{"id":"https://openalex.org/W3093090459","doi":"https://doi.org/10.1145/3394171.3414444","title":"Visual-speech Synthesis of Exaggerated Corrective Feedback","display_name":"Visual-speech Synthesis of Exaggerated Corrective Feedback","publication_year":2020,"publication_date":"2020-10-12","ids":{"openalex":"https://openalex.org/W3093090459","doi":"https://doi.org/10.1145/3394171.3414444","mag":"3093090459"},"language":"en","primary_location":{"id":"doi:10.1145/3394171.3414444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","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/A5025685539","display_name":"Yaohua Bu","orcid":"https://orcid.org/0009-0005-3024-0704"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaohua Bu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100359307","display_name":"Weijun Li","orcid":"https://orcid.org/0000-0001-6068-5185"},"institutions":[{"id":"https://openalex.org/I184983240","display_name":"Northeast Normal University","ror":"https://ror.org/02rkvz144","country_code":"CN","type":"education","lineage":["https://openalex.org/I184983240"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijun Li","raw_affiliation_strings":["Northeast Normal University, Changchun, China"],"affiliations":[{"raw_affiliation_string":"Northeast Normal University, Changchun, China","institution_ids":["https://openalex.org/I184983240"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069632856","display_name":"Tianyi Ma","orcid":"https://orcid.org/0000-0002-1042-8700"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianyi Ma","raw_affiliation_strings":["Tsinghua University & Ministry of Education, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University & Ministry of Education, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101491052","display_name":"Shengqi Chen","orcid":"https://orcid.org/0000-0002-2310-5249"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengqi Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100405562","display_name":"Jia Jia","orcid":"https://orcid.org/0000-0001-8013-7290"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Jia","raw_affiliation_strings":["Tsinghua University & Ministry of Education & Beijing National Research Center for Information Science and Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University & Ministry of Education & Beijing National Research Center for Information Science and Technology, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100685189","display_name":"Kun Li","orcid":"https://orcid.org/0000-0001-6988-448X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kun Li","raw_affiliation_strings":["SpeechX Ltd., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"SpeechX Ltd., Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004560818","display_name":"Xiaobo Lu","orcid":"https://orcid.org/0009-0005-2673-8673"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaobo Lu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5025685539"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.3031,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.5475971,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"4521","last_page":"4523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.9995999932289124,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9968000054359436,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive 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/pronunciation","display_name":"Pronunciation","score":0.9096739292144775},{"id":"https://openalex.org/keywords/exaggeration","display_name":"Exaggeration","score":0.8041530847549438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7635477781295776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7150747776031494},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.6402655839920044},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6048097610473633},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.5293952822685242},{"id":"https://openalex.org/keywords/viseme","display_name":"Viseme","score":0.5094884037971497},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38149023056030273},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.322127103805542},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3084182143211365},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.17570221424102783},{"id":"https://openalex.org/keywords/speech-technology","display_name":"Speech technology","score":0.138151615858078},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10801577568054199}],"concepts":[{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.9096739292144775},{"id":"https://openalex.org/C2777003408","wikidata":"https://www.wikidata.org/wiki/Q5419252","display_name":"Exaggeration","level":2,"score":0.8041530847549438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7635477781295776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7150747776031494},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.6402655839920044},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6048097610473633},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.5293952822685242},{"id":"https://openalex.org/C33767174","wikidata":"https://www.wikidata.org/wiki/Q371190","display_name":"Viseme","level":4,"score":0.5094884037971497},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38149023056030273},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.322127103805542},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3084182143211365},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.17570221424102783},{"id":"https://openalex.org/C504749915","wikidata":"https://www.wikidata.org/wiki/Q9010971","display_name":"Speech technology","level":3,"score":0.138151615858078},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10801577568054199},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3394171.3414444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3394171.3414444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 28th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.7799999713897705}],"awards":[{"id":"https://openalex.org/G7009243909","display_name":null,"funder_award_id":"61521002","funder_id":"https://openalex.org/F4320315254","funder_display_name":"Innovative Research Group Project of the National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320315254","display_name":"Innovative Research Group Project of the National Natural Science Foundation of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W176276367","https://openalex.org/W598767079","https://openalex.org/W1481055560","https://openalex.org/W1592822300","https://openalex.org/W1975163393","https://openalex.org/W1978717898","https://openalex.org/W1994657794","https://openalex.org/W1997485640","https://openalex.org/W2003919115","https://openalex.org/W2022399114","https://openalex.org/W2067679396","https://openalex.org/W2068447135","https://openalex.org/W2095072163","https://openalex.org/W2152208325","https://openalex.org/W2529309347","https://openalex.org/W2552635739","https://openalex.org/W2579478650","https://openalex.org/W2765636281","https://openalex.org/W2769810959","https://openalex.org/W2954234533","https://openalex.org/W2964243274","https://openalex.org/W6601897980"],"related_works":["https://openalex.org/W3081908777","https://openalex.org/W2910051094","https://openalex.org/W789364040","https://openalex.org/W2365101699","https://openalex.org/W2153381665","https://openalex.org/W2372549685","https://openalex.org/W3085218227","https://openalex.org/W4212815228","https://openalex.org/W1852407300","https://openalex.org/W2777626350"],"abstract_inverted_index":{"To":[0],"provide":[1],"more":[2],"discriminative":[3],"feedback":[4,23,73],"for":[5,20],"the":[6,45,60,65],"second":[7],"language":[8],"(L2)":[9],"learners":[10,79],"to":[11],"better":[12],"identify":[13],"their":[14],"mispronunciation,":[15],"we":[16],"propose":[17],"a":[18],"method":[19],"exaggerated":[21,72],"visual-speech":[22],"in":[24],"computer-assisted":[25],"pronunciation":[26,81,84],"training":[27],"(CAPT).":[28],"The":[29],"speech":[30,37],"exaggeration":[31,47],"is":[32,48],"realized":[33],"by":[34,50],"an":[35],"emphatic":[36],"generation":[38],"neural":[39],"network":[40],"based":[41],"on":[42,77],"Tacotron,":[43],"while":[44],"visual":[46],"accomplished":[49],"ADC":[51],"Viseme":[52],"Blending,":[53],"namely":[54],"increasing":[55],"Amplitude":[56],"of":[57],"movement,":[58],"extending":[59],"phone's":[61],"Duration":[62],"and":[63,83],"enhancing":[64],"color":[66],"Contrast.":[67],"User":[68],"studies":[69],"show":[70],"that":[71],"outperforms":[74],"non-exaggerated":[75],"version":[76],"helping":[78],"with":[80],"identification":[82],"improvement.":[85]},"counts_by_year":[{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}