{"id":"https://openalex.org/W3136989387","doi":"https://doi.org/10.1109/icassp39728.2021.9414716","title":"Advancing RNN Transducer Technology for Speech Recognition","display_name":"Advancing RNN Transducer Technology for Speech Recognition","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3136989387","doi":"https://doi.org/10.1109/icassp39728.2021.9414716","mag":"3136989387"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2103.09935","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zoltan Tuske","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zoltan Tuske","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047310311","display_name":"Daniel Bola\u00f1os","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Daniel Bolanos","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Research AI, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5654","last_page":"5658"},"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":0.9980999827384949,"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":0.9936000108718872,"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/computer-science","display_name":"Computer science","score":0.7899547815322876},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7129913568496704},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7114882469177246},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.6887567639350891},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.6630575060844421},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6355107426643372},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6077302098274231},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5083405375480652},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4863439202308655},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.461056113243103},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.452130526304245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42795509099960327},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38897132873535156},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.30455851554870605},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08135470747947693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7899547815322876},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7129913568496704},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7114882469177246},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.6887567639350891},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.6630575060844421},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6355107426643372},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6077302098274231},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5083405375480652},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4863439202308655},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.461056113243103},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.452130526304245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42795509099960327},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38897132873535156},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.30455851554870605},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08135470747947693},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414716","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2103.09935","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.09935","pdf_url":"https://arxiv.org/pdf/2103.09935","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3136989387","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2103.09935.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2103.09935","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2103.09935","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"},{"id":"doi:10.17023/eg8d-wq22","is_oa":true,"landing_page_url":"https://doi.org/10.17023/eg8d-wq22","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Audiovisual"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2103.09935","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2103.09935","pdf_url":"https://arxiv.org/pdf/2103.09935","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5299999713897705,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3136989387.pdf","grobid_xml":"https://content.openalex.org/works/W3136989387.grobid-xml"},"referenced_works_count":49,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1524333225","https://openalex.org/W1828163288","https://openalex.org/W2079623482","https://openalex.org/W2143612262","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2525778437","https://openalex.org/W2888519496","https://openalex.org/W2889282842","https://openalex.org/W2911544293","https://openalex.org/W2936774411","https://openalex.org/W2937780860","https://openalex.org/W2952148143","https://openalex.org/W2962760690","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963414781","https://openalex.org/W2963573053","https://openalex.org/W2963587345","https://openalex.org/W2963827914","https://openalex.org/W2973229104","https://openalex.org/W2982413405","https://openalex.org/W2987019345","https://openalex.org/W2990501692","https://openalex.org/W2994821360","https://openalex.org/W3002595344","https://openalex.org/W3007227084","https://openalex.org/W3007776460","https://openalex.org/W3008037978","https://openalex.org/W3008174054","https://openalex.org/W3011207290","https://openalex.org/W3015190365","https://openalex.org/W3016234571","https://openalex.org/W3021984791","https://openalex.org/W3028545098","https://openalex.org/W3096518646","https://openalex.org/W3097747488","https://openalex.org/W6600213771","https://openalex.org/W6631362777","https://openalex.org/W6638749077","https://openalex.org/W6713762819","https://openalex.org/W6719700797","https://openalex.org/W6756286202","https://openalex.org/W6769806307","https://openalex.org/W6770245836","https://openalex.org/W6770425081","https://openalex.org/W6771465236","https://openalex.org/W6776544788"],"related_works":["https://openalex.org/W2936774411","https://openalex.org/W1828163288","https://openalex.org/W2963403868","https://openalex.org/W2127141656","https://openalex.org/W2782451907","https://openalex.org/W3011207290","https://openalex.org/W3134568285","https://openalex.org/W854541894","https://openalex.org/W3097777922","https://openalex.org/W3002595344","https://openalex.org/W2964121744","https://openalex.org/W2407080277","https://openalex.org/W2327501763","https://openalex.org/W2064675550","https://openalex.org/W2594897229","https://openalex.org/W2949937978","https://openalex.org/W2920796740","https://openalex.org/W2533523411","https://openalex.org/W2759071281","https://openalex.org/W2160648924"],"abstract_inverted_index":{"We":[0,126],"investigate":[1],"a":[2,55,128,149],"set":[3],"of":[4,59,79,95,116,142],"techniques":[5,36],"for":[6,104],"RNN":[7],"Transducers":[8],"(RNN-Ts)":[9],"that":[10],"were":[11],"instrumental":[12],"in":[13,66,85],"lowering":[14],"the":[15,60,67,77,93,96,113,136,143,153],"word":[16,132],"error":[17,133],"rate":[18,134],"on":[19,123,135,152],"three":[20],"different":[21],"tasks":[22],"(Switchboard":[23],"300":[24],"hours,":[25],"conversational":[26,31],"Spanish":[27],"780":[28],"hours":[29],"and":[30,48,62,120,130,138,148],"Italian":[32,156],"900":[33],"hours).":[34],"The":[35],"pertain":[37],"to":[38,72,83],"architectural":[39],"changes,":[40],"speaker":[41,81],"adaptation,":[42],"language":[43,101],"model":[44,46,102],"fusion,":[45],"combination":[47],"general":[49],"training":[50,118],"recipe.":[51],"First,":[52],"we":[53,75,91,111],"introduce":[54],"novel":[56],"multiplicative":[57],"integration":[58],"encoder":[61],"prediction":[63],"network":[64,69],"vectors":[65],"joint":[68],"(as":[70],"opposed":[71],"additive).":[73],"Second,":[74],"discuss":[76],"applicability":[78],"i-vector":[80],"adaptation":[82],"RNN-Ts":[84],"conjunction":[86],"with":[87],"data":[88],"perturbation.":[89],"Third,":[90],"explore":[92],"effectiveness":[94],"recently":[97],"proposed":[98],"density":[99],"ratio":[100],"fusion":[103],"these":[105],"tasks.":[106],"Last":[107],"but":[108],"not":[109],"least,":[110],"describe":[112],"other":[114],"components":[115],"our":[117],"recipe":[119],"their":[121],"effect":[122],"recognition":[124],"performance.":[125],"report":[127],"5.9%":[129],"12.5%":[131],"Switchboard":[137],"CallHome":[139],"test":[140,157],"sets":[141],"NIST":[144],"Hub5":[145],"2000":[146],"evaluation":[147],"12.7%":[150],"WER":[151],"Mozilla":[154],"CommonVoice":[155],"set.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}