{"id":"https://openalex.org/W2143072537","doi":"https://doi.org/10.1109/icassp.2002.5745033","title":"Triphone based unit selection for concatenative visual speech synthesis","display_name":"Triphone based unit selection for concatenative visual speech synthesis","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W2143072537","doi":"https://doi.org/10.1109/icassp.2002.5745033","mag":"2143072537"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5745033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745033","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"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/A5113902826","display_name":"Fu Jie Huang","orcid":"https://orcid.org/0000-0002-0985-1042"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fu Jie Huang","raw_affiliation_strings":["AT and T Laboratories Research","AT&T Lab. Res., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT and T Laboratories Research","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Lab. Res., USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012049132","display_name":"Eric Cosatto","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric Cosatto","raw_affiliation_strings":["AT and T Laboratories Research","AT&T Lab. Res., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT and T Laboratories Research","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Lab. Res., USA","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110182290","display_name":"Hans Peter Graf","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hans Peter Graf","raw_affiliation_strings":["AT and T Laboratories Research","AT&T Lab. Res., USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT and T Laboratories Research","institution_ids":["https://openalex.org/I1283103587"]},{"raw_affiliation_string":"AT&T Lab. Res., USA","institution_ids":["https://openalex.org/I1283103587"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1283103587"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"II","last_page":"2037"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9993000030517578,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.7857480049133301},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.7091434597969055},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.6656888723373413},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5875121355056763},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5324125289916992},{"id":"https://openalex.org/keywords/limiting","display_name":"Limiting","score":0.5007593631744385},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.46484795212745667},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.4508039355278015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43930497765541077},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08081263303756714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7857480049133301},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.7091434597969055},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.6656888723373413},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5875121355056763},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5324125289916992},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.5007593631744385},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.46484795212745667},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.4508039355278015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43930497765541077},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08081263303756714},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5745033","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5745033","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Conference on Acoustics Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.47999998927116394,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W88864901","https://openalex.org/W1521793179","https://openalex.org/W1554803342","https://openalex.org/W1560013842","https://openalex.org/W1572730534","https://openalex.org/W1595816827","https://openalex.org/W2150658333","https://openalex.org/W2162598851","https://openalex.org/W4255959360","https://openalex.org/W6633431331","https://openalex.org/W6821567254"],"related_works":["https://openalex.org/W4243145179","https://openalex.org/W4255875982","https://openalex.org/W4244853958","https://openalex.org/W2029404707","https://openalex.org/W4285325679","https://openalex.org/W4247719608","https://openalex.org/W4237439661","https://openalex.org/W1928239295","https://openalex.org/W4242981732","https://openalex.org/W4232927149"],"abstract_inverted_index":{"Concatenative":[0],"visual":[1],"speech":[2],"synthesis":[3,51,105],"selects":[4],"frames":[5],"from":[6],"a":[7,63,90,97],"large":[8],"recorded":[9],"video":[10],"database":[11],"of":[12,49,103],"mouth":[13],"shapes":[14,40],"to":[15,52,99],"generate":[16],"photo-realistic":[17],"talking":[18],"head":[19],"sequences.":[20],"The":[21,32],"synthesized":[22],"sequence":[23],"must":[24],"exhibit":[25],"precise":[26],"lip-sound":[27],"synchronization":[28],"and":[29,107],"smooth":[30],"articulation.":[31],"selection":[33,66],"process":[34],"for":[35],"finding":[36],"the":[37,47,50,79,82,101,104],"best":[38],"lip":[39],"has":[41],"been":[42],"computationally":[43],"expensive":[44],"[1],":[45],"limiting":[46],"speed":[48],"far":[53],"less":[54],"than":[55,87],"real":[56],"time.":[57],"In":[58],"this":[59,75,110],"paper,":[60],"we":[61],"propose":[62],"rapid":[64],"unit":[65],"approach":[67],"based":[68],"on":[69,89],"triphone":[70],"units.":[71],"Experiments":[72],"show":[73,108],"that":[74,109],"algorithm":[76],"can":[77],"make":[78],"synthesis,":[80],"excluding":[81],"rendering,":[83],"50":[84],"times":[85],"faster":[86],"real-time":[88],"standard":[91],"desktop":[92],"PC.":[93],"We":[94],"also":[95],"developed":[96],"metric":[98],"test":[100],"quality":[102],"objectively,":[106],"measurement":[111,116],"is":[112],"consistent":[113],"with":[114],"subjective":[115],"results.":[117]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
