{"id":"https://openalex.org/W4319862724","doi":"https://doi.org/10.1109/slt54892.2023.10022569","title":"An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition","display_name":"An Investigation of Monotonic Transducers for Large-Scale Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-01-09","ids":{"openalex":"https://openalex.org/W4319862724","doi":"https://doi.org/10.1109/slt54892.2023.10022569"},"language":"en","primary_location":{"id":"doi:10.1109/slt54892.2023.10022569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022569","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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/A5071286568","display_name":"Niko Moritz","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Niko Moritz","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072932051","display_name":"Frank Seide","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frank Seide","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103098852","display_name":"Duc Le","orcid":"https://orcid.org/0000-0001-9490-2563"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duc Le","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074237839","display_name":"Jay Mahadeokar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jay Mahadeokar","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047073253","display_name":"Christian Fuegen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christian Fuegen","raw_affiliation_strings":["Meta AI"],"affiliations":[{"raw_affiliation_string":"Meta AI","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5071286568"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7706,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.67319588,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"324","last_page":"330"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9980000257492065,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9966999888420105,"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/monotonic-function","display_name":"Monotonic function","score":0.8500455617904663},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.8096306324005127},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7116726040840149},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6875324845314026},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5832513570785522},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5218940377235413},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49753478169441223},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.4654695689678192},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4115734100341797},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40852075815200806},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33226513862609863},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17923614382743835},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14486068487167358},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.1308692991733551}],"concepts":[{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.8500455617904663},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.8096306324005127},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7116726040840149},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6875324845314026},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5832513570785522},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5218940377235413},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49753478169441223},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.4654695689678192},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4115734100341797},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40852075815200806},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33226513862609863},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17923614382743835},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14486068487167358},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.1308692991733551},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt54892.2023.10022569","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt54892.2023.10022569","pdf_url":null,"source":{"id":"https://openalex.org/S4363605953","display_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE Spoken Language Technology Workshop (SLT)","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":37,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1526236009","https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2131342762","https://openalex.org/W2157749010","https://openalex.org/W2327501763","https://openalex.org/W2514741789","https://openalex.org/W2933138175","https://openalex.org/W2962760690","https://openalex.org/W2962780374","https://openalex.org/W2963414781","https://openalex.org/W2987019345","https://openalex.org/W3007227084","https://openalex.org/W3008174054","https://openalex.org/W3015190365","https://openalex.org/W3015194534","https://openalex.org/W3015315932","https://openalex.org/W3015974384","https://openalex.org/W3016010032","https://openalex.org/W3016234571","https://openalex.org/W3028545098","https://openalex.org/W3094667432","https://openalex.org/W3095311338","https://openalex.org/W3097777922","https://openalex.org/W3149509723","https://openalex.org/W3152221657","https://openalex.org/W3162665866","https://openalex.org/W3162833755","https://openalex.org/W3163907627","https://openalex.org/W3197654132","https://openalex.org/W3211040052","https://openalex.org/W4210663600","https://openalex.org/W4287647128","https://openalex.org/W6638749077","https://openalex.org/W6770245836","https://openalex.org/W6783314596"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W3176564347","https://openalex.org/W3031039437","https://openalex.org/W3204184292","https://openalex.org/W1985458517","https://openalex.org/W2355833770","https://openalex.org/W1732468982","https://openalex.org/W2805949325","https://openalex.org/W4300536205"],"abstract_inverted_index":{"The":[0],"two":[1,23],"most":[2],"popular":[3],"loss":[4,24],"functions":[5],"for":[6,134,137],"streaming":[7],"end-to-end":[8],"automatic":[9],"speech":[10],"recognition":[11],"(ASR)":[12],"are":[13,76],"RNN-Transducer":[14],"(RNN-T)":[15],"and":[16,33,75,122,136],"connectionist":[17],"temporal":[18],"classification":[19],"(CTC).":[20],"Between":[21],"these":[22],"types":[25],"we":[26],"can":[27,48],"classify":[28],"the":[29,34,86,109],"monotonic":[30,65],"RNN-T":[31,47],"(MonoRNN-T)":[32],"recently":[35],"proposed":[36],"CTC-like":[37],"Transducer":[38],"(CTC-T).":[39],"Monotonic":[40],"transducers":[41,66],"have":[42,94,102],"a":[43,54,138],"few":[44],"advantages.":[45],"First,":[46],"suffer":[49],"from":[50,118],"runaway":[51],"hallucination,":[52],"where":[53],"model":[55,70],"keeps":[56],"emitting":[57],"non-blank":[58],"symbols":[59],"without":[60],"advancing":[61],"in":[62],"time.":[63],"Secondly,":[64],"consume":[67],"exactly":[68],"one":[69],"score":[71],"per":[72],"time":[73],"step":[74],"therefore":[77],"more":[78],"compatible":[79],"with":[80],"traditional":[81],"FST-based":[82],"ASR":[83],"decoders.":[84],"However,":[85],"MonoRNN-T":[87,121],"so":[88],"far":[89],"has":[90],"been":[91],"found":[92],"to":[93,103],"worse":[95],"accuracy":[96],"than":[97,129],"RNN-T.":[98,130],"It":[99],"does":[100],"not":[101],"be":[104],"that":[105],"way:":[106],"By":[107],"regularizing":[108],"training":[110,114],"via":[111],"joint":[112],"LAS":[113],"or":[115,127],"parameter":[116],"initialization":[117],"RNN-T,":[119],"both":[120],"CTC-T":[123],"perform":[124],"as":[125],"well":[126],"better":[128],"This":[131],"is":[132],"demonstrated":[133],"LibriSpeech":[135],"large-scale":[139],"in-house":[140],"data":[141],"set.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}