{"id":"https://openalex.org/W3010912466","doi":"https://doi.org/10.1109/ialp48816.2019.9037726","title":"A General Procedure for Improving Language Models in Low-Resource Speech Recognition","display_name":"A General Procedure for Improving Language Models in Low-Resource Speech Recognition","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3010912466","doi":"https://doi.org/10.1109/ialp48816.2019.9037726","mag":"3010912466"},"language":"en","primary_location":{"id":"doi:10.1109/ialp48816.2019.9037726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","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/A5037327117","display_name":"Qian Liu","orcid":"https://orcid.org/0000-0002-3162-935X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qian Liu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100620892","display_name":"Yao Liu","orcid":"https://orcid.org/0000-0002-4690-3008"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao Liu","raw_affiliation_strings":["China General Technology Research Institute, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China General Technology Research Institute, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"428","last_page":"433"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","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/T10201","display_name":"Speech Recognition and Synthesis","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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":0.9909999966621399,"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":0.8701717853546143},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7387826442718506},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6318643093109131},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6129351854324341},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6030285954475403},{"id":"https://openalex.org/keywords/lexicon","display_name":"Lexicon","score":0.5806664824485779},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.526155412197113},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5135378837585449},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.4669545590877533},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4531642496585846},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44404417276382446},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.4431299567222595},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4389488995075226},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.40912121534347534},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3713679313659668},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.09447333216667175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8701717853546143},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7387826442718506},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6318643093109131},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6129351854324341},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6030285954475403},{"id":"https://openalex.org/C2778121359","wikidata":"https://www.wikidata.org/wiki/Q8096","display_name":"Lexicon","level":2,"score":0.5806664824485779},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.526155412197113},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5135378837585449},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.4669545590877533},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4531642496585846},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44404417276382446},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.4431299567222595},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4389488995075226},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40912121534347534},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3713679313659668},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.09447333216667175},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp48816.2019.9037726","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ialp48816.2019.9037726","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Asian Language Processing (IALP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8399999737739563}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":49,"referenced_works":["https://openalex.org/W179707045","https://openalex.org/W179875071","https://openalex.org/W196214544","https://openalex.org/W309335912","https://openalex.org/W1494910745","https://openalex.org/W1524333225","https://openalex.org/W1614298861","https://openalex.org/W1631260214","https://openalex.org/W1981706894","https://openalex.org/W2090755665","https://openalex.org/W2110006374","https://openalex.org/W2117278770","https://openalex.org/W2123237149","https://openalex.org/W2131744502","https://openalex.org/W2155033295","https://openalex.org/W2158195707","https://openalex.org/W2250600805","https://openalex.org/W2278779172","https://openalex.org/W2290554209","https://openalex.org/W2399715921","https://openalex.org/W2402268235","https://openalex.org/W2407420912","https://openalex.org/W2407922671","https://openalex.org/W2514600732","https://openalex.org/W2516354030","https://openalex.org/W2638982800","https://openalex.org/W2671240430","https://openalex.org/W2671812860","https://openalex.org/W2746778230","https://openalex.org/W2950577311","https://openalex.org/W2951559648","https://openalex.org/W2963660642","https://openalex.org/W4299951565","https://openalex.org/W6607333740","https://openalex.org/W6607431696","https://openalex.org/W6607974698","https://openalex.org/W6629637077","https://openalex.org/W6631362777","https://openalex.org/W6636510571","https://openalex.org/W6636811518","https://openalex.org/W6640598943","https://openalex.org/W6677328538","https://openalex.org/W6678292227","https://openalex.org/W6679775712","https://openalex.org/W6691371945","https://openalex.org/W6713098461","https://openalex.org/W6713813099","https://openalex.org/W6714027799","https://openalex.org/W6739857368"],"related_works":["https://openalex.org/W2495256954","https://openalex.org/W2259317772","https://openalex.org/W2594897229","https://openalex.org/W2151348424","https://openalex.org/W4221142855","https://openalex.org/W2050138804","https://openalex.org/W4290708361","https://openalex.org/W2129812225","https://openalex.org/W26527944","https://openalex.org/W2523799048"],"abstract_inverted_index":{"It":[0],"is":[1,119],"difficult":[2],"for":[3,68,92],"a":[4,60],"language":[5],"model":[6],"(LM)":[7],"to":[8,30,38,65,85,123],"perform":[9],"well":[10],"with":[11],"limited":[12],"in-domain":[13],"transcripts":[14],"in":[15],"low-resource":[16],"speech":[17],"recognition.":[18],"In":[19],"this":[20],"paper,":[21],"we":[22,131],"mainly":[23],"summarize":[24],"and":[25,52,72],"extend":[26],"some":[27,129],"effective":[28,67],"methods":[29,42,56],"make":[31],"the":[32,35,87,124,140],"most":[33],"of":[34,89,114],"out-of-domain":[36,81],"data":[37,44,82,142],"improve":[39,86],"LMs.":[40,75],"These":[41],"include":[43],"selection,":[45],"vocabulary":[46],"expansion,":[47],"lexicon":[48],"augmentation,":[49],"multi-model":[50],"fusion":[51],"so":[53],"on.":[54],"The":[55],"are":[57,83],"integrated":[58],"into":[59],"systematic":[61],"procedure,":[62],"which":[63],"proves":[64],"be":[66],"improving":[69,109],"both":[70],"n-gram":[71],"neural":[73],"network":[74],"Additionally,":[76],"pre-trained":[77],"word":[78,115],"vectors":[79],"using":[80],"utilized":[84],"performance":[88],"RNN/LSTM":[90],"LMs":[91],"rescoring":[93],"first-pass":[94],"decoding":[95],"results.":[96],"Experiments":[97],"on":[98,139],"five":[99],"Asian":[100],"languages":[101],"from":[102],"Babel":[103],"Build":[104],"Packs":[105],"show":[106],"that,":[107],"after":[108],"LMs,":[110],"5.4-7.6%":[111],"relative":[112],"reduction":[113],"error":[116],"rate":[117],"(WER)":[118],"generally":[120],"achieved":[121],"compared":[122],"baseline":[125],"ASR":[126],"systems.":[127],"For":[128],"languages,":[130],"achieve":[132],"lower":[133],"WER":[134],"than":[135],"newly":[136],"published":[137],"results":[138],"same":[141],"sets.":[143]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}