388820551","https://openalex.org/W4391021740","https://openalex.org/W4391021741","https://openalex.org/W4392903108","https://openalex.org/W4392903386","https://openalex.org/W4400905918","https://openalex.org/W4402987946","https://openalex.org/W4405634116","https://openalex.org/W4406858895","https://openalex.org/W4406859726","https://openalex.org/W4408352822","https://openalex.org/W4411203695","https://openalex.org/W4416011273"],"related_works":[],"abstract_inverted_index":{"Code-switching":[0],"scheme":[1],"aims":[2],"to":[3,31,103,142],"imitate":[4],"how":[5],"speakers":[6],"alternately":[7],"switch":[8],"different":[9],"languages":[10,106],"during":[11],"speech":[12,23,48,110],"communication":[13],"in":[14,62,97,107,127],"a":[15,26,44,53,63,72,94,108,123,143],"multilingual":[16],"community.":[17],"However,":[18],"building":[19],"an":[20,84],"efficient":[21],"code-switching":[22,109,118],"recognition":[24,38,49],"remains":[25],"challenging":[27],"issue,":[28,43],"primarily":[29],"due":[30],"the":[32,37,57,76,80,100,133],"language":[33,81,95],"confusion,":[34],"which":[35],"degrades":[36],"performance.":[39],"To":[40],"address":[41],"this":[42,69],"novel":[45],"probabilistic":[46],"language-aware":[47,73],"is":[50,111],"developed":[51],"through":[52],"parameter-efficient":[54],"learning":[55],"where":[56],"tunable":[58],"adapters":[59],"are":[60],"configured":[61],"frozen":[64],"Whisper":[65],"backbone.":[66],"In":[67],"particular,":[68],"study":[70],"incorporates":[71],"calibrator":[74],"at":[75],"prediction":[77],"stage,":[78],"introducing":[79],"identity":[82],"as":[83],"additional":[85],"condition":[86],"for":[87],"next":[88],"token":[89],"prediction.":[90],"By":[91],"merging":[92],"such":[93],"awareness":[96],"conditional":[98],"generation,":[99],"model's":[101],"ability":[102],"distinguish":[104],"between":[105],"significantly":[112],"improved.":[113],"The":[114],"results":[115],"on":[116],"Chinese-English":[117],"dataset":[119],"using":[120,132],"SEAME":[121],"show":[122],"4.9%":[124],"relative":[125,141],"improvement":[126],"mixed":[128],"error":[129],"rate":[130],"by":[131],"proposed":[134],"method":[135],"with":[136,146],"only":[137],"5.1%":[138],"fine-tuned":[139,148],"parameters":[140],"strong":[144],"baseline":[145],"full":[147],"parameters.":[149]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-11-28T00:00:00"}
