{"id":"https://openalex.org/W2105537028","doi":"https://doi.org/10.1109/icassp.2004.1326070","title":"A real-time Cantonese text-to-audiovisual speech synthesizer","display_name":"A real-time Cantonese text-to-audiovisual speech synthesizer","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2105537028","doi":"https://doi.org/10.1109/icassp.2004.1326070","mag":"2105537028"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","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/A5074787625","display_name":"Jianqing Wang","orcid":"https://orcid.org/0000-0001-8794-8678"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jian-Qing Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, Virtual Reality, Visualization and Imaging Research Centre","Virtual Reality, Visualization and Imaging Research Centre, Department of Computer Science and Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Virtual Reality, Visualization and Imaging Research Centre","institution_ids":[]},{"raw_affiliation_string":"Virtual Reality, Visualization and Imaging Research Centre, Department of Computer Science and Engineering, Chinese University of Hong Kong, New Territories, 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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"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, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032708386","display_name":"Pheng\u2010Ann Heng","orcid":"https://orcid.org/0000-0003-3055-5034"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pheng-Ann Pheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102225156","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":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"H.M. Meng","raw_affiliation_strings":["Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5017857966","display_name":"Tien\u2010Tsin Wong","orcid":"https://orcid.org/0000-0002-7792-9307"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tien-Tsin Wong","raw_affiliation_strings":["Department of Computer Science and Engineering, Virtual Reality, Visualization and Imaging Research Centre","Virtual Reality, Visualization and Imaging Research Centre, Department of Computer Science and Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Virtual Reality, Visualization and Imaging Research Centre","institution_ids":[]},{"raw_affiliation_string":"Virtual Reality, Visualization and Imaging Research Centre, Department of Computer Science and Engineering, Chinese University of Hong Kong, New Territories, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"653"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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/T11448","display_name":"Face recognition and analysis","score":0.9988999962806702,"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"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.8424667119979858},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7977555394172668},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7940417528152466},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6720036268234253},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.6598817706108093},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.4820495545864105},{"id":"https://openalex.org/keywords/syllable","display_name":"Syllable","score":0.446706622838974},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42926138639450073},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3376336097717285},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.16927936673164368}],"concepts":[{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.8424667119979858},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7977555394172668},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7940417528152466},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6720036268234253},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.6598817706108093},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.4820495545864105},{"id":"https://openalex.org/C109089402","wikidata":"https://www.wikidata.org/wiki/Q8188","display_name":"Syllable","level":2,"score":0.446706622838974},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42926138639450073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3376336097717285},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.16927936673164368},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326070","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326070","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.49000000953674316,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320337350","display_name":"National Eye Institute","ror":"https://ror.org/03wkg3b53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W124159830","https://openalex.org/W1482312584","https://openalex.org/W1521793179","https://openalex.org/W1843294844","https://openalex.org/W2072578292","https://openalex.org/W2099257899","https://openalex.org/W2198657171","https://openalex.org/W2339343773","https://openalex.org/W2407385273","https://openalex.org/W4230277160","https://openalex.org/W6605053472","https://openalex.org/W6668622107","https://openalex.org/W6713834979"],"related_works":["https://openalex.org/W1974357398","https://openalex.org/W2053099149","https://openalex.org/W1559261064","https://openalex.org/W2299511660","https://openalex.org/W2124254345","https://openalex.org/W2164147372","https://openalex.org/W2105537028","https://openalex.org/W2550171623","https://openalex.org/W4253660971","https://openalex.org/W1480529103"],"abstract_inverted_index":{"This":[0,44],"paper":[1,45],"describes":[2,46],"the":[3,47,61,76,116,120],"design":[4,135],"and":[5,56,70,109,136],"development":[6],"of":[7,49,119,138],"a":[8,24,34,111,139],"Cantonese":[9,30,36],"TTVS":[10,31,140],"synthesizer,":[11],"which":[12],"can":[13,142],"generate":[14],"highly":[15],"natural":[16],"synthetic":[17],"speech":[18],"that":[19,58,80,114,133],"is":[20],"precisely":[21],"time-synchronized":[22],"with":[23,94],"real-time":[25,144],"3D":[26,103],"face":[27,97,104,122],"rendering.":[28],"Our":[29],"synthesizer":[32,141],"utilizes":[33],"homegrown":[35],"syllable-based":[37],"concatenative":[38],"text-to-speech":[39],"system":[40],"named":[41],"CU":[42,50],"VOCAL.":[43],"extension":[48],"VOCAL":[51],"to":[52,60,75,82,101,124],"output":[53,62],"syllable":[54],"labels":[55],"durations":[57],"correspond":[59,81],"acoustic":[63],"wave":[64],"file.":[65],"The":[66],"syllables":[67],"are":[68,73],"decomposed":[69],"their":[71],"initials/finals":[72],"mapped":[74],"nearest":[77],"IPA":[78],"symbols":[79],"static":[83,90,121],"viseme":[84,91],"models.":[85,98,130],"We":[86,131],"have":[87,107],"authored":[88],"sixteen":[89],"models":[92,123],"together":[93],"two":[95],"emotion-based":[96],"In":[99],"order":[100],"achieve":[102,143],"rendering,":[105],"we":[106],"designed":[108],"implemented":[110],"blending":[112],"technique":[113],"computes":[115],"linear":[117],"combinations":[118],"effect":[125],"smooth":[126],"transitions":[127],"in":[128,146],"between":[129],"demonstrate":[132],"this":[134],"implementation":[137],"performance":[145],"generation.":[147]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}