{"id":"https://openalex.org/W1972362276","doi":"https://doi.org/10.1109/coginfocom.2013.6719170","title":"Development of text-to-audiovisual speech synthesis to support interactive language learning on a mobile device","display_name":"Development of text-to-audiovisual speech synthesis to support interactive language learning on a mobile device","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1972362276","doi":"https://doi.org/10.1109/coginfocom.2013.6719170","mag":"1972362276"},"language":"en","primary_location":{"id":"doi:10.1109/coginfocom.2013.6719170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2013.6719170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 4th International Conference on Cognitive Infocommunications (CogInfoCom)","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/A5078785570","display_name":"Wai-Kim Leung","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wai-Kim Leung","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045126674","display_name":"Ka-Wa Yuen","orcid":null},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ka-Wa Yuen","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102891041","display_name":"Ka Ho Wong","orcid":"https://orcid.org/0000-0002-4818-1467"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ka-Ho Wong","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China"],"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong SAR, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Dept. of Syst. Eng. & Eng. Manage., Chinese Univ. of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078785570"],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.9647,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.73433266,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"583","last_page":"588"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9951000213623047,"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/T11439","display_name":"Video Analysis and Summarization","score":0.9901999831199646,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8761578798294067},{"id":"https://openalex.org/keywords/scalable-vector-graphics","display_name":"Scalable Vector Graphics","score":0.6583625674247742},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.6348533034324646},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6158496141433716},{"id":"https://openalex.org/keywords/interactivity","display_name":"Interactivity","score":0.6143917441368103},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.5683147311210632},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.5569392442703247},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.5262550115585327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5087142586708069},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.4399445056915283},{"id":"https://openalex.org/keywords/closed-captioning","display_name":"Closed captioning","score":0.42298710346221924},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.3865675926208496},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2366430163383484},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.17314574122428894},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.1377021074295044},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.1309724748134613}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8761578798294067},{"id":"https://openalex.org/C202629362","wikidata":"https://www.wikidata.org/wiki/Q2078","display_name":"Scalable Vector Graphics","level":2,"score":0.6583625674247742},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.6348533034324646},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6158496141433716},{"id":"https://openalex.org/C144430266","wikidata":"https://www.wikidata.org/wiki/Q839721","display_name":"Interactivity","level":2,"score":0.6143917441368103},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.5683147311210632},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.5569392442703247},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.5262550115585327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5087142586708069},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.4399445056915283},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.42298710346221924},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.3865675926208496},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2366430163383484},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.17314574122428894},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.1377021074295044},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1309724748134613},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/coginfocom.2013.6719170","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coginfocom.2013.6719170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 4th International Conference on Cognitive Infocommunications (CogInfoCom)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.642.1572","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.642.1572","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www1.se.cuhk.edu.hk/~hccl/publications/pub/2013_Development of Text-to-Audiovisual Speech Synthesis to Support Interactive Language Learning on a Mobile Device.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.7799999713897705,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320326427","display_name":"Innovation and Technology Fund","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W657830927","https://openalex.org/W1978717898","https://openalex.org/W1984080009","https://openalex.org/W2094760346","https://openalex.org/W2149954081","https://openalex.org/W2152208325","https://openalex.org/W4409091606"],"related_works":["https://openalex.org/W2401811665","https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W1559261064","https://openalex.org/W2124254345","https://openalex.org/W4397292310","https://openalex.org/W2500421879","https://openalex.org/W2184371793","https://openalex.org/W2186688931","https://openalex.org/W2105537028"],"abstract_inverted_index":{"We":[0,67],"have":[1,68],"developed":[2,70],"distributed":[3],"text-to-audiovisual-speech":[4],"synthesizer":[5],"(TTAVS)":[6],"to":[7,22,52,62,114,135],"support":[8],"interactivity":[9],"in":[10,42,88,122,141],"computer-aided":[11],"pronunciation":[12],"training":[13],"(CAPT)":[14],"on":[15,28,108],"a":[16,71,118],"mobile":[17],"platform.":[18],"The":[19],"TTAVS":[20,72],"serves":[21],"generate":[23],"audiovisual":[24],"corrective":[25],"feedback":[26],"based":[27],"detected":[29],"mispronunciations":[30],"from":[31,132],"the":[32,53,56,64,78,109,115,126,133,136,149,152],"second":[33],"language":[34],"learner's":[35],"speech.":[36,66],"Our":[37],"approach":[38,100],"encodes":[39],"key":[40],"visemes":[41],"SVG":[43],"format":[44],"that":[45,75,92,101,129],"are":[46,130],"compressed":[47],"by":[48],"GZIP":[49],"and":[50,80],"transmitted":[51,131],"client,":[54,116,137],"where":[55],"browser":[57],"can":[58,76],"perform":[59],"real-time":[60],"morphing":[61],"render":[63],"visual":[65,81],"also":[69],"animation":[73],"player":[74],"play":[77],"audio":[79],"speech":[82],"synchronously":[83],"while":[84],"enabling":[85],"user":[86],"controls":[87],"play/pause/resume.":[89],"Evaluation":[90],"shows":[91],"this":[93],"newly":[94],"proposed":[95],"approach,":[96],"vis-\u00e0-vis":[97],"our":[98],"original":[99],"involves":[102],"generation":[103],"of":[104,125,139,151],"an":[105],"Ogg":[106],"video":[107],"server-side":[110],"which":[111],"is":[112],"streamed":[113],"achieves":[117],"significant":[119],"reduction":[120,138],"(66%)":[121],"average":[123],"size":[124],"output":[127],"files":[128],"server":[134],"(83%)":[140],"client":[142],"waiting":[143],"times,":[144],"as":[145,147],"well":[146],"preserve":[148],"quality":[150],"image.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}