{"id":"https://openalex.org/W4392903296","doi":"https://doi.org/10.1109/icassp48485.2024.10447685","title":"Transducers with Pronunciation-Aware Embeddings for Automatic Speech Recognition","display_name":"Transducers with Pronunciation-Aware Embeddings for Automatic Speech Recognition","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392903296","doi":"https://doi.org/10.1109/icassp48485.2024.10447685"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 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/A5100409299","display_name":"Xu H","orcid":"https://orcid.org/0009-0001-1201-443X"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hainan Xu","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002433660","display_name":"Zhehuai Chen","orcid":"https://orcid.org/0000-0003-4400-5340"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhehuai Chen","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011196247","display_name":"Fei Jia","orcid":"https://orcid.org/0000-0001-5212-6551"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fei Jia","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032957280","display_name":"Boris Ginsburg","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Boris Ginsburg","raw_affiliation_strings":["NVIDIA,USA","NVIDIA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NVIDIA,USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":"NVIDIA, USA","institution_ids":["https://openalex.org/I4210127875"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210127875"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12026","last_page":"12030"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9998000264167786,"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":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.8322979211807251},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7176084518432617},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.7086362838745117},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.7070269584655762},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6443212628364563},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5519437789916992},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41901636123657227},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.4109652042388916},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4092161953449249},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.09983479976654053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8322979211807251},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7176084518432617},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.7086362838745117},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.7070269584655762},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6443212628364563},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5519437789916992},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41901636123657227},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.4109652042388916},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4092161953449249},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.09983479976654053},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447685","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":29,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2284628133","https://openalex.org/W2327501763","https://openalex.org/W2886319145","https://openalex.org/W2889048668","https://openalex.org/W2899879954","https://openalex.org/W2937402758","https://openalex.org/W2946200149","https://openalex.org/W2973172693","https://openalex.org/W2974231335","https://openalex.org/W2985308740","https://openalex.org/W3008912312","https://openalex.org/W3151526698","https://openalex.org/W3167533889","https://openalex.org/W4210423654","https://openalex.org/W4225985539","https://openalex.org/W4319862458","https://openalex.org/W4372348570","https://openalex.org/W4391021542","https://openalex.org/W6603616073","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6695553435","https://openalex.org/W6754473786","https://openalex.org/W6763832098","https://openalex.org/W6767671539"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2366752344"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"Transducers":[3,10],"with":[4,32,90,127],"Pronunciation-aware":[5],"Embeddings":[6],"(PET).":[7],"Unlike":[8],"conventional":[9,61],"where":[11],"the":[12,21,33,110,113,128],"decoder":[13,24],"embeddings":[14],"for":[15,29],"different":[16],"tokens":[17,31],"are":[18],"trained":[19],"independently,":[20],"PET":[22,52,101],"model\u2019s":[23],"embedding":[25],"incorporates":[26],"shared":[27],"components":[28],"text":[30],"same":[34],"or":[35],"similar":[36],"pronunciations.":[37],"With":[38],"experiments":[39],"conducted":[40],"in":[41,44],"multiple":[42],"datasets":[43],"Mandarin":[45],"Chinese":[46],"and":[47],"Korean,":[48],"we":[49,70],"show":[50],"that":[51,69,100],"models":[53,102],"consistently":[54],"improve":[55],"speech":[56],"recognition":[57,77],"accuracy":[58],"compared":[59],"to":[60,87],"Transducers.":[62],"Our":[63,97,122],"investigation":[64],"also":[65],"uncovers":[66],"a":[67,119],"phenomenon":[68],"call":[71],"error":[72],"chain":[73],"reactions.":[74],"Instead":[75],"of":[76,112],"errors":[78,92,117],"being":[79],"evenly":[80],"spread":[81],"throughout":[82],"an":[83],"utterance,":[84],"they":[85],"tend":[86],"group":[88],"together,":[89],"subsequent":[91],"often":[93],"following":[94,118],"earlier":[95],"ones.":[96],"analysis":[98],"shows":[99],"effectively":[103],"mitigate":[104],"this":[105],"issue":[106],"by":[107],"substantially":[108],"reducing":[109],"likelihood":[111],"model":[114],"generating":[115],"additional":[116],"prior":[120],"one.":[121],"implementation":[123],"will":[124],"be":[125],"open-sourced":[126],"NeMo":[129],"toolkit.":[130]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}