{"id":"https://openalex.org/W4282837673","doi":"https://doi.org/10.1145/3543854","title":"VoiceTalk: Multimedia-IoT Applications for Mixing Mandarin, Taiwanese, and English","display_name":"VoiceTalk: Multimedia-IoT Applications for Mixing Mandarin, Taiwanese, and English","publication_year":2022,"publication_date":"2022-06-14","ids":{"openalex":"https://openalex.org/W4282837673","doi":"https://doi.org/10.1145/3543854"},"language":"en","primary_location":{"id":"doi:10.1145/3543854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543854","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543854","source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Internet Technology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3543854","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041723502","display_name":"Yi\u2010Bing Lin","orcid":"https://orcid.org/0000-0001-6841-4718"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yi-Bing Lin","raw_affiliation_strings":["College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University, China Medicine University, Department of Computer Science and Information Engineering, Asia University, College of Humanities and Sciences, Miin Wu School of Computing, National Cheng Kung University"],"affiliations":[{"raw_affiliation_string":"College of Artificial Intelligence and Green Energy, National Yang Ming Chiao Tung University, China Medicine University, Department of Computer Science and Information Engineering, Asia University, College of Humanities and Sciences, Miin Wu School of Computing, National Cheng Kung University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082271172","display_name":"Yuan\u2010Fu Liao","orcid":"https://orcid.org/0000-0003-0191-2178"},"institutions":[{"id":"https://openalex.org/I118292597","display_name":"National Taipei University of Technology","ror":"https://ror.org/00cn92c09","country_code":"TW","type":"education","lineage":["https://openalex.org/I118292597"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yuan-Fu Liao","raw_affiliation_strings":["Department of Electronic\u00a0Engineering, National Taipei University of\u00a0Technology","Department of Electronic Engineering, National Taipei University of Technology"],"affiliations":[{"raw_affiliation_string":"Department of Electronic\u00a0Engineering, National Taipei University of\u00a0Technology","institution_ids":["https://openalex.org/I118292597"]},{"raw_affiliation_string":"Department of Electronic Engineering, National Taipei University of Technology","institution_ids":["https://openalex.org/I118292597"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015529786","display_name":"Sin\u2010Horng Chen","orcid":"https://orcid.org/0000-0002-9820-2318"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Sin-Horng Chen","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering,\u00a0National Yang Ming Chiao Tung University","Dept. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering,\u00a0National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016301887","display_name":"Shaw\u2010Hwa Hwang","orcid":"https://orcid.org/0000-0003-1358-0502"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Shaw-Hwa Hwang","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering,\u00a0National Yang Ming Chiao Tung University","Dept. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering,\u00a0National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071941088","display_name":"Yih\u2010Ru Wang","orcid":"https://orcid.org/0000-0002-4483-1418"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yih-Ru Wang","raw_affiliation_strings":["Dept. of Electrical and Computer Engineering,\u00a0National Yang Ming Chiao Tung University","Dept. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University"],"affiliations":[{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering,\u00a0National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]},{"raw_affiliation_string":"Dept. of Electrical and Computer Engineering, National Yang Ming Chiao Tung University","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041723502"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4138,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.67103967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"23","issue":"2","first_page":"1","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":0.9993000030517578,"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/T11309","display_name":"Music and Audio Processing","score":0.9984999895095825,"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/computer-science","display_name":"Computer science","score":0.9128289222717285},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.6125070452690125},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6063889861106873},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.4764545261859894},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.4417310953140259},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.43499141931533813},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.41133439540863037},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2791290879249573},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.13284221291542053},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.08011952042579651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9128289222717285},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.6125070452690125},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6063889861106873},{"id":"https://openalex.org/C81860439","wikidata":"https://www.wikidata.org/wiki/Q251212","display_name":"Internet of Things","level":2,"score":0.4764545261859894},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.4417310953140259},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.43499141931533813},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.41133439540863037},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2791290879249573},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.13284221291542053},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.08011952042579651},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3543854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543854","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543854","source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Internet Technology","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3543854","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3543854","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3543854","source":{"id":"https://openalex.org/S97833917","display_name":"ACM Transactions on Internet Technology","issn_l":"1533-5399","issn":["1533-5399","1557-6051"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Internet Technology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7442899463","display_name":null,"funder_award_id":"108-2221-E-009-047, 107-2221- E-197-006-MY3, 108-2321-B-197-003, 109-2221-E-027-108","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4282837673.pdf","grobid_xml":"https://content.openalex.org/works/W4282837673.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1608166496","https://openalex.org/W1987417036","https://openalex.org/W1995562189","https://openalex.org/W2001292406","https://openalex.org/W2086402015","https://openalex.org/W2125396006","https://openalex.org/W2127141656","https://openalex.org/W2131940329","https://openalex.org/W2138536471","https://openalex.org/W2143612262","https://openalex.org/W2144651251","https://openalex.org/W2154084853","https://openalex.org/W2160815625","https://openalex.org/W2531320996","https://openalex.org/W2551524776","https://openalex.org/W2552462220","https://openalex.org/W2587282545","https://openalex.org/W2595054336","https://openalex.org/W2603415636","https://openalex.org/W2624950010","https://openalex.org/W2770439812","https://openalex.org/W2802643546","https://openalex.org/W2936994305","https://openalex.org/W2972451902","https://openalex.org/W2990318197","https://openalex.org/W3016966266","https://openalex.org/W3019166713","https://openalex.org/W3109489268","https://openalex.org/W3133366846","https://openalex.org/W3143835353","https://openalex.org/W4298208567"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W3088136942","https://openalex.org/W2949362007","https://openalex.org/W2775506363","https://openalex.org/W4290852288","https://openalex.org/W4388893791","https://openalex.org/W4283207562","https://openalex.org/W2963177403","https://openalex.org/W2330246314","https://openalex.org/W2949522393"],"abstract_inverted_index":{"The":[0],"voice-based":[1],"Internet":[2],"of":[3,10,43,166],"Multimedia":[4],"Things":[5],"(IoMT)":[6],"is":[7,29,170,175,198,218],"the":[8,59,69,80,91,103,113,125,138,163,179,188,191,195,201,207,215,268],"combination":[9],"IoT":[11,48,64,96,119,147],"interfaces":[12],"and":[13,37,54,135,159,209,236,257,266],"protocols":[14],"with":[15,68,145],"associated":[16],"voice-related":[17],"information,":[18],"which":[19,75],"enables":[20],"advanced":[21],"applications":[22,65,100],"based":[23,116],"on":[24,112,117],"human-to-device":[25],"interactions.":[26],"An":[27],"example":[28],"Automatic":[30],"Speech":[31,261],"Recognition":[32,262],"(ASR)":[33],"for":[34,45,88,154,194,275],"live":[35],"captioning":[36],"voice":[38],"translation.":[39],"Three":[40],"major":[41],"issues":[42,115],"ASR":[44,70,104,133,273],"IoMT":[46],"are":[47,66,76,98,178],"development":[49],"cost,":[50],"speech":[51,156,248],"recognition":[52,83,157,249,277],"accuracy,":[53],"execution":[55],"time":[56],"complexity.":[57],"For":[58,79,90,162],"first":[60,180,196],"issue,":[61,82,93],"most":[62],"non-voice":[63],"upgraded":[67],"feature":[71],"through":[72],"hard":[73],"coding,":[74],"error":[77],"prone.":[78],"second":[81,202],"accuracy":[84,158,169,174,250,278],"must":[85,106],"be":[86,107,142],"improved":[87],"ASR.":[89],"third":[92],"many":[94],"multimedia":[95],"services":[97],"real-time":[99],"and,":[101],"therefore,":[102],"delay":[105,193,217],"short.":[108],"This":[109],"article":[110],"elaborates":[111],"above":[114],"an":[118,183],"platform":[120],"called":[121],"VoiceTalk.":[122],"We":[123,149,177],"built":[124],"largest":[126],"Taiwanese":[127,246,276],"spoken":[128],"corpus":[129],"to":[130,181,186,221],"train":[131],"VoiceTalk":[132],"(VT-ASR)":[134],"show":[136,213],"how":[137],"VT-ASR":[139,160,192,216,242],"mechanism":[140],"can":[141],"transparently":[143],"integrated":[144],"existing":[146],"applications.":[148],"consider":[150],"two":[151],"performance":[152],"measures":[153],"VoiceTalk:":[155],"delay.":[161],"acoustic":[164],"tests":[165],"PAL-Labs,":[167],"VT-ASR's":[168],"96.47%,":[171],"while":[172],"Google's":[173],"94.28%.":[176],"develop":[182],"analytic":[184,210],"model":[185],"investigate":[187],"probability":[189],"that":[190,214],"speaker":[197,203],"complete":[199],"before":[200],"starts":[204],"talking.":[205],"From":[206],"measurements":[208],"modeling,":[211],"we":[212],"short":[219],"enough":[220],"result":[222],"in":[223,240,259,279],"a":[224],"very":[225],"good":[226],"user":[227],"experience.":[228],"Our":[229],"solution":[230],"has":[231,243],"won":[232],"several":[233],"important":[234],"government":[235],"commercial":[237,253],"TV":[238],"contracts":[239],"Taiwan.":[241],"demonstrated":[244],"better":[245],"Mandarin":[247],"than":[251],"famous":[252],"products":[254],"(including":[255],"Google":[256],"Iflytek)":[258],"Formosa":[260],"Challenge":[263],"2018":[264],"(FSR-2018)":[265],"was":[267],"best":[269],"among":[270],"all":[271],"participating":[272],"systems":[274],"FSR-2020.":[280]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-04T09:10:02.777135","created_date":"2025-10-10T00:00:00"}
