{"id":"https://openalex.org/W2295421726","doi":"https://doi.org/10.21437/interspeech.2014-186","title":"Speech-driven head motion synthesis using neural networks","display_name":"Speech-driven head motion synthesis using neural networks","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2295421726","doi":"https://doi.org/10.21437/interspeech.2014-186","mag":"2295421726"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","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/A5113730802","display_name":"Chuang Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chuang Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050166453","display_name":"Pengcheng Zhu","orcid":"https://orcid.org/0000-0001-9867-7041"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pengcheng Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668966","display_name":"Lei Xie","orcid":"https://orcid.org/0000-0001-8234-0823"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100296396","display_name":"Zhonghua Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhong-Hua Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2303","last_page":"2307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9994000196456909,"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/T12290","display_name":"Human Motion and Animation","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8395408391952515},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7257651686668396},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6898670196533203},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6423481106758118},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.559019923210144},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.4824441075325012},{"id":"https://openalex.org/keywords/avatar","display_name":"Avatar","score":0.4609009027481079},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4335814118385315},{"id":"https://openalex.org/keywords/perceptron","display_name":"Perceptron","score":0.43174540996551514},{"id":"https://openalex.org/keywords/animation","display_name":"Animation","score":0.4301265478134155},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.42304831743240356},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4201924800872803},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.4109610319137573},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3594992160797119},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.08546182513237}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8395408391952515},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7257651686668396},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6898670196533203},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6423481106758118},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.559019923210144},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.4824441075325012},{"id":"https://openalex.org/C2777365542","wikidata":"https://www.wikidata.org/wiki/Q83090","display_name":"Avatar","level":2,"score":0.4609009027481079},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4335814118385315},{"id":"https://openalex.org/C60908668","wikidata":"https://www.wikidata.org/wiki/Q690207","display_name":"Perceptron","level":3,"score":0.43174540996551514},{"id":"https://openalex.org/C502989409","wikidata":"https://www.wikidata.org/wiki/Q11425","display_name":"Animation","level":2,"score":0.4301265478134155},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.42304831743240356},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4201924800872803},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.4109610319137573},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3594992160797119},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.08546182513237},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2014-186","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-186","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.651.6287","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.651.6287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.nwpu-aslp.org/lxie/papers/2014Interspeech-DingZhu.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W44815768","https://openalex.org/W1483472084","https://openalex.org/W1496997718","https://openalex.org/W1498436455","https://openalex.org/W1533861849","https://openalex.org/W1778203727","https://openalex.org/W1984541135","https://openalex.org/W1999681822","https://openalex.org/W2007997442","https://openalex.org/W2017210891","https://openalex.org/W2020661758","https://openalex.org/W2054721804","https://openalex.org/W2083164975","https://openalex.org/W2100495367","https://openalex.org/W2117752179","https://openalex.org/W2118004237","https://openalex.org/W2124173482","https://openalex.org/W2124399597","https://openalex.org/W2131062138","https://openalex.org/W2132424367","https://openalex.org/W2136922672","https://openalex.org/W2150133190","https://openalex.org/W2151539117","https://openalex.org/W2157285372","https://openalex.org/W2160815625","https://openalex.org/W2168982238","https://openalex.org/W2385132364","https://openalex.org/W2395955767","https://openalex.org/W2400063444"],"related_works":["https://openalex.org/W3138471234","https://openalex.org/W4247958311","https://openalex.org/W4396832849","https://openalex.org/W2785089443","https://openalex.org/W161037869","https://openalex.org/W2904846757","https://openalex.org/W175280642","https://openalex.org/W2688184458","https://openalex.org/W4297818177","https://openalex.org/W2953037075"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,16,30,42,49],"neural":[4,45,145,148],"network":[5,46,52],"approach":[6,118],"for":[7],"speech-driven":[8,114],"head":[9,18,80,115,142],"motion":[10,81,116,143],"synthesis,":[11,144],"which":[12],"can":[13,92,107,131],"automatically":[14],"predict":[15],"speaker\u2019s":[17],"movement":[19],"from":[20,33,122],"his/her":[21],"speech.":[22],"Specifically,":[23],"we":[24,39,61,84],"realize":[25],"speech-to-head-motion":[26],"mapping":[27],"by":[28],"learning":[29],"multi-layer":[31],"perceptron":[32],"audio-visual":[34],"broadcast":[35],"news":[36],"data.":[37],"First,":[38],"show":[40],"that":[41,63,86],"generatively":[43],"pre-trained":[44],"significantly":[47],"outperforms":[48],"randomly":[50],"initialized":[51],"and":[53,73,129],"the":[54,64,95,104,120],"hidden":[55],"Markov":[56],"model":[57],"(HMM)":[58],"approach.":[59],"Second,":[60],"demonstrate":[62],"feature":[65],"combination":[66],"of":[67],"log":[68],"Mel-scale":[69],"filter-bank":[70],"(FBank),":[71],"energy":[72],"fundamental":[74],"frequency":[75],"(F0)":[76],"performs":[77],"best":[78],"in":[79,103,135],"prediction.":[82],"Third,":[83],"discover":[85],"using":[87],"long":[88],"context":[89],"acoustic":[90],"information":[91],"further":[93],"improve":[94],"performance.":[96],"Finally,":[97],"extra":[98],"unlabeled":[99],"training":[100],"data":[101],"used":[102,134],"pre-training":[105],"stage":[106],"achieve":[108],"more":[109],"performance":[110],"gain.":[111],"The":[112],"proposed":[113],"synthesis":[117],"increases":[119],"CCA":[121],"0.299":[123],"(the":[124],"HMM":[125],"approach)":[126],"to":[127],"0.565":[128],"it":[130],"be":[132],"effectively":[133],"expressive":[136],"talking":[137,150],"avatar":[138,151],"animation.":[139],"Index":[140],"Terms:":[141],"network,":[146,149],"deep":[147]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}