{"id":"https://openalex.org/W4213423981","doi":"https://doi.org/10.1109/lsp.2022.3154241","title":"Improving Mandarin End-to-End Speech Recognition With Word N-Gram Language Model","display_name":"Improving Mandarin End-to-End Speech Recognition With Word N-Gram Language Model","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4213423981","doi":"https://doi.org/10.1109/lsp.2022.3154241"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2022.3154241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3154241","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2201.01995","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068192693","display_name":"Jinchuan Tian","orcid":"https://orcid.org/0000-0002-2129-471X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jinchuan Tian","raw_affiliation_strings":["Advanced Data and Signal Processing Laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Advanced Data and Signal Processing Laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004643540","display_name":"Jianwei Yu","orcid":"https://orcid.org/0000-0002-2449-1436"},"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":"Jianwei Yu","raw_affiliation_strings":["Tencent AI LAB, China","Tencent ASR Oteam, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI LAB, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent ASR Oteam, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"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":"Chao Weng","raw_affiliation_strings":["Tencent AI LAB, China","Tencent ASR Oteam, China"],"affiliations":[{"raw_affiliation_string":"Tencent AI LAB, China","institution_ids":["https://openalex.org/I2250653659"]},{"raw_affiliation_string":"Tencent ASR Oteam, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002795838","display_name":"Yuexian Zou","orcid":"https://orcid.org/0000-0001-9999-6140"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuexian Zou","raw_affiliation_strings":["Advanced Data and Signal Processing Laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Advanced Data and Signal Processing Laboratory, School of Electric and Computer Science, Peking University, Shenzhen Graduate School, Shenzhen, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"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":"Dong Yu","raw_affiliation_strings":["Tencent ASR Oteam, China"],"affiliations":[{"raw_affiliation_string":"Tencent ASR Oteam, China","institution_ids":["https://openalex.org/I2250653659"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068192693"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.7927,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.86877168,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"29","issue":null,"first_page":"812","last_page":"816"},"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":0.9990000128746033,"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/T10860","display_name":"Speech and Audio Processing","score":0.9965000152587891,"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":0.7721073627471924},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.756956160068512},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6610949635505676},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6566889882087708},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6340386867523193},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5851013660430908},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5168431401252747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.41868114471435547},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.15290164947509766},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12352865934371948},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0675070583820343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7721073627471924},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.756956160068512},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6610949635505676},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6566889882087708},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6340386867523193},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5851013660430908},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5168431401252747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41868114471435547},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.15290164947509766},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12352865934371948},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0675070583820343},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/lsp.2022.3154241","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2022.3154241","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2201.01995","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.01995","pdf_url":"https://arxiv.org/pdf/2201.01995","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":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2201.01995","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2201.01995","pdf_url":"https://arxiv.org/pdf/2201.01995","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":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.5600000023841858,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1574901103","https://openalex.org/W1631260214","https://openalex.org/W1828163288","https://openalex.org/W1915251500","https://openalex.org/W2046932483","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2408623794","https://openalex.org/W2514741789","https://openalex.org/W2766219058","https://openalex.org/W2787663903","https://openalex.org/W2794289187","https://openalex.org/W2886180730","https://openalex.org/W2888779557","https://openalex.org/W2889048668","https://openalex.org/W2889282842","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2963242190","https://openalex.org/W2963362078","https://openalex.org/W2964539095","https://openalex.org/W3015190365","https://openalex.org/W3015611708","https://openalex.org/W3095376166","https://openalex.org/W3097777922","https://openalex.org/W3156902660","https://openalex.org/W3163793923","https://openalex.org/W3164692279","https://openalex.org/W3167533889","https://openalex.org/W3197478142","https://openalex.org/W3200601846","https://openalex.org/W4200629210","https://openalex.org/W4299649720","https://openalex.org/W4310658830","https://openalex.org/W4327845728","https://openalex.org/W4385245566","https://openalex.org/W6640059789","https://openalex.org/W6739901393","https://openalex.org/W6754473786","https://openalex.org/W6794920533"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Despite":[0],"the":[1,22,27,37,60,67,73,76,157,161,167],"rapid":[2],"progress":[3],"of":[4,30,62,75,160],"end-to-end":[5],"(E2E)":[6],"automatic":[7],"speech":[8],"recognition":[9,28],"(ASR),":[10],"it":[11],"has":[12],"been":[13,86],"shown":[14],"that":[15,193],"incorporating":[16],"external":[17,77,91,172],"language":[18],"models":[19],"(LMs)":[20],"into":[21],"decoding":[23,137],"can":[24,124],"further":[25],"improve":[26],"performance":[29],"E2E":[31,41,56,80,94],"ASR":[32,42,57],"systems.":[33,58],"To":[34,130],"align":[35],"with":[36,54,103,170],"modelingunits":[38],"adopted":[39],"in":[40,79,93,119],"systems,":[43],"subword-level":[44,63,198],"(e.g.,":[45],"characters,":[46],"BPE)":[47],"LMs":[48,64,78,92],"are":[49,98],"usually":[50],"used":[51],"to":[52,88,115,146],"cooperate":[53],"current":[55],"However,":[59],"use":[61],"will":[65],"ignore":[66],"word-level":[68,90,141],"information,":[69],"which":[70,120],"may":[71],"limit":[72],"strength":[74],"ASR.":[81],"Although":[82],"several":[83],"methods":[84,97],"have":[85,125],"proposed":[87,177],"incorporate":[89],"ASR,":[95],"these":[96],"mainly":[99],"designed":[100],"for":[101,152],"languages":[102,116],"clear":[104],"word":[105,128,150,173],"boundaries":[106],"such":[107],"as":[108],"English":[109],"and":[110,186,203,216,221],"cannot":[111],"be":[112],"directly":[113],"applied":[114],"like":[117],"Mandarin,":[118],"each":[121,153],"character":[122],"sequence":[123],"multiple":[126],"corresponding":[127],"sequences.":[129],"this":[131],"end,":[132],"we":[133],"propose":[134],"a":[135,140,228],"novel":[136],"algorithm":[138],"where":[139],"lattice":[142,169],"is":[143,163,179,233],"constructed":[144],"on-the-fly":[145],"consider":[147],"all":[148],"possible":[149],"sequences":[151],"partial":[154],"hypothesis.":[155],"Then,":[156],"LM":[158,202],"score":[159],"hypothesis":[162],"obtained":[164],"by":[165,224],"intersecting":[166],"generated":[168],"an":[171],"N-gram":[174,201],"LM.":[175,206],"The":[176],"method":[178,195],"examined":[180],"on":[181,211,227],"both":[182,212],"Attention-based":[183],"Encoder-Decoder":[184],"(AED)":[185],"Neural":[187],"Transducer":[188],"(NT)":[189],"frameworks.":[190],"Experiments":[191],"suggest":[192],"our":[194],"consistently":[196],"outperforms":[197],"LMs,":[199],"including":[200],"neural":[204],"network":[205],"We":[207],"achieve":[208],"state-of-the-art":[209],"results":[210],"Aishell-1":[213],"(CER":[214,218],"4.18%)":[215],"Aishell-2":[217],"5.06%)":[219],"datasets":[220],"reduce":[222],"CER":[223],"14.8%":[225],"relatively":[226],"21K-hour":[229],"Mandarin":[230],"dataset.":[231],"Code":[232],"released.":[234]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":5}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}