{"id":"https://openalex.org/W3117101778","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295005","title":"Using Taigi Dramas with Mandarin Chinese Subtitles to Improve Taigi Speech Recognition","display_name":"Using Taigi Dramas with Mandarin Chinese Subtitles to Improve Taigi Speech Recognition","publication_year":2020,"publication_date":"2020-11-05","ids":{"openalex":"https://openalex.org/W3117101778","doi":"https://doi.org/10.1109/o-cocosda50338.2020.9295005","mag":"3117101778"},"language":"en","primary_location":{"id":"doi:10.1109/o-cocosda50338.2020.9295005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","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":"https://openalex.org/A5051612838","display_name":"Pin\u2010Yuan Chen","orcid":"https://orcid.org/0000-0003-3324-0695"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Pin-Yuan Chen","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024882790","display_name":"Chia-Hua Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chia-Hua Wu","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048338308","display_name":"Hung-Shin Lee","orcid":"https://orcid.org/0000-0001-7044-9434"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-Shin Lee","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087035339","display_name":"Shao-Kang Tsao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shao-Kang Tsao","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112454407","display_name":"Ming\u2010Tat Ko","orcid":null},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Ming-Tat Ko","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210098366"],"apc_list":null,"apc_paid":null,"fwci":0.23,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52891967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"12","issue":null,"first_page":"71","last_page":"76"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9921000003814697,"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":0.9912999868392944,"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":0.897484540939331},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.832470178604126},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7387496829032898},{"id":"https://openalex.org/keywords/subtitle","display_name":"Subtitle","score":0.6114218235015869},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5137215852737427},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4631452262401581},{"id":"https://openalex.org/keywords/drama","display_name":"Drama","score":0.43868327140808105},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.43782302737236023},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4091108441352844},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.20422795414924622}],"concepts":[{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.897484540939331},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.832470178604126},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7387496829032898},{"id":"https://openalex.org/C2780364048","wikidata":"https://www.wikidata.org/wiki/Q204028","display_name":"Subtitle","level":2,"score":0.6114218235015869},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5137215852737427},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4631452262401581},{"id":"https://openalex.org/C523419034","wikidata":"https://www.wikidata.org/wiki/Q25372","display_name":"Drama","level":2,"score":0.43868327140808105},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.43782302737236023},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4091108441352844},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.20422795414924622},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/o-cocosda50338.2020.9295005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/o-cocosda50338.2020.9295005","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 23rd Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W94103259","https://openalex.org/W313768120","https://openalex.org/W318751970","https://openalex.org/W1645339924","https://openalex.org/W1950350537","https://openalex.org/W1995002055","https://openalex.org/W2008308193","https://openalex.org/W2134541711","https://openalex.org/W2134817403","https://openalex.org/W2139820289","https://openalex.org/W2148367456","https://openalex.org/W2150769028","https://openalex.org/W2167733672","https://openalex.org/W2514741789","https://openalex.org/W2736553904","https://openalex.org/W2785866355","https://openalex.org/W2936774411","https://openalex.org/W4285719527","https://openalex.org/W6603815097","https://openalex.org/W6610933761","https://openalex.org/W6611193399","https://openalex.org/W6636792408","https://openalex.org/W6640862880","https://openalex.org/W6679989464","https://openalex.org/W6680125536","https://openalex.org/W6682164309","https://openalex.org/W6684782818","https://openalex.org/W6747888962"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2944691285"],"abstract_inverted_index":{"An":[0],"obvious":[1],"problem":[2],"with":[3,30,95],"automatic":[4],"speech":[5,28],"recognition":[6],"(ASR)":[7],"for":[8,33,47,85,112],"Taigi":[9,60,75,92,117,126,139],"is":[10,17,39,52,61,121],"that":[11,150],"the":[12,35,72,109,136,145],"amount":[13,90],"of":[14,74,91,116],"training":[15,34,51,110,160],"data":[16,29,45,111,161],"far":[18],"from":[19],"enough":[20],"to":[21,57,107,122,129,144],"build":[22],"a":[23,62,66,88,105,131],"practical":[24],"ASR":[25,127,152],"system.":[26],"Collecting":[27],"reliable":[31],"transcripts":[32],"acoustic":[36],"model":[37,49],"(AM)":[38],"feasible":[40],"but":[41],"expensive.":[42],"Moreover,":[43],"text":[44],"used":[46,68],"language":[48],"(LM)":[50],"extremely":[53],"scarce":[54],"and":[55,114],"difficult":[56],"collect":[58],"because":[59],"spoken":[63],"language,":[64],"not":[65],"commonly":[67],"written":[69],"language.":[70],"Interestingly,":[71],"subtitles":[73,98],"drama":[76,93],"in":[77,82],"Taiwan":[78],"have":[79],"long":[80],"been":[81],"Chinese":[83,97,133],"characters":[84],"Mandarin.":[86],"Since":[87],"large":[89],"episodes":[94],"Mandarin":[96,132],"are":[99],"available":[100],"on":[101],"YouTube,":[102],"we":[103],"propose":[104],"method":[106],"augment":[108],"AM":[113],"LM":[115],"ASR.":[118],"The":[119],"idea":[120],"use":[123],"an":[124],"initial":[125],"system":[128,153],"convert":[130],"subtitle":[134],"into":[135],"most":[137],"likely":[138],"word":[140],"sequence":[141],"by":[142,158],"referring":[143],"speech.":[146],"Experimental":[147],"results":[148],"show":[149],"our":[151],"can":[154],"be":[155],"remarkably":[156],"improved":[157],"such":[159],"augmentation.":[162]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}