{"id":"https://openalex.org/W4416799837","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249064","title":"Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation","display_name":"Zero-shot Context Biasing with Trie-based Decoding using Synthetic Multi-Pronunciation","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416799837","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249064"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249064","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/A5101489952","display_name":"Changsong Liu","orcid":"https://orcid.org/0000-0002-1387-7499"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY","SG"],"is_corresponding":false,"raw_author_name":"Changsong Liu","raw_affiliation_strings":["Nanyang Technological University,Alibaba-NTU Global e-Sustainability CorpLab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Alibaba-NTU Global e-Sustainability CorpLab,Singapore","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114025990","display_name":"Yizhou Peng","orcid":"https://orcid.org/0000-0002-5718-570X"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]},{"id":"https://openalex.org/I4210086143","display_name":"Alibaba Group (Cayman Islands)","ror":"https://ror.org/00mnrxf72","country_code":"KY","type":"company","lineage":["https://openalex.org/I4210086143","https://openalex.org/I45928872"]}],"countries":["KY","SG"],"is_corresponding":false,"raw_author_name":"Yizhou Peng","raw_affiliation_strings":["Nanyang Technological University,Alibaba-NTU Global e-Sustainability CorpLab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,Alibaba-NTU Global e-Sustainability CorpLab,Singapore","institution_ids":["https://openalex.org/I4210086143","https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["College of Computing and Data Science, Nanyang Technological University,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computing and Data Science, Nanyang Technological University,Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"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":0.17663267,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"873","last_page":"878"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9416999816894531,"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":0.9416999816894531,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.012799999676644802,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.008799999952316284,"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/security-token","display_name":"Security token","score":0.7960000038146973},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.7210000157356262},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6366999745368958},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5691999793052673},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.558899998664856},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5360000133514404},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5153999924659729},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.3646000027656555}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.7960000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7641000151634216},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.7210000157356262},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6366999745368958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6050000190734863},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5691999793052673},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5360000133514404},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5153999924659729},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47859999537467957},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3817000091075897},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C2987487971","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexical access","level":3,"score":0.3215000033378601},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3127000033855438},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2782000005245209},{"id":"https://openalex.org/C3018824978","wikidata":"https://www.wikidata.org/wiki/Q2894891","display_name":"Error analysis","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2587999999523163},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.2556999921798706},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.25360000133514404}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249064","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":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2395440424","https://openalex.org/W2886319145","https://openalex.org/W2972625221","https://openalex.org/W3097777922","https://openalex.org/W3198004110","https://openalex.org/W3211278025","https://openalex.org/W4226462878","https://openalex.org/W4283832239","https://openalex.org/W4385245566","https://openalex.org/W4385822246","https://openalex.org/W4385822953","https://openalex.org/W4392903019","https://openalex.org/W4392903078","https://openalex.org/W4392903329","https://openalex.org/W4392909899","https://openalex.org/W4406461293","https://openalex.org/W4412945617"],"related_works":[],"abstract_inverted_index":{"Contextual":[0],"automatic":[1],"speech":[2,63],"recognition":[3],"(ASR)":[4],"systems":[5,59],"allow":[6],"for":[7],"recognizing":[8],"out-of-vocabulary":[9],"(OOV)":[10],"words,":[11],"such":[12],"as":[13],"named":[14],"entities":[15],"or":[16,30],"rare":[17,68,115],"words.":[18],"However,":[19],"it":[20],"remains":[21],"challenging":[22],"due":[23],"to":[24,60,77,95,112],"limited":[25],"training":[26],"data":[27],"and":[28,70,142],"ambiguous":[29],"inconsistent":[31],"pronunciations.":[32],"In":[33],"this":[34],"paper,":[35],"we":[36,55],"propose":[37],"a":[38,50,90,99],"synthesis-driven":[39],"multipronunciation":[40],"contextual":[41,47],"biasing":[42],"method":[43,131],"that":[44,129],"performs":[45],"zero-shot":[46],"ASR":[48],"on":[49,124,140,145],"pretrained":[51,74],"Whisper":[52,75],"model.":[53],"Specifically,":[54],"leverage":[56],"text-to-speech":[57],"(TTS)":[58],"synthesize":[61],"diverse":[62],"samples":[64],"containing":[65],"each":[66],"target":[67],"word,":[69],"then":[71],"use":[72],"the":[73,113,118,125],"model":[76],"extract":[78],"multiple":[79],"predicted":[80],"pronunciation":[81],"variants.":[82],"These":[83],"variant":[84,108],"token":[85],"sequences":[86],"are":[87],"compiled":[88],"into":[89],"prefix-trie,":[91],"which":[92],"assigns":[93],"rewards":[94],"beam":[96],"hypotheses":[97],"in":[98,117],"shallow-fusion":[100],"manner":[101],"during":[102],"beam-search":[103],"decoding.":[104],"Subsequently,":[105],"any":[106],"recognized":[107],"is":[109],"mapped":[110],"back":[111],"original":[114],"word":[116],"final":[119],"transcription.":[120],"The":[121],"evaluation":[122],"results":[123],"LibriSpeech":[126],"dataset":[127],"show":[128],"our":[130],"reduces":[132],"biasedword":[133],"error":[134],"rate":[135],"(B-WER)":[136],"by":[137],"43":[138],"%":[139,144],"test-clean":[141],"44":[143],"test-other":[146],"while":[147],"maintaining":[148],"unbiased-WER":[149],"(U-WER)":[150],"essentially":[151],"unchanged.":[152]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}