{"id":"https://openalex.org/W4408352079","doi":"https://doi.org/10.1109/icassp49660.2025.10888752","title":"Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing","display_name":"Automatic Text Pronunciation Correlation Generation and Application for Contextual Biasing","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352079","doi":"https://doi.org/10.1109/icassp49660.2025.10888752"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10888752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5072887461","display_name":"Gaofeng Cheng","orcid":"https://orcid.org/0000-0002-2102-6061"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaofeng Cheng","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017349618","display_name":"Haitian Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haitian Lu","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107601103","display_name":"Chengxu Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengxu Yang","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100451341","display_name":"Xuyang Wang","orcid":"https://orcid.org/0000-0003-0055-0929"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuyang Wang","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052454197","display_name":"Li Ta","orcid":"https://orcid.org/0000-0001-5431-9787"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ta Li","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100425112","display_name":"Yonghong Yan","orcid":"https://orcid.org/0000-0001-6907-5770"},"institutions":[{"id":"https://openalex.org/I4210099069","display_name":"Institute of Acoustics","ror":"https://ror.org/00v8rqv75","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210099069"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghong Yan","raw_affiliation_strings":["Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Acoustics, CAS,Key Laboratory of Speech Acoustics and Content Understanding,China","institution_ids":["https://openalex.org/I4210099069"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210099069"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.964900016784668,"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":0.964900016784668,"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/T12031","display_name":"Speech and dialogue systems","score":0.9151999950408936,"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/pronunciation","display_name":"Pronunciation","score":0.7119709253311157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7007056474685669},{"id":"https://openalex.org/keywords/biasing","display_name":"Biasing","score":0.6022331714630127},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.5644358992576599},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43154066801071167},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.41774415969848633},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3556450605392456},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.17863857746124268},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.1565079689025879},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.12041476368904114},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10129398107528687},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10084772109985352}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7119709253311157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7007056474685669},{"id":"https://openalex.org/C20254490","wikidata":"https://www.wikidata.org/wiki/Q719550","display_name":"Biasing","level":3,"score":0.6022331714630127},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.5644358992576599},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43154066801071167},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.41774415969848633},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3556450605392456},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.17863857746124268},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.1565079689025879},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.12041476368904114},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10129398107528687},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10084772109985352},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10888752","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10888752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4099999964237213,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1574284142","https://openalex.org/W1618325928","https://openalex.org/W2100340603","https://openalex.org/W2127141656","https://openalex.org/W2165143604","https://openalex.org/W2327501763","https://openalex.org/W2937402758","https://openalex.org/W2963242190","https://openalex.org/W2972625221","https://openalex.org/W2973172693","https://openalex.org/W3018242354","https://openalex.org/W3042416212","https://openalex.org/W3160413945","https://openalex.org/W3162639446","https://openalex.org/W3198429080","https://openalex.org/W3207815550","https://openalex.org/W3211278025","https://openalex.org/W4221040649","https://openalex.org/W4221165942","https://openalex.org/W4221167707","https://openalex.org/W4226380987","https://openalex.org/W4240592325","https://openalex.org/W4285115600","https://openalex.org/W4385822246","https://openalex.org/W6696449567","https://openalex.org/W6754473786"],"related_works":["https://openalex.org/W2183593636","https://openalex.org/W2350724007","https://openalex.org/W2355751417","https://openalex.org/W2423284978","https://openalex.org/W2083922162","https://openalex.org/W2000075989","https://openalex.org/W3006486861","https://openalex.org/W4220683390","https://openalex.org/W2776838583","https://openalex.org/W2359469050"],"abstract_inverted_index":{"Effectively":[0],"distinguishing":[1],"the":[2,56,74,84,100,108],"pronunciation":[3,18,25,39,44,141],"correlations":[4,19],"between":[5],"different":[6,113],"written":[7],"texts":[8],"is":[9,53,80,96],"a":[10,32,93],"significant":[11],"issue":[12],"in":[13,129],"linguistic":[14],"acoustics.":[15],"Traditionally,":[16],"such":[17],"are":[20],"obtained":[21],"through":[22],"manually":[23],"designed":[24],"lexicons.":[26,142],"In":[27],"this":[28,51],"paper,":[29],"we":[30,106],"propose":[31],"data-driven":[33],"method":[34,52],"to":[35,82,98,116],"automatically":[36],"acquire":[37],"these":[38],"correlations,":[40],"called":[41],"automatic":[42,62],"text":[43,71,90,114],"correlation":[45],"(ATPC).":[46],"The":[47],"supervision":[48,57],"required":[49],"for":[50,59,135],"consistent":[54],"with":[55,86],"needed":[58],"training":[60],"end-to-end":[61],"speech":[63,68,85,94,101,103,109],"recognition":[64],"(E2E-ASR)":[65],"systems,":[66],"i.e.,":[67],"and":[69,132],"corresponding":[70,88],"annotations.":[72],"First,":[73],"iteratively-trained":[75],"timestamp":[76],"estimator":[77],"(ITSE)":[78],"algorithm":[79],"employed":[81],"align":[83],"their":[87],"annotated":[89],"symbols.":[91],"Then,":[92],"encoder":[95],"used":[97],"convert":[99],"into":[102],"embeddings.":[104],"Finally,":[105],"compare":[107],"embeddings":[110],"distances":[111],"of":[112],"symbols":[115],"obtain":[117],"ATPC.":[118],"Experimental":[119],"results":[120],"on":[121],"Mandarin":[122],"show":[123],"that":[124],"ATPC":[125],"enhances":[126],"E2E-ASR":[127],"performance":[128],"contextual":[130],"biasing":[131],"holds":[133],"promise":[134],"dialects":[136],"or":[137],"languages":[138],"lacking":[139],"artificial":[140]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}