{"id":"https://openalex.org/W2802422770","doi":"https://doi.org/10.1109/icassp.2018.8461704","title":"Neural Network Language Modeling with Letter-Based Features and Importance Sampling","display_name":"Neural Network Language Modeling with Letter-Based Features and Importance Sampling","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2802422770","doi":"https://doi.org/10.1109/icassp.2018.8461704","mag":"2802422770"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5034399968","display_name":"Hainan Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Hainan Xu","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University;","Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University;","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100343462","display_name":"Ke Li","orcid":"https://orcid.org/0000-0001-9206-0892"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Ke Li","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University;","Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University;","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377935","display_name":"Yiming Wang","orcid":"https://orcid.org/0000-0002-5932-4371"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Yiming Wang","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University;","Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University;","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370484","display_name":"Wang Jian","orcid":"https://orcid.org/0000-0002-7477-3343"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Wang","raw_affiliation_strings":["Toutiao AI Lab, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Toutiao AI Lab, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083463839","display_name":"Shiyin Kang","orcid":"https://orcid.org/0000-0001-8304-5260"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiyin Kang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082237990","display_name":"Xie Chen","orcid":"https://orcid.org/0000-0001-6205-5574"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xie Chen","raw_affiliation_strings":["Machine Intelligence Laboratory, Cambridge University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Machine Intelligence Laboratory, Cambridge University","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084286453","display_name":"Daniel Povey","orcid":"https://orcid.org/0000-0002-0611-3634"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Daniel Povey","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University;","Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University;","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]},{"id":"https://openalex.org/I4210098364","display_name":"Institute for Language and Speech Processing","ror":"https://ror.org/00z24kr14","country_code":"GR","type":"nonprofit","lineage":["https://openalex.org/I4210098364"]}],"countries":["GR","US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Center for Language and Speech Processing, Johns Hopkins University;","Center for Language and Speech Processing, Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University;","institution_ids":["https://openalex.org/I145311948","https://openalex.org/I4210098364"]},{"raw_affiliation_string":"Center for Language and Speech Processing, Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.98,"has_fulltext":false,"cited_by_count":55,"citation_normalized_percentile":{"value":0.96537883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6109","last_page":"6113"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","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/T10181","display_name":"Natural Language Processing Techniques","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/T10028","display_name":"Topic Modeling","score":0.9995999932289124,"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":0.9995999932289124,"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":0.8816176652908325},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7517248392105103},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6602904796600342},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6333305239677429},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.622790515422821},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.5959882140159607},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5463321208953857},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5195470452308655},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5038551688194275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.45555102825164795},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35370808839797974},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1359635293483734}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8816176652908325},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7517248392105103},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6602904796600342},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6333305239677429},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.622790515422821},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.5959882140159607},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5463321208953857},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5195470452308655},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5038551688194275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.45555102825164795},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35370808839797974},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1359635293483734},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8700000047683716}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1938755728","https://openalex.org/W1964742985","https://openalex.org/W1999965501","https://openalex.org/W2033612074","https://openalex.org/W2056590938","https://openalex.org/W2111305191","https://openalex.org/W2136189984","https://openalex.org/W2152790380","https://openalex.org/W2259472270","https://openalex.org/W2396033037","https://openalex.org/W2400997536","https://openalex.org/W2401969231","https://openalex.org/W2402146185","https://openalex.org/W2474824677","https://openalex.org/W2514741789","https://openalex.org/W2696967604","https://openalex.org/W2749475572","https://openalex.org/W2802201485","https://openalex.org/W2951559648","https://openalex.org/W2963347649","https://openalex.org/W2963582782","https://openalex.org/W2998704965","https://openalex.org/W6631362777","https://openalex.org/W6640598943","https://openalex.org/W6641128210","https://openalex.org/W6650436118","https://openalex.org/W6664908224","https://openalex.org/W6680450716","https://openalex.org/W6680532216","https://openalex.org/W6682948231","https://openalex.org/W6711802761","https://openalex.org/W6712930963","https://openalex.org/W6713346354","https://openalex.org/W6720877245"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2389073067","https://openalex.org/W4224009465","https://openalex.org/W1989705153","https://openalex.org/W4286629047","https://openalex.org/W2759980945","https://openalex.org/W2359001871","https://openalex.org/W1986205833","https://openalex.org/W2250741237"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"describe":[4],"an":[5],"extension":[6],"of":[7,32,40,64],"the":[8,30,45,79],"Kaldi":[9],"software":[10],"toolkit":[11],"to":[12,74],"support":[13],"neural-based":[14],"language":[15,96],"modeling,":[16],"intended":[17],"for":[18,62],"use":[19,31],"in":[20],"automatic":[21],"speech":[22],"recognition":[23],"(ASR)":[24],"and":[25,37,102],"related":[26],"tasks.":[27],"We":[28,54],"combine":[29],"subword":[33],"features":[34],"(letter":[35],"n-grams)":[36],"one-hot":[38],"encoding":[39],"frequent":[41],"words":[42],"so":[43],"that":[44,60,89],"models":[46],"can":[47],"handle":[48],"large":[49],"vocabularies":[50],"containing":[51],"infrequent":[52],"words.":[53],"propose":[55],"a":[56],"new":[57],"objective":[58],"function":[59],"allows":[61],"training":[63,77,103],"unnormalized":[65],"probabilities.":[66],"An":[67],"importance":[68],"sampling":[69],"based":[70],"method":[71],"is":[72,81],"supported":[73],"speed":[75],"up":[76],"when":[78],"vocabulary":[80],"large.":[82],"Experimental":[83],"results":[84],"on":[85,100],"five":[86],"corpora":[87],"show":[88],"Kaldi-RNNLM":[90],"rivals":[91],"other":[92],"recurrent":[93],"neural":[94],"network":[95],"model":[97],"toolkits":[98],"both":[99],"performance":[101],"speed.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":9}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}