{"id":"https://openalex.org/W7151837208","doi":"https://doi.org/10.1109/access.2026.3681804","title":"Toward Unified Chinese Multi-Dialectal Speech Recognition via Pinyin Intermediate Representation","display_name":"Toward Unified Chinese Multi-Dialectal Speech Recognition via Pinyin Intermediate Representation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7151837208","doi":"https://doi.org/10.1109/access.2026.3681804"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3681804","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3681804","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3681804","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Junjie Cheng","orcid":"https://orcid.org/0009-0006-5462-5497"},"institutions":[{"id":"https://openalex.org/I134687103","display_name":"Nanjing Tech University","ror":"https://ror.org/03sd35x91","country_code":"CN","type":"education","lineage":["https://openalex.org/I134687103"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junjie Cheng","raw_affiliation_strings":["Nanjing Tech University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0006-5462-5497","affiliations":[{"raw_affiliation_string":"Nanjing Tech University, Nanjing, China","institution_ids":["https://openalex.org/I134687103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5133206207","display_name":"Xiaorong Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaorong Wu","raw_affiliation_strings":["Nanhang Jincheng College, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanhang Jincheng College, Nanjing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39362348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.6485000252723694,"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":0.6485000252723694,"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":0.05770000070333481,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.04479999840259552,"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/pinyin","display_name":"Pinyin","score":0.9070000052452087},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5789999961853027},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3736000061035156},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.34200000762939453},{"id":"https://openalex.org/keywords/standard-chinese","display_name":"Standard Chinese","score":0.3407000005245209},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.2953999936580658}],"concepts":[{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.9070000052452087},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8421000242233276},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7142999768257141},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5789999961853027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5133000016212463},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48010000586509705},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C2776618157","wikidata":"https://www.wikidata.org/wiki/Q727694","display_name":"Standard Chinese","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2833999991416931},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.25619998574256897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3681804","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3681804","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:9482edd1ec474850bc4d7e692840a9bd","is_oa":true,"landing_page_url":"https://doaj.org/article/9482edd1ec474850bc4d7e692840a9bd","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 55194-55208 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3681804","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3681804","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multi-dialect":[0],"speech":[1,56,80,295],"recognition":[2,57,296],"is":[3],"essential":[4],"for":[5,224,299],"the":[6,14,31,68,100,104,144,172,222,235,240,257,268,279],"widespread":[7],"adoption":[8],"of":[9,16,102,117,125,139,185,199,206,267,281],"intelligent":[10],"interactive":[11],"systems":[12],"and":[13,27,30,83,112,154,227,292],"preservation":[15],"dialectal":[17],"language":[18,28,89,127],"resources.":[19],"However,":[20],"existing":[21],"approaches":[22],"often":[23],"tightly":[24],"couple":[25],"acoustic":[26,77,242],"modeling,":[29],"prevailing":[32],"one-dialect-one-model":[33],"paradigm":[34],"results":[35,169],"in":[36,121,143,152,231],"parameter":[37],"redundancy":[38],"while":[39,98],"failing":[40],"to":[41,81,106],"exploit":[42],"shared":[43,131],"characteristics":[44],"across":[45,157,187,276],"dialects.":[46],"In":[47],"this":[48,118],"paper,":[49],"we":[50],"propose":[51],"an":[52,178,202],"exploratory":[53],"unified":[54,123,155,291],"cross-dialect":[55,76,140],"framework":[58,105,119],"based":[59],"on":[60,95,164,256],"a":[61,88,130,136,165,193],"tonal":[62],"Pinyin":[63,132,145,246,249,269],"intermediate":[64,133,270],"representation,":[65],"which":[66],"decouples":[67],"original":[69],"speech-to-Chinese":[70],"character":[71,85,181,196],"task":[72],"into":[73],"two":[74],"stages:":[75],"modeling":[78,124,156],"from":[79],"Pinyin,":[82],"Pinyin-to-Chinese":[84],"decoding":[86],"using":[87],"model.":[90],"This":[91],"study":[92],"focuses":[93],"primarily":[94],"Mandarin":[96,209,238,300],"dialects":[97,158,210,216,277],"exploring":[99],"feasibility":[101],"extending":[103],"more":[107],"distant,":[108],"low-resource":[109],"varieties":[110],"(Cantonese":[111],"Shanghainese).":[113],"The":[114,148],"core":[115],"contribution":[116,150],"lies":[120,151],"enabling":[122],"eleven":[126],"variants":[128],"through":[129],"layer,":[134],"allowing":[135],"systematic":[137,273],"investigation":[138],"feature":[141],"sharing":[142],"representation":[146,271],"space.":[147],"primary":[149],"efficiency":[153],"rather":[159],"than":[160],"achieving":[161,201],"state-of-the-art":[162,253],"performance":[163],"single":[166],"dialect.":[167],"Experimental":[168],"show":[170],"that":[171],"proposed":[173],"Pinyin-based":[174],"two-stage":[175],"system":[176],"achieves":[177],"average":[179,203],"Chinese":[180,195],"error":[182],"rate":[183],"(CER)":[184],"20.96%":[186],"all":[188],"11":[189],"dialects,":[190],"compared":[191],"with":[192],"direct":[194],"baseline":[197],"CER":[198,247],"22.97%,":[200],"relative":[204],"improvement":[205],"11.03%.":[207],"While":[208],"achieve":[211],"practically":[212],"usable":[213],"performance,":[214],"non-Mandarin":[215],"remain":[217],"at":[218,278],"preliminary":[219],"levels,":[220],"underscoring":[221],"need":[223],"dialect-specific":[225],"adaptations":[226],"larger":[228],"training":[229],"corpora":[230],"future":[232],"work.":[233],"On":[234],"AISHELL-1":[236,259],"standard":[237],"dataset,":[239],"first-stage":[241],"model":[243],"attains":[244],"1.57%":[245],"(3.42%":[248],"WER),":[250],"surpassing":[251],"previous":[252],"methods":[254],"trained":[255],"same":[258],"dataset":[260],"under":[261],"comparable":[262],"data":[263],"conditions.":[264],"Furthermore,":[265],"analysis":[266],"reveals":[272],"phonetic":[274],"correspondences":[275],"level":[280],"fundamental":[282],"pronunciation":[283],"units.":[284],"These":[285],"findings":[286],"provide":[287],"empirical":[288],"evidence":[289],"supporting":[290],"generalizable":[293],"multi-dialect":[294],"architectures,":[297],"particularly":[298],"dialect":[301],"groups.":[302]},"counts_by_year":[],"updated_date":"2026-04-09T06:13:59.934233","created_date":"2026-04-09T00:00:00"}
