{"id":"https://openalex.org/W3204687321","doi":"https://doi.org/10.1109/icassp43922.2022.9746830","title":"Minimum Word Error Training For Non-Autoregressive Transformer-Based Code-Switching ASR","display_name":"Minimum Word Error Training For Non-Autoregressive Transformer-Based Code-Switching ASR","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W3204687321","doi":"https://doi.org/10.1109/icassp43922.2022.9746830","mag":"3204687321"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746830","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 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/A5051467915","display_name":"Yizhou Peng","orcid":null},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizhou Peng","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,China","School of Information Science and Engineering, Xinjiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100729896","display_name":"Jicheng Zhang","orcid":"https://orcid.org/0000-0003-4295-2950"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jicheng Zhang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,China","School of Information Science and Engineering, Xinjiang University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039696635","display_name":"Haihua Xu","orcid":"https://orcid.org/0000-0002-2220-8465"},"institutions":[{"id":"https://openalex.org/I4210109012","display_name":"Waseda Bioscience Research Institute in Singapore","ror":"https://ror.org/01m343c98","country_code":"SG","type":"education","lineage":["https://openalex.org/I4210109012"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Haihua Xu","raw_affiliation_strings":["Bytedance AI Lab,Singapore","Bytedance AI Lab, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Bytedance AI Lab,Singapore","institution_ids":["https://openalex.org/I4210109012"]},{"raw_affiliation_string":"Bytedance AI Lab, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024772368","display_name":"Hao Huang","orcid":"https://orcid.org/0000-0001-6604-0951"},"institutions":[{"id":"https://openalex.org/I96908189","display_name":"Xinjiang University","ror":"https://ror.org/059gw8r13","country_code":"CN","type":"education","lineage":["https://openalex.org/I96908189"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Huang","raw_affiliation_strings":["Xinjiang University,School of Information Science and Engineering,China","School of Information Science and Engineering, Xinjiang University, China","Xinjiang Provincial Key Laboratory of Multi-Lingual Information Technology, Urumqi, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xinjiang University,School of Information Science and Engineering,China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"School of Information Science and Engineering, Xinjiang University, China","institution_ids":["https://openalex.org/I96908189"]},{"raw_affiliation_string":"Xinjiang Provincial Key Laboratory of Multi-Lingual Information Technology, Urumqi, China","institution_ids":[]}]},{"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":["Nanyang Technological University,School of Computer Science and Engineering,Singapore","School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University,School of Computer Science and Engineering,Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6869,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.85955827,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"7807","last_page":"7811"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9986000061035156,"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/T10601","display_name":"Handwritten Text Recognition Techniques","score":0.9879000186920166,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.7750498056411743},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.7000081539154053},{"id":"https://openalex.org/keywords/code-switching","display_name":"Code-switching","score":0.601412296295166},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5408127903938293},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5233951210975647},{"id":"https://openalex.org/keywords/word-embedding","display_name":"Word embedding","score":0.502622127532959},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.48713967204093933},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4849410355091095},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.47455722093582153},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.45749151706695557},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4514939486980438},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.45133382081985474},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3969873785972595},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.23250272870063782},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09795612096786499},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09728321433067322}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7750498056411743},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.7000081539154053},{"id":"https://openalex.org/C18552078","wikidata":"https://www.wikidata.org/wiki/Q255615","display_name":"Code-switching","level":2,"score":0.601412296295166},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5408127903938293},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5233951210975647},{"id":"https://openalex.org/C2777462759","wikidata":"https://www.wikidata.org/wiki/Q18395344","display_name":"Word embedding","level":3,"score":0.502622127532959},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.48713967204093933},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4849410355091095},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.47455722093582153},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.45749151706695557},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514939486980438},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.45133382081985474},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3969873785972595},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.23250272870063782},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09795612096786499},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09728321433067322},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/icassp43922.2022.9746830","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746830","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1828163288","https://openalex.org/W2127141656","https://openalex.org/W2407080277","https://openalex.org/W2526425061","https://openalex.org/W2626778328","https://openalex.org/W2746192915","https://openalex.org/W2766219058","https://openalex.org/W2767206889","https://openalex.org/W2795935804","https://openalex.org/W2892009249","https://openalex.org/W2926989360","https://openalex.org/W2936774411","https://openalex.org/W2962765220","https://openalex.org/W2962780374","https://openalex.org/W2963414781","https://openalex.org/W2963434219","https://openalex.org/W2963747784","https://openalex.org/W2964156075","https://openalex.org/W2964330921","https://openalex.org/W2988975212","https://openalex.org/W3014413043","https://openalex.org/W3023751411","https://openalex.org/W3024732798","https://openalex.org/W3097625183","https://openalex.org/W3097777922","https://openalex.org/W3097874139","https://openalex.org/W3097882114","https://openalex.org/W3100753857","https://openalex.org/W3147414526","https://openalex.org/W3160622492","https://openalex.org/W3162899666","https://openalex.org/W3197530164","https://openalex.org/W3198522318","https://openalex.org/W4226440507","https://openalex.org/W4385245566","https://openalex.org/W6638749077","https://openalex.org/W6739901393","https://openalex.org/W6746208923","https://openalex.org/W6747398299","https://openalex.org/W6775187155"],"related_works":["https://openalex.org/W2432897346","https://openalex.org/W2771594921","https://openalex.org/W3138119129","https://openalex.org/W2181336723","https://openalex.org/W3158134258","https://openalex.org/W2125652721","https://openalex.org/W1540371141","https://openalex.org/W2940588741","https://openalex.org/W2293063924","https://openalex.org/W2896411932"],"abstract_inverted_index":{"Non-autoregressive":[0],"end-to-end":[1],"ASR":[2,33,53],"framework":[3],"might":[4],"be":[5],"potentially":[6],"appropriate":[7],"for":[8,107,143],"code-switching":[9,52,68,141],"recognition":[10],"task":[11],"thanks":[12],"to":[13,42,84,94,102,121],"its":[14],"inherent":[15],"property":[16],"that":[17,63],"present":[18],"output":[19],"token":[20],"being":[21],"independent":[22],"of":[23,46,89,131],"historical":[24],"ones.":[25],"However,":[26],"it":[27],"still":[28],"under-performs":[29],"the":[30,44,86,90,104,129,132,149,153,163],"state-of-the-art":[31],"autoregressive":[32],"frameworks.":[34],"In":[35],"this":[36],"paper,":[37],"we":[38,58,77,117],"propose":[39],"various":[40],"approaches":[41,120],"boosting":[43],"performance":[45,160],"a":[47,96,108,115,138],"CTC-mask-based":[48],"non-autoregressive":[49],"Transformer":[50],"under":[51],"scenario.":[54],"To":[55,112],"begin":[56],"with,":[57],"attempt":[59],"diversified":[60,97],"masking":[61],"method":[62,157],"are":[64],"closely":[65],"related":[66],"with":[67,148],"point,":[69],"yielding":[70,122],"an":[71],"improved":[72],"baseline":[73],"model.":[74,87],"More":[75],"importantly,":[76],"employ":[78],"Minimum":[79],"Word":[80],"Error":[81],"(MWE)":[82],"criterion":[83],"train":[85],"One":[88],"challenges":[91],"is":[92],"how":[93],"generate":[95],"hypothetical":[98,125],"space,":[99],"so":[100],"as":[101],"obtain":[103],"average":[105],"loss":[106],"given":[109],"ground":[110],"truth.":[111],"address":[113],"such":[114],"challenge,":[116],"explore":[118],"different":[119],"desired":[123],"N-best-based":[124],"space.":[126],"We":[127],"demonstrate":[128],"efficacy":[130],"proposed":[133,154],"methods":[134],"on":[135,162],"SEAME":[136],"corpus,":[137],"challenging":[139],"English-Mandarin":[140],"corpus":[142],"Southeast":[144],"Asia":[145],"community.":[146],"Compared":[147],"cross-entropy-trained":[150],"strong":[151],"baseline,":[152],"MWE":[155],"training":[156],"achieves":[158],"consistent":[159],"improvement":[161],"test":[164],"sets.":[165]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}