{"id":"https://openalex.org/W2114570173","doi":"https://doi.org/10.1109/icassp.2011.5947374","title":"Synthesizing visual speech trajectory with minimum generation error","display_name":"Synthesizing visual speech trajectory with minimum generation error","publication_year":2011,"publication_date":"2011-05-01","ids":{"openalex":"https://openalex.org/W2114570173","doi":"https://doi.org/10.1109/icassp.2011.5947374","mag":"2114570173"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2011.5947374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100436501","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0002-2517-2728"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lijuan Wang","raw_affiliation_strings":["Microsoft Research Asia, Microsoft Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039492028","display_name":"Yi-Jian Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi-Jian Wu","raw_affiliation_strings":["Microsoft Research Asia, Microsoft Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110376025","display_name":"Xiaodan Zhuang","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]},{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiaodan Zhuang","raw_affiliation_strings":["Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","Microsoft Research Asia, Microsoft Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beckman Institute, ECE Department, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Microsoft Research Asia, Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065394791","display_name":"Frank K. Soong","orcid":"https://orcid.org/0000-0002-9088-3577"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Frank K. Soong","raw_affiliation_strings":["Microsoft Research Asia, Microsoft Corporation, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Asia, Microsoft Corporation, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8088,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.91344275,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"3","issue":null,"first_page":"4580","last_page":"4583"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9979000091552734,"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":0.9965000152587891,"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":0.7828656435012817},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6366075277328491},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6241872906684875},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5961927771568298},{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.5236589312553406},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4814395308494568},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.45948705077171326},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.4429852068424225},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.43563610315322876},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.42172881960868835},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3912167251110077},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3439466059207916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14240533113479614},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08354648947715759}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7828656435012817},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6366075277328491},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6241872906684875},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5961927771568298},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5236589312553406},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4814395308494568},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.45948705077171326},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.4429852068424225},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.43563610315322876},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.42172881960868835},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3912167251110077},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3439466059207916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14240533113479614},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08354648947715759},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2011.5947374","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2011.5947374","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W34110307","https://openalex.org/W71477782","https://openalex.org/W1552213476","https://openalex.org/W2070726616","https://openalex.org/W2106632010","https://openalex.org/W2111194146","https://openalex.org/W2120605154","https://openalex.org/W2143132120","https://openalex.org/W2147885303","https://openalex.org/W2162598851","https://openalex.org/W6602918789","https://openalex.org/W6676358011","https://openalex.org/W6681253763"],"related_works":["https://openalex.org/W2029561777","https://openalex.org/W1554502231","https://openalex.org/W172797710","https://openalex.org/W2945105049","https://openalex.org/W4387098302","https://openalex.org/W2626699140","https://openalex.org/W3165080709","https://openalex.org/W2948317131","https://openalex.org/W4288365855","https://openalex.org/W2111961547"],"abstract_inverted_index":{"In":[0,77],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,54,64],"minimum":[6],"generation":[7],"error":[8,96],"(MGE)":[9],"training":[10,34],"method":[11,56,88],"to":[12,17,57,68],"refine":[13],"the":[14,25,31,37,45,59,70,74,82,85,93,108,115],"audio-visual":[15,46,111],"HMM":[16,47],"improve":[18],"visual":[19,41],"speech":[20,42],"trajectory":[21],"synthesis.":[22],"Compared":[23],"with":[24,81],"traditional":[26],"maximum":[27],"likelihood":[28],"(ML)":[29],"estimation,":[30],"proposed":[32,86],"MGE":[33,75],"explicitly":[35],"optimizes":[36],"quality":[38],"of":[39,102],"generated":[40],"trajectory,":[43],"where":[44],"modeling":[48],"is":[49],"jointly":[50],"refined":[51],"by":[52],"using":[53],"heuristic":[55],"find":[58],"optimal":[60],"state":[61],"alignment":[62],"and":[63,100,110],"probabilistic":[65],"descent":[66],"algorithm":[67],"optimize":[69],"model":[71],"parameters":[72],"under":[73],"criterion.":[76],"objective":[78],"evaluation,":[79],"compared":[80],"ML-based":[83],"method,":[84],"MGE-based":[87],"achieves":[89],"consistent":[90],"improvement":[91],"in":[92,114],"mean":[94],"square":[95],"reduction,":[97],"correlation":[98],"increase,":[99],"recovery":[101],"global":[103],"variance.":[104],"It":[105],"also":[106],"improves":[107],"naturalness":[109],"consistency":[112],"perceptually":[113],"subjective":[116],"test.":[117]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}