{"id":"https://openalex.org/W2075977168","doi":"https://doi.org/10.1109/apsipa.2013.6694335","title":"A real-time speech driven talking avatar based on deep neural network","display_name":"A real-time speech driven talking avatar based on deep neural network","publication_year":2013,"publication_date":"2013-10-01","ids":{"openalex":"https://openalex.org/W2075977168","doi":"https://doi.org/10.1109/apsipa.2013.6694335","mag":"2075977168"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2013.6694335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","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/A5078276127","display_name":"Kai Zhao","orcid":"https://orcid.org/0000-0002-2496-0829"},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":true,"raw_author_name":"Kai Zhao","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Tsinghua-CUHK Joint Res. Center for Media Sci., Tsinghua Univ., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Res. Center for Media Sci., Tsinghua Univ., Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102869280","display_name":"Zhiyong Wu","orcid":"https://orcid.org/0000-0001-8533-0524"},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Zhiyong Wu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Tsinghua-CUHK Joint Res. Center for Media Sci., Tsinghua Univ., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Res. Center for Media Sci., Tsinghua Univ., Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053661520","display_name":"Lianhong Cai","orcid":null},"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"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["CN","HK"],"is_corresponding":false,"raw_author_name":"Lianhong Cai","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","Tsinghua-CUHK Joint Res. Center for Media Sci., Tsinghua Univ., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Tsinghua-CUHK Joint Res. Center for Media Sci., Tsinghua Univ., Shenzhen, China","institution_ids":["https://openalex.org/I99065089","https://openalex.org/I889458895"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078276127"],"corresponding_institution_ids":["https://openalex.org/I889458895","https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":1.596,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84069345,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9900000095367432,"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/T11309","display_name":"Music and Audio Processing","score":0.9883999824523926,"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/avatar","display_name":"Avatar","score":0.8369444608688354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8028864860534668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7051987051963806},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6148669719696045},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.43023619055747986},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4261452853679657},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.42446696758270264},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3807947337627411},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.20311999320983887}],"concepts":[{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.8369444608688354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8028864860534668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7051987051963806},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6148669719696045},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.43023619055747986},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4261452853679657},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.42446696758270264},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3807947337627411},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.20311999320983887}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2013.6694335","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2013.6694335","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W20555154","https://openalex.org/W60202269","https://openalex.org/W113709255","https://openalex.org/W1482312584","https://openalex.org/W1982854652","https://openalex.org/W2105478683","https://openalex.org/W2114336453","https://openalex.org/W2116064496","https://openalex.org/W2136922672","https://openalex.org/W2231075402","https://openalex.org/W2395578248","https://openalex.org/W6600832158","https://openalex.org/W6604631218","https://openalex.org/W6711777497"],"related_works":["https://openalex.org/W2044408773","https://openalex.org/W2130717063","https://openalex.org/W4383605217","https://openalex.org/W2164147372","https://openalex.org/W2550171623","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W4253660971","https://openalex.org/W2041273198","https://openalex.org/W2131711534"],"abstract_inverted_index":{"This":[0],"paper":[1],"describes":[2],"our":[3],"initial":[4],"work":[5],"in":[6],"developing":[7],"a":[8,43],"real-time":[9],"speech":[10,27,74],"driven":[11],"talking":[12],"avatar":[13],"system":[14,23],"with":[15,38],"deep":[16,63],"neural":[17,64],"network.":[18],"The":[19,46],"input":[20,40,50],"of":[21,62],"the":[22,25,29,32,39,49,54,69,79],"is":[24,31,58],"acoustic":[26,51],"and":[28],"output":[30,55],"articulatory":[33,56],"movements":[34],"(that":[35],"are":[36],"synchronized":[37],"speech)":[41],"on":[42,68,85],"3-dimentional":[44],"avatar.":[45],"mapping":[47,82],"from":[48],"features":[52,57],"to":[53],"achieved":[59],"by":[60],"virtue":[61],"network":[65],"(DNN).":[66],"Experiments":[67],"well":[70],"known":[71],"acoustic-articulatory":[72],"English":[73],"corpus":[75],"MNGU0":[76],"demonstrate":[77],"that":[78],"proposed":[80],"audio-visual":[81],"method":[83],"based":[84],"DNN":[86],"can":[87],"achieve":[88],"good":[89],"performance.":[90]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}