{"id":"https://openalex.org/W4319586049","doi":"https://doi.org/10.1109/iscslp57327.2022.10037884","title":"Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition","display_name":"Multi-Level Modeling Units for End-to-End Mandarin Speech Recognition","publication_year":2022,"publication_date":"2022-12-11","ids":{"openalex":"https://openalex.org/W4319586049","doi":"https://doi.org/10.1109/iscslp57327.2022.10037884"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp57327.2022.10037884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037884","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5028185223","display_name":"Yuting Yang","orcid":"https://orcid.org/0000-0003-4260-4550"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuting Yang","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001063248","display_name":"Binbin Du","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binbin Du","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100697195","display_name":"Yuke Li","orcid":"https://orcid.org/0000-0001-9204-9239"},"institutions":[{"id":"https://openalex.org/I4210091137","display_name":"NetEase (China)","ror":"https://ror.org/00fp6fj05","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210091137"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuke Li","raw_affiliation_strings":["NetEase Yidun AI Lab,Hangzhou,China","NetEase Yidun AI Lab, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NetEase Yidun AI Lab,Hangzhou,China","institution_ids":["https://openalex.org/I4210091137"]},{"raw_affiliation_string":"NetEase Yidun AI Lab, Hangzhou, China","institution_ids":["https://openalex.org/I4210091137"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210091137"],"apc_list":null,"apc_paid":null,"fwci":0.4152,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.60694408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"175","last_page":"179"},"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/T11309","display_name":"Music and Audio Processing","score":0.9926999807357788,"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/mandarin-chinese","display_name":"Mandarin Chinese","score":0.8463839292526245},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7878334522247314},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6987917423248291},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5565845966339111},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5312604308128357},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.473409503698349},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.4598676860332489},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4529118537902832},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44765177369117737},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.4460921883583069},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.41777873039245605},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37578365206718445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09689879417419434},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07798510789871216},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07624584436416626}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.8463839292526245},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878334522247314},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6987917423248291},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5565845966339111},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5312604308128357},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.473409503698349},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.4598676860332489},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4529118537902832},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44765177369117737},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.4460921883583069},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.41777873039245605},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37578365206718445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09689879417419434},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07798510789871216},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07624584436416626},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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/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},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp57327.2022.10037884","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp57327.2022.10037884","pdf_url":null,"source":{"id":"https://openalex.org/S4363607181","display_name":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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":"2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5299999713897705,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1522301498","https://openalex.org/W2046932483","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2142384583","https://openalex.org/W2327501763","https://openalex.org/W2407080277","https://openalex.org/W2766219058","https://openalex.org/W2884254529","https://openalex.org/W2884975363","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2941814890","https://openalex.org/W2962778134","https://openalex.org/W2963242190","https://openalex.org/W2963303028","https://openalex.org/W2963850025","https://openalex.org/W2963939538","https://openalex.org/W2972686346","https://openalex.org/W3015960524","https://openalex.org/W3097777922","https://openalex.org/W3144557079","https://openalex.org/W3151526698","https://openalex.org/W3162249256","https://openalex.org/W3163793923","https://openalex.org/W3197140813","https://openalex.org/W3197478142","https://openalex.org/W4200629210","https://openalex.org/W4210423654","https://openalex.org/W4226440507","https://openalex.org/W4297727296","https://openalex.org/W4385245566","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6674330103","https://openalex.org/W6752958021","https://openalex.org/W6761563299"],"related_works":["https://openalex.org/W2222951281","https://openalex.org/W2272290179","https://openalex.org/W156219719","https://openalex.org/W2068412075","https://openalex.org/W2356756483","https://openalex.org/W27484908","https://openalex.org/W2348863460","https://openalex.org/W2355692578","https://openalex.org/W2028119700","https://openalex.org/W2529685800"],"abstract_inverted_index":{"The":[0],"choice":[1],"of":[2,34,152],"modeling":[3,38,57,74,83],"units":[4,39,75],"is":[5,40],"crucial":[6],"for":[7,63],"automatic":[8],"speech":[9,44,65],"recognition":[10],"(ASR)":[11],"tasks.":[12],"In":[13,46],"mandarin":[14,64],"scenarios,":[15],"the":[16,27,32,68,77,87,112,122,132,137,157,160],"Chinese":[17,35,129],"characters":[18,36,130],"represent":[19],"meaning":[20],"but":[21],"are":[22,116],"not":[23],"directly":[24],"related":[25],"to":[26,42,93,106],"pronunciation.":[28],"Thus":[29],"only":[30],"considering":[31],"writing":[33],"as":[37,73],"insufficient":[41],"capture":[43],"features.":[45],"this":[47],"paper,":[48],"we":[49,96],"present":[50],"a":[51],"novel":[52],"method":[53,146],"involves":[54],"with":[55,81,150],"multi-level":[56,61],"units,":[58],"which":[59],"integrates":[60],"information":[62],"recognition.":[66],"Specifically,":[67],"encoder":[69,123],"block":[70,79,124],"considers":[71],"syllables":[72],"and":[76,125,154,159],"decoder":[78,108,133],"deals":[80],"character-level":[82],"units.":[84],"To":[85],"facilitate":[86],"incremental":[88],"conversion":[89],"from":[90],"syllable":[91,119],"features":[92],"character":[94],"features,":[95],"design":[97],"an":[98],"auxiliary":[99],"task":[100],"that":[101,144],"applies":[102],"cross-entropy":[103],"(CE)":[104],"loss":[105],"intermediate":[107],"layers.":[109],"During":[110],"inference,":[111],"input":[113],"feature":[114],"sequences":[115,120],"converted":[117,127],"into":[118,128],"by":[121,131],"then":[126],"block.":[134],"Experiments":[135],"on":[136],"widely":[138],"used":[139],"AISHELL-I":[140],"[1]":[141],"corpus":[142],"demonstrate":[143],"our":[145],"achieves":[147],"promising":[148],"results":[149],"CER":[151],"4.1%/4.6%":[153],"4.6%/5.2%,":[155],"using":[156],"Conformer":[158],"Transformer":[161],"backbones":[162],"respectively.":[163]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}