{"id":"https://openalex.org/W4385823303","doi":"https://doi.org/10.21437/interspeech.2023-1362","title":"Memory Augmented Lookup Dictionary Based Language Modeling for Automatic Speech Recognition","display_name":"Memory Augmented Lookup Dictionary Based Language Modeling for Automatic Speech Recognition","publication_year":2023,"publication_date":"2023-08-14","ids":{"openalex":"https://openalex.org/W4385823303","doi":"https://doi.org/10.21437/interspeech.2023-1362"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2023-1362","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1362","pdf_url":"https://www.isca-archive.org/interspeech_2023/feng23d_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.isca-archive.org/interspeech_2023/feng23d_interspeech.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101199919","display_name":"Yukun Feng","orcid":"https://orcid.org/0009-0002-5467-5954"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yukun Feng","raw_affiliation_strings":["ByteDance Inc , San Jose , CA , US"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc , San Jose , CA , US","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102334100","display_name":"Ming Tu","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Tu","raw_affiliation_strings":["ByteDance Inc , San Jose , CA , US"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc , San Jose , CA , US","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100605555","display_name":"Rui Xia","orcid":"https://orcid.org/0000-0003-3605-509X"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Xia","raw_affiliation_strings":["ByteDance Inc , San Jose , CA , US"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc , San Jose , CA , US","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018343941","display_name":"Chuanzeng Huang","orcid":null},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuanzeng Huang","raw_affiliation_strings":["ByteDance Inc , San Jose , CA , US"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc , San Jose , CA , US","institution_ids":["https://openalex.org/I173632517"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103854502","display_name":"Yuxuan Wang","orcid":"https://orcid.org/0000-0001-8269-3354"},"institutions":[{"id":"https://openalex.org/I173632517","display_name":"MediaTek (China)","ror":"https://ror.org/05xvgy636","country_code":"CN","type":"company","lineage":["https://openalex.org/I173632517","https://openalex.org/I4210148979"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxuan Wang","raw_affiliation_strings":["ByteDance Inc , San Jose , CA , US"],"affiliations":[{"raw_affiliation_string":"ByteDance Inc , San Jose , CA , US","institution_ids":["https://openalex.org/I173632517"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101199919"],"corresponding_institution_ids":["https://openalex.org/I173632517"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09861739,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"481","last_page":"485"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7732999920845032,"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":0.7732999920845032,"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":0.8579565286636353},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6455954909324646},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5296440124511719},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47090935707092285},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43761271238327026},{"id":"https://openalex.org/keywords/lookup-table","display_name":"Lookup table","score":0.4231104552745819},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.17227420210838318}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8579565286636353},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6455954909324646},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5296440124511719},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47090935707092285},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43761271238327026},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.4231104552745819},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.17227420210838318}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2023-1362","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1362","pdf_url":"https://www.isca-archive.org/interspeech_2023/feng23d_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2023-1362","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2023-1362","pdf_url":"https://www.isca-archive.org/interspeech_2023/feng23d_interspeech.pdf","source":null,"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"INTERSPEECH 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6100000143051147,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385823303.pdf","grobid_xml":"https://content.openalex.org/works/W4385823303.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2798215405","https://openalex.org/W2990962948","https://openalex.org/W2084169748","https://openalex.org/W2127529229","https://openalex.org/W2355515259","https://openalex.org/W2124289628","https://openalex.org/W1822998120","https://openalex.org/W2165625444","https://openalex.org/W2524480813","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recent":[0],"studies":[1,49],"have":[2,35],"shown":[3],"that":[4,20],"using":[5],"an":[6],"external":[7],"Language":[8],"Model":[9],"(LM)":[10],"benefits":[11],"the":[12,25,103,126,131,139],"end-to-end":[13],"Automatic":[14],"Speech":[15],"Recognition":[16],"(ASR).However,":[17],"predicting":[18],"tokens":[19,118],"appear":[21],"less":[22],"frequently":[23],"in":[24,39,77,137],"training":[26,78],"set":[27],"is":[28,81,99,121],"still":[29],"quite":[30],"challenging.The":[31],"longtail":[32,145],"prediction":[33],"problems":[34],"been":[36,44],"widely":[37],"studied":[38],"many":[40],"applications,":[41],"but":[42],"only":[43],"addressed":[45],"by":[46,107],"a":[47,58,108],"few":[48],"for":[50,67,144],"ASR":[51,140],"and":[52,92,116],"LMs.In":[53],"this":[54],"paper,":[55],"we":[56,129],"propose":[57],"new":[59],"memory":[60],"augmented":[61],"lookup":[62,71],"dictionary":[63,72],"based":[64],"Transformer":[65,105],"architecture":[66],"LM.The":[68],"newly":[69],"introduced":[70],"incorporates":[73],"rich":[74],"contextual":[75],"information":[76],"set,":[79],"which":[80],"vital":[82],"to":[83,101],"correctly":[84],"predict":[85],"long-tail":[86],"tokens.With":[87],"intensive":[88],"experiments":[89],"on":[90,111,125],"Chinese":[91],"English":[93],"data":[94],"sets,":[95],"our":[96,134],"proposed":[97,135],"method":[98,136],"proved":[100],"outperform":[102],"baseline":[104],"LM":[106],"great":[109],"margin":[110],"both":[112],"word/character":[113],"error":[114,119],"rate":[115],"tail":[117],"rate.This":[120],"achieved":[122],"without":[123],"impact":[124],"decoding":[127,141],"efficiency.Overall,":[128],"demonstrate":[130],"effectiveness":[132],"of":[133],"boosting":[138],"performance,":[142],"especially":[143],"tokens.":[146]},"counts_by_year":[],"updated_date":"2026-03-14T06:41:57.775601","created_date":"2025-10-10T00:00:00"}