{"id":"https://openalex.org/W4388821259","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317462","title":"Hybrid Syllable and Character Representations for Mandarin ASR","display_name":"Hybrid Syllable and Character Representations for Mandarin ASR","publication_year":2023,"publication_date":"2023-10-31","ids":{"openalex":"https://openalex.org/W4388821259","doi":"https://doi.org/10.1109/apsipaasc58517.2023.10317462"},"language":"en","primary_location":{"id":"doi:10.1109/apsipaasc58517.2023.10317462","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5027555657","display_name":"Fengrun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Fengrun Zhang","raw_affiliation_strings":["TAL Education Group,Beijing,China","TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000406335","display_name":"Chengfei Li","orcid":"https://orcid.org/0000-0002-1356-7466"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chengfei Li","raw_affiliation_strings":["TAL Education Group,Beijing,China","TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084115316","display_name":"Shuhao Deng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuhao Deng","raw_affiliation_strings":["TAL Education Group,Beijing,China","TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102819501","display_name":"Yao-Ping Wang","orcid":"https://orcid.org/0000-0003-0994-6030"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yaoping Wang","raw_affiliation_strings":["TAL Education Group,Beijing,China","TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036032938","display_name":"Jinfeng Bai","orcid":"https://orcid.org/0000-0001-8940-480X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinfeng Bai","raw_affiliation_strings":["TAL Education Group,Beijing,China","TAL Education Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"TAL Education Group,Beijing,China","institution_ids":[]},{"raw_affiliation_string":"TAL Education Group, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5027555657"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15020387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"1949","last_page":"1954"},"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":0.9958000183105469,"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/T10860","display_name":"Speech and Audio Processing","score":0.9954000115394592,"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/pinyin","display_name":"Pinyin","score":0.8925728797912598},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8175672292709351},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7499929070472717},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.6999304294586182},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.64892578125},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6250197887420654},{"id":"https://openalex.org/keywords/chinese-characters","display_name":"Chinese characters","score":0.6133973598480225},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5782583951950073},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49191784858703613},{"id":"https://openalex.org/keywords/chinese-speech-synthesis","display_name":"Chinese speech synthesis","score":0.4785650074481964},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4726898968219757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4695228934288025},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35232409834861755},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.27179592847824097},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.20824119448661804},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.13811710476875305},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08570462465286255}],"concepts":[{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.8925728797912598},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8175672292709351},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7499929070472717},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.6999304294586182},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.64892578125},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6250197887420654},{"id":"https://openalex.org/C2781051154","wikidata":"https://www.wikidata.org/wiki/Q8201","display_name":"Chinese characters","level":2,"score":0.6133973598480225},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5782583951950073},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49191784858703613},{"id":"https://openalex.org/C73411735","wikidata":"https://www.wikidata.org/wiki/Q16369","display_name":"Chinese speech synthesis","level":4,"score":0.4785650074481964},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4726898968219757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4695228934288025},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35232409834861755},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.27179592847824097},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.20824119448661804},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.13811710476875305},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08570462465286255},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc58517.2023.10317462","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/apsipaasc58517.2023.10317462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6600000262260437,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W2046932483","https://openalex.org/W2127141656","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2884254529","https://openalex.org/W2884975363","https://openalex.org/W2892009249","https://openalex.org/W2936774411","https://openalex.org/W2963242190","https://openalex.org/W2972650231","https://openalex.org/W3036601975","https://openalex.org/W3097777922","https://openalex.org/W3151526698","https://openalex.org/W3162899666","https://openalex.org/W3197478142","https://openalex.org/W3197813307","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4210423654","https://openalex.org/W4212774754","https://openalex.org/W4296068993","https://openalex.org/W4319586049","https://openalex.org/W4361990931","https://openalex.org/W4385245566","https://openalex.org/W6780218876","https://openalex.org/W6838276489"],"related_works":["https://openalex.org/W4385493412","https://openalex.org/W2090669199","https://openalex.org/W3159297355","https://openalex.org/W1575804004","https://openalex.org/W2547767923","https://openalex.org/W1788792945","https://openalex.org/W3123716854","https://openalex.org/W2529685800","https://openalex.org/W1932828703","https://openalex.org/W2372811119"],"abstract_inverted_index":{"With":[0],"the":[1,26,33,42,44,53,74,82,93,101,124,133,136,171,187],"development":[2],"of":[3,35,41,47,55,76,85,135,139,178],"deep":[4],"learning,":[5],"End-to-End":[6],"(E2E)":[7],"automatic":[8],"speech":[9,31],"recognition":[10],"(ASR)":[11],"based":[12,150],"on":[13,151,202],"Connectionist":[14],"Temporal":[15],"Classification":[16],"(CTC)":[17],"and":[18,24,57,104,129,141,153,161],"attention":[19,163],"has":[20],"achieved":[21],"great":[22],"success":[23],"become":[25],"most":[27],"popular":[28],"method.":[29],"In":[30,88,108],"recognition,":[32],"selection":[34],"modeling":[36,45,119,138],"units":[37,46],"is":[38,62,183],"critical.":[39],"Most":[40],"time,":[43],"Mandarin":[48],"are":[49],"Chinese":[50,61,77,86,96,127,142,168],"characters.":[51,87],"However,":[52],"phenomenon":[54],"homophones":[56],"polyphonic":[58],"characters":[59,97,128,169],"in":[60],"very":[63],"common,":[64],"which":[65,79,155],"degrades":[66],"ASR":[67,148,189],"performance.":[68],"Pinyin":[69],"can":[70,80],"be":[71],"regarded":[72],"as":[73,116],"syllables":[75,140,152,166],"characters,":[78,143,154],"reflect":[81],"pronunciation":[83],"information":[84],"E2E":[89],"ASR,":[90],"due":[91],"to":[92,100,121,167,170],"sequence-to-sequence":[94],"form,":[95],"directly":[98],"correspond":[99],"acoustic":[102,130],"features":[103],"lack":[105],"intermediate-level":[106],"representations.":[107],"this":[109],"paper,":[110],"we":[111,144],"introduce":[112],"pinyin":[113],"with":[114,186],"tones":[115],"an":[117,162],"auxiliary":[118,180],"unit":[120],"compensate":[122],"for":[123],"mismatch":[125],"between":[126],"features.":[131],"On":[132],"basis":[134],"hybrid":[137],"propose":[145],"a":[146,157,176,194],"multi-task":[147],"model":[149],"introduces":[156],"syllable":[158,179],"CTC":[159],"decoder":[160,164],"from":[165],"joint":[172],"CTC-attention":[173],"model.":[174],"Furthermore,":[175],"method":[177,182,192],"attention-rescoring":[181],"proposed.":[184],"Compared":[185],"character-based":[188],"model,":[190],"our":[191],"achieves":[193],"relative":[195],"8.6%/9.4%":[196],"character":[197],"error":[198],"rate":[199],"(CER)":[200],"drop":[201],"Aishell-1":[203],"by":[204],"greedy-search/attention-rescoring.":[205]},"counts_by_year":[],"updated_date":"2025-12-25T23:11:45.687758","created_date":"2025-10-10T00:00:00"}