{"id":"https://openalex.org/W2951553268","doi":"https://doi.org/10.21437/interspeech.2018-1021","title":"Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR","display_name":"Unsupervised and Efficient Vocabulary Expansion for Recurrent Neural Network Language Models in ASR","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2951553268","doi":"https://doi.org/10.21437/interspeech.2018-1021","mag":"2951553268"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1021","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1806.10306","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047310084","display_name":"Yerbolat Khassanov","orcid":"https://orcid.org/0000-0001-9422-6833"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Yerbolat Khassanov","raw_affiliation_strings":["NTU Corporate Lab, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTU Corporate Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070872826","display_name":"Eng Siong Chng","orcid":"https://orcid.org/0000-0001-6257-7399"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Eng Siong Chng","raw_affiliation_strings":["NTU Corporate Lab, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTU Corporate Lab, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5047310084"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":0.7916,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78967251,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3343","last_page":"3347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994000196456909,"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/T10201","display_name":"Speech Recognition and Synthesis","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7767245173454285},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6754993796348572},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6074546575546265},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5606752634048462},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5597695112228394},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5314249992370605},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5233268737792969},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.36620277166366577},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.16342559456825256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7767245173454285},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6754993796348572},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6074546575546265},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5606752634048462},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5597695112228394},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5314249992370605},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5233268737792969},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.36620277166366577},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.16342559456825256},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2018-1021","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1021","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1806.10306","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.10306","pdf_url":"https://arxiv.org/pdf/1806.10306","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1806.10306","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1806.10306","pdf_url":"https://arxiv.org/pdf/1806.10306","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W36903255","https://openalex.org/W101286142","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W1520465330","https://openalex.org/W1524333225","https://openalex.org/W1558797106","https://openalex.org/W1591801644","https://openalex.org/W1614298861","https://openalex.org/W1631260214","https://openalex.org/W1847088711","https://openalex.org/W1938755728","https://openalex.org/W1965154800","https://openalex.org/W2038721957","https://openalex.org/W2057653135","https://openalex.org/W2111305191","https://openalex.org/W2117130368","https://openalex.org/W2120861206","https://openalex.org/W2131462252","https://openalex.org/W2141599568","https://openalex.org/W2152808281","https://openalex.org/W2158195707","https://openalex.org/W2171928131","https://openalex.org/W2250357346","https://openalex.org/W2250539671","https://openalex.org/W2259472270","https://openalex.org/W2345190899","https://openalex.org/W2402268235","https://openalex.org/W2519314406","https://openalex.org/W2611669587","https://openalex.org/W2802422770","https://openalex.org/W2899771611","https://openalex.org/W2950577311","https://openalex.org/W2951559648","https://openalex.org/W2963034893","https://openalex.org/W2963932686"],"related_works":["https://openalex.org/W4298287631","https://openalex.org/W2953061907","https://openalex.org/W1847088711","https://openalex.org/W4225394202","https://openalex.org/W3036642985","https://openalex.org/W3032952384","https://openalex.org/W2964335273","https://openalex.org/W2160451571","https://openalex.org/W2495256954","https://openalex.org/W2259317772"],"abstract_inverted_index":{"In":[0,136],"automatic":[1],"speech":[2,48],"recognition":[3],"(ASR)":[4],"systems,":[5],"recurrent":[6],"neural":[7],"network":[8,67],"language":[9],"models":[10],"(RNNLM)":[11],"are":[12,154],"used":[13],"to":[14,24,42,58,78,163,179,186],"rescore":[15],"a":[16,84],"word":[17,124],"lattice":[18],"or":[19],"N-best":[20],"hypotheses":[21],"list.":[22],"Due":[23],"the":[25,28,60,65,80,99,123,132,139,142,165,181],"expensive":[26,89],"training,":[27],"RNNLM's":[29],"vocabulary":[30,188],"set":[31,82],"accommodates":[32],"only":[33],"small":[34],"shortlist":[35,61,81],"of":[36,83,101,141,183],"most":[37],"frequent":[38],"words.":[39,53,175],"This":[40],"leads":[41],"suboptimal":[43],"performance":[44],"if":[45],"an":[46,75],"input":[47,110],"contains":[49],"many":[50],"out-of-shortlist":[51],"(OOS)":[52],"An":[54],"effective":[55],"solution":[56],"is":[57,69],"increase":[59],"size":[62],"and":[63,91,115,130],"retrain":[64],"entire":[66],"which":[68,103],"highly":[70],"inefficient.":[71],"Therefore,":[72],"we":[73,177],"propose":[74,162,178],"efficient":[76],"method":[77,97,121],"expand":[79,187],"pretrained":[85,143],"RNNLM":[86,102,144],"without":[87],"incurring":[88],"retraining":[90],"using":[92],"additional":[93],"training":[94],"data.":[95],"Our":[96],"exploits":[98],"structure":[100],"can":[104],"be":[105,146],"decoupled":[106],"into":[107],"three":[108],"parts:":[109],"projection":[111,117,128],"layer,":[112],"middle":[113,133],"layers,":[114],"output":[116],"layer.":[118],"Specifically,":[119],"our":[120],"expands":[122],"embedding":[125,159],"matrices":[126],"in":[127,157,189],"layers":[129,134],"keeps":[131],"unchanged.":[135],"this":[137],"approach,":[138],"functionality":[140],"will":[145],"correctly":[147],"maintained":[148],"as":[149,151],"long":[150],"OOS":[152,166,184],"words":[153,167,185],"properly":[155],"modeled":[156],"two":[158],"spaces.":[160],"We":[161],"model":[164],"by":[168,192],"borrowing":[169],"linguistic":[170],"knowledge":[171],"from":[172,196],"appropriate":[173],"in-shortlist":[174],"Additionally,":[176],"generate":[180],"list":[182],"unsupervised":[190],"manner":[191],"automatically":[193],"extracting":[194],"them":[195],"ASR":[197],"output.":[198]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2019-06-27T00:00:00"}