{"id":"https://openalex.org/W4415708150","doi":"https://doi.org/10.1109/icme59968.2025.11209855","title":"Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations","display_name":"Teochew-Wild: The First In-the-wild Teochew Dataset with Orthographic Annotations","publication_year":2025,"publication_date":"2025-06-30","ids":{"openalex":"https://openalex.org/W4415708150","doi":"https://doi.org/10.1109/icme59968.2025.11209855"},"language":null,"primary_location":{"id":"doi:10.1109/icme59968.2025.11209855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","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":null,"display_name":"Linrong Pan","orcid":null},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linrong Pan","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102000320","display_name":"Chenglong Jiang","orcid":"https://orcid.org/0009-0007-3935-9482"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglong Jiang","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Gaoze Hou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210090512","display_name":"Guangzhou Experimental Station","ror":"https://ror.org/00f2c2516","country_code":"CN","type":"facility","lineage":["https://openalex.org/I107851509","https://openalex.org/I4210090512","https://openalex.org/I4210127390","https://openalex.org/I4210151987"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gaoze Hou","raw_affiliation_strings":["Guangzhou No.6 Middle School,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Guangzhou No.6 Middle School,Guangzhou,China","institution_ids":["https://openalex.org/I4210090512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101828088","display_name":"Ying Gao","orcid":"https://orcid.org/0000-0002-8925-8192"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Gao","raw_affiliation_strings":["South China University of Technology,School of Computer Science and Engineering,Guangzhou,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"South China University of Technology,School of Computer Science and Engineering,Guangzhou,China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.326200008392334,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.326200008392334,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.2485000044107437,"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":0.05719999969005585,"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/orthographic-projection","display_name":"Orthographic projection","score":0.6523000001907349},{"id":"https://openalex.org/keywords/pinyin","display_name":"Pinyin","score":0.6416000127792358},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43709999322891235},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.41600000858306885},{"id":"https://openalex.org/keywords/orthography","display_name":"Orthography","score":0.31619998812675476},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3041999936103821}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8288000226020813},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.7050999999046326},{"id":"https://openalex.org/C175694140","wikidata":"https://www.wikidata.org/wiki/Q980329","display_name":"Orthographic projection","level":2,"score":0.6523000001907349},{"id":"https://openalex.org/C2781095461","wikidata":"https://www.wikidata.org/wiki/Q42222","display_name":"Pinyin","level":3,"score":0.6416000127792358},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6331999897956848},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5584999918937683},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43709999322891235},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.41600000858306885},{"id":"https://openalex.org/C150670947","wikidata":"https://www.wikidata.org/wiki/Q43091","display_name":"Orthography","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C2474386","wikidata":"https://www.wikidata.org/wiki/Q461183","display_name":"Text corpus","level":2,"score":0.2849999964237213},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C123406163","wikidata":"https://www.wikidata.org/wiki/Q82042","display_name":"Part of speech","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icme59968.2025.11209855","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icme59968.2025.11209855","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2937197076","https://openalex.org/W2964243274","https://openalex.org/W2972359262","https://openalex.org/W3081416955","https://openalex.org/W3092424727","https://openalex.org/W3198694222","https://openalex.org/W3203407300","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4225302959","https://openalex.org/W4285144981","https://openalex.org/W4392903247","https://openalex.org/W4402111455","https://openalex.org/W4406461681","https://openalex.org/W4412945617"],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"reports":[2],"the":[3,6,12,71,78,92,95],"construction":[4],"of":[5,11,20,73],"Teochew-Wild,":[7],"a":[8],"speech":[9,23,55,64],"corpus":[10,16],"Teochew":[13,22,82],"dialect.":[14],"The":[15],"includes":[17],"18.9":[18],"hours":[19],"in-the-wild":[21],"data":[24],"from":[25],"multiple":[26],"speakers,":[27],"covering":[28],"both":[29],"formal":[30],"and":[31,37,47,52,67,94,102],"colloquial":[32],"expressions,":[33],"with":[34,84],"precise":[35],"orthographic":[36,86],"pinyin":[38],"annotations.":[39,87],"Additionally,":[40],"we":[41],"provide":[42],"supplementary":[43],"text":[44],"processing":[45],"tools":[46],"resources":[48],"to":[49],"propel":[50],"research":[51],"applications":[53],"in":[54,100],"tasks":[56],"for":[57],"this":[58,76],"low-resource":[59],"language,":[60],"such":[61],"as":[62],"automatic":[63],"recognition":[65],"(ASR)":[66],"text-to-speech":[68],"(TTS).":[69],"To":[70],"best":[72],"our":[74],"knowledge,":[75],"is":[77],"first":[79],"publicly":[80],"available":[81],"dataset":[83],"accurate":[85],"We":[88],"conduct":[89],"experiments":[90],"on":[91],"corpus,":[93],"results":[96],"validate":[97],"its":[98],"effectiveness":[99],"ASR":[101],"TTS":[103],"tasks.":[104]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-30T00:00:00"}