{"id":"https://openalex.org/W4296068786","doi":"https://doi.org/10.21437/interspeech.2022-414","title":"VQ-T: RNN Transducers using Vector-Quantized Prediction Network States","display_name":"VQ-T: RNN Transducers using Vector-Quantized Prediction Network States","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296068786","doi":"https://doi.org/10.21437/interspeech.2022-414"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-414","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-414","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5101063912","display_name":"Jiatong Shi","orcid":null},"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":true,"raw_author_name":"Jiatong Shi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079994647","display_name":"George Saon","orcid":"https://orcid.org/0009-0004-6837-5009"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"George Saon","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049318367","display_name":"David Haws","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Haws","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"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":["Language Technologies Institute, Carnegie Mellon University, PA, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003725957","display_name":"Brian Kingsbury","orcid":"https://orcid.org/0000-0002-1343-6837"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Kingsbury","raw_affiliation_strings":["IBM Research AI, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Research AI, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101063912"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":0.3122,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50638367,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1656","last_page":"1660"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10320","display_name":"Neural Networks and Applications","score":0.9855999946594238,"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/T11949","display_name":"Nuclear Physics and Applications","score":0.9818000197410583,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7054944038391113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5621811747550964},{"id":"https://openalex.org/keywords/transducer","display_name":"Transducer","score":0.47353431582450867},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.37152400612831116},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35695546865463257},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3552131652832031},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33580249547958374},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.18594759702682495},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.17787611484527588}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7054944038391113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5621811747550964},{"id":"https://openalex.org/C56318395","wikidata":"https://www.wikidata.org/wiki/Q215928","display_name":"Transducer","level":2,"score":0.47353431582450867},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.37152400612831116},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35695546865463257},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3552131652832031},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33580249547958374},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.18594759702682495},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.17787611484527588}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-414","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-414","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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":38,"referenced_works":["https://openalex.org/W7198584","https://openalex.org/W38527073","https://openalex.org/W181370797","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1585876329","https://openalex.org/W1828163288","https://openalex.org/W1895481600","https://openalex.org/W1920923476","https://openalex.org/W1970987322","https://openalex.org/W2007261869","https://openalex.org/W2080401855","https://openalex.org/W2097003869","https://openalex.org/W2098318492","https://openalex.org/W2116047093","https://openalex.org/W2150907703","https://openalex.org/W2327501763","https://openalex.org/W2547875792","https://openalex.org/W2594610113","https://openalex.org/W2697044473","https://openalex.org/W2766219058","https://openalex.org/W2772028198","https://openalex.org/W2911544293","https://openalex.org/W2963414781","https://openalex.org/W2972451902","https://openalex.org/W2972953886","https://openalex.org/W2973229104","https://openalex.org/W2979476256","https://openalex.org/W3015190365","https://openalex.org/W3016234571","https://openalex.org/W3093427098","https://openalex.org/W3125709657","https://openalex.org/W3140224754","https://openalex.org/W3161375121","https://openalex.org/W3163300396","https://openalex.org/W3163793923","https://openalex.org/W3209355693","https://openalex.org/W4385739939"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W2012283803","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W4384820447","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W2072454424","https://openalex.org/W2117438306"],"abstract_inverted_index":{"Beam":[0],"search,":[1],"which":[2],"is":[3,41],"the":[4,35,57,64,69,82,87,116,126,129],"dominant":[5],"ASR":[6,70,93],"decoding":[7,20],"algorithm":[8],"for":[9,77,115],"end-to-end":[10],"models,":[11],"generates":[12],"tree-structured":[13],"hypotheses.However,":[14],"recent":[15],"studies":[16],"have":[17],"shown":[18],"that":[19,86],"with":[21,30,44,68,97,106],"hypothesis":[22,45],"merging":[23],"can":[24,73],"achieve":[25],"a":[26,107],"more":[27],"efficient":[28],"search":[29],"comparable":[31],"or":[32],"better":[33],"performance.But,":[34],"full":[36],"context":[37],"in":[38,56],"recurrent":[39],"networks":[40,100],"not":[42],"compatible":[43],"merging.We":[46],"propose":[47],"to":[48],"use":[49],"vector-quantized":[50],"long":[51],"short-term":[52],"memory":[53],"units":[54],"(VQ-LSTM)":[55],"prediction":[58,99],"network":[59],"of":[60,128],"RNN":[61,90],"transducers.By":[62],"training":[63],"discrete":[65],"representation":[66],"jointly":[67],"network,":[71],"hypotheses":[72],"be":[74],"actively":[75],"merged":[76],"lattice":[78,131],"generation.Our":[79],"experiments":[80,123],"on":[81],"Switchboard":[83],"corpus":[84],"show":[85],"proposed":[88,130],"VQ":[89],"transducers":[91,96],"improve":[92],"performance":[94],"over":[95],"regular":[98],"while":[101],"also":[102,124],"producing":[103],"denser":[104],"lattices":[105],"very":[108],"low":[109],"oracle":[110],"word":[111],"error":[112],"rate":[113],"(WER)":[114],"same":[117],"beam":[118],"size.Additional":[119],"language":[120],"model":[121],"rescoring":[122],"demonstrate":[125],"effectiveness":[127],"generation":[132],"scheme.":[133]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}