{"id":"https://openalex.org/W4375869197","doi":"https://doi.org/10.1109/icassp49357.2023.10095553","title":"Multi-Blank Transducers for Speech Recognition","display_name":"Multi-Blank Transducers for Speech Recognition","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869197","doi":"https://doi.org/10.1109/icassp49357.2023.10095553"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095553","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5102775750","display_name":"Fei Jia","orcid":"https://orcid.org/0000-0003-4644-7193"},"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":"middle","author":{"id":"https://openalex.org/A5027823948","display_name":"Somshubra Majumdar","orcid":"https://orcid.org/0000-0001-5635-4893"},"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":"Somshubra Majumdar","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/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,PA,USA","Carnegie Mellon University, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,PA,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"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":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"28","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":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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/blank","display_name":"Blank","score":0.9715794324874878},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7409783601760864},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6511676907539368},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.5969270467758179},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5698121786117554},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.564814031124115},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.42668643593788147},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4119175970554352},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38525766134262085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33835846185684204},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33624041080474854},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08420860767364502},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07507681846618652}],"concepts":[{"id":"https://openalex.org/C2778089247","wikidata":"https://www.wikidata.org/wiki/Q368951","display_name":"Blank","level":2,"score":0.9715794324874878},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7409783601760864},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6511676907539368},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.5969270467758179},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5698121786117554},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.564814031124115},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.42668643593788147},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4119175970554352},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38525766134262085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33835846185684204},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33624041080474854},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08420860767364502},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07507681846618652},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095553","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095553","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1494198834","https://openalex.org/W1524333225","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2507132449","https://openalex.org/W2933138175","https://openalex.org/W2962780374","https://openalex.org/W2962784628","https://openalex.org/W2974231335","https://openalex.org/W3005302685","https://openalex.org/W3007227084","https://openalex.org/W3008912312","https://openalex.org/W3015315932","https://openalex.org/W3015686596","https://openalex.org/W3016010032","https://openalex.org/W3095173472","https://openalex.org/W3095410713","https://openalex.org/W3097777922","https://openalex.org/W3119308075","https://openalex.org/W3149509723","https://openalex.org/W3161571818","https://openalex.org/W3163907627","https://openalex.org/W3167533889","https://openalex.org/W3188328320","https://openalex.org/W4220743925","https://openalex.org/W4283700324","https://openalex.org/W4296069356","https://openalex.org/W4297841536","https://openalex.org/W4375869165","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6767671539"],"related_works":["https://openalex.org/W2361638505","https://openalex.org/W1993662208","https://openalex.org/W2370352440","https://openalex.org/W2009954581","https://openalex.org/W4296141694","https://openalex.org/W2379220204","https://openalex.org/W3160305016","https://openalex.org/W2005071119","https://openalex.org/W3158546193","https://openalex.org/W4249926107"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"a":[3,20,66],"modification":[4],"to":[5,48,73,99],"RNN-Transducer":[6],"(RNN-T)":[7],"models":[8],"for":[9,102],"automatic":[10],"speech":[11],"recognition":[12],"(ASR).":[13],"In":[14],"standard":[15],"RNN-T,":[16],"the":[17,49,56,126,129],"emission":[18],"of":[19,76,96,125],"blank":[21,35],"symbol":[22],"consumes":[23],"exactly":[24],"one":[25],"input":[26,42],"frame;":[27],"in":[28,71,128],"our":[29,123],"proposed":[30],"method,":[31],"we":[32,64,86],"introduce":[33],"additional":[34],"symbols,":[36],"which":[37],"consume":[38],"two":[39],"or":[40],"more":[41],"frames":[43],"when":[44],"emitted.":[45],"We":[46,120],"refer":[47],"added":[50],"symbols":[51],"as":[52],"big":[53,77],"blanks,":[54],"and":[55,84,105],"method":[57,70,114,127],"multi-blank":[58,62,89,112],"RNN-T.":[59],"For":[60],"training":[61],"RNN-Ts,":[63],"propose":[65],"novel":[67],"logit":[68],"under-normalization":[69],"order":[72],"prioritize":[74],"emissions":[75],"blanks.":[78],"With":[79],"experiments":[80],"on":[81],"multiple":[82],"languages":[83],"datasets,":[85,109],"show":[87],"that":[88],"RNN-T":[90,113],"methods":[91],"could":[92],"bring":[93],"relative":[94],"speedups":[95],"over":[97],"+90%/+139%":[98],"model":[100],"inference":[101],"English":[103],"Librispeech":[104,108],"German":[106],"Multilingual":[107],"respectively.":[110],"The":[111],"also":[115],"improves":[116],"ASR":[117],"accuracy":[118],"consistently.":[119],"will":[121],"release":[122],"implementation":[124],"NeMo":[130],"(https://github.com/NVIDIA/NeMo)":[131],"toolkit.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}