{"id":"https://openalex.org/W3163702140","doi":"https://doi.org/10.1109/icassp39728.2021.9414598","title":"An Investigation of Using Hybrid Modeling Units for Improving End-to-End Speech Recognition System","display_name":"An Investigation of Using Hybrid Modeling Units for Improving End-to-End Speech Recognition System","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3163702140","doi":"https://doi.org/10.1109/icassp39728.2021.9414598","mag":"3163702140"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5040858443","display_name":"Shunfei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Shunfei Chen","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030369257","display_name":"Xinhui Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinhui Hu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053726259","display_name":"Sheng Li","orcid":"https://orcid.org/0000-0001-7636-3797"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sheng Li","raw_affiliation_strings":["National Institute of Information and Communications Technology (NICT),Kyoto,Japan","National Institute of Information and Communications Technology (NICT), Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT),Kyoto,Japan","institution_ids":["https://openalex.org/I90023481"]},{"raw_affiliation_string":"National Institute of Information and Communications Technology (NICT), Kyoto, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000141731","display_name":"Xinkang Xu","orcid":"https://orcid.org/0009-0003-2771-1398"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinkang Xu","raw_affiliation_strings":["Hithink RoyalFlush AI Research Institute,Zhejiang,China","Hithink RoyalFlush AI Research Institute, Zhejiang, China"],"affiliations":[{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute,Zhejiang,China","institution_ids":[]},{"raw_affiliation_string":"Hithink RoyalFlush AI Research Institute, Zhejiang, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5040858443"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8158,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.77609077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6743","last_page":"6747"},"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/T11309","display_name":"Music and Audio Processing","score":0.9962000250816345,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.991100013256073,"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":0.800571620464325},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7700538635253906},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6623346209526062},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6322205066680908},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6233231425285339},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6065014004707336},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.5530746579170227},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5319752097129822},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47935324907302856},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.457484632730484},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.43597960472106934},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.36982280015945435},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2656235098838806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08045351505279541}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.800571620464325},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7700538635253906},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6623346209526062},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6322205066680908},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6233231425285339},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6065014004707336},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.5530746579170227},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5319752097129822},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47935324907302856},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.457484632730484},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.43597960472106934},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36982280015945435},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2656235098838806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08045351505279541},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 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","score":0.5199999809265137,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1922655562","https://openalex.org/W2121879602","https://openalex.org/W2127141656","https://openalex.org/W2147768505","https://openalex.org/W2193413348","https://openalex.org/W2514969556","https://openalex.org/W2526425061","https://openalex.org/W2884254529","https://openalex.org/W2888226713","https://openalex.org/W2890197052","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2963194026","https://openalex.org/W2963242190","https://openalex.org/W2963303028","https://openalex.org/W2963850025","https://openalex.org/W2963939538","https://openalex.org/W2963970535","https://openalex.org/W2972629567","https://openalex.org/W2972686346","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015457435","https://openalex.org/W6638575559","https://openalex.org/W6640090968","https://openalex.org/W6687566353","https://openalex.org/W6752958021","https://openalex.org/W6753776127"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W2068412075","https://openalex.org/W156219719","https://openalex.org/W27484908","https://openalex.org/W2163874654","https://openalex.org/W2061937230","https://openalex.org/W2132658536","https://openalex.org/W1566315437","https://openalex.org/W2151348424"],"abstract_inverted_index":{"The":[0,117,139,169],"acoustic":[1],"modeling":[2,58,148],"unit":[3,77,95,149],"is":[4,78,96],"crucial":[5],"for":[6,13,60],"an":[7,125],"end-to-end":[8,62],"speech":[9,25,63,132],"recognition":[10,26,64,118],"system,":[11],"especially":[12],"the":[14,21,50,57,61,68,75,82,86,93,100,105,110,136,145,155],"Mandarin":[15,24,131],"language.":[16],"Until":[17],"now,":[18],"most":[19],"of":[20,33,41,49,129,158],"studies":[22],"on":[23,28,67,122,165],"focused":[27],"individual":[29],"units,":[30],"and":[31,54,124,160],"few":[32],"them":[34],"paid":[35],"attention":[36],"to":[37,80,98],"using":[38,144],"a":[39,47,174],"combination":[40],"these":[42],"units.":[43],"This":[44],"paper":[45],"uses":[46],"hybrid":[48,147],"syllable,":[51],"Chinese":[52],"character,":[53],"subword":[55],"as":[56],"units":[59,157],"system":[65],"based":[66],"CTC/attention":[69],"multi-task":[70],"learning.":[71],"In":[72,91],"this":[73],"approach,":[74],"character-subword":[76],"assigned":[79,97],"train":[81],"transformer":[83],"model":[84],"in":[85,104],"main":[87],"task":[88,107],"learning":[89],"stage.":[90],"contrast,":[92],"syllable":[94],"enhance":[99],"transformer\u2019s":[101],"shared":[102],"encoder":[103],"auxiliary":[106],"stage":[108],"with":[109],"Connectionist":[111],"Temporal":[112],"Classification":[113],"(CTC)":[114],"loss":[115],"function.":[116],"experiments":[119],"were":[120],"conducted":[121],"AISHELL-1":[123],"open":[126],"data":[127],"set":[128],"1200-hour":[130,167],"corpus":[133],"collected":[134],"from":[135],"OpenSLR,":[137],"respectively.":[138],"experimental":[140],"results":[141],"demonstrated":[142],"that":[143],"syllable-char-subword":[146],"can":[150],"achieve":[151],"better":[152],"performances":[153],"than":[154],"conventional":[156],"char-subword,":[159],"6.6%":[161],"relative":[162],"CER":[163],"reduction":[164],"our":[166],"data.":[168],"substitution":[170],"error":[171],"also":[172],"achieves":[173],"considerable":[175],"reduction.":[176]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}