{"id":"https://openalex.org/W2902293851","doi":"https://doi.org/10.1109/icpr.2018.8545744","title":"Dense Convolutional Recurrent Neural Network for Generalized Speech Animation","display_name":"Dense Convolutional Recurrent Neural Network for Generalized Speech Animation","publication_year":2018,"publication_date":"2018-08-01","ids":{"openalex":"https://openalex.org/W2902293851","doi":"https://doi.org/10.1109/icpr.2018.8545744","mag":"2902293851"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2018.8545744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","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/A5100441099","display_name":"Lei Xiao","orcid":"https://orcid.org/0000-0003-0307-6206"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xiao","raw_affiliation_strings":["Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103123751","display_name":"Zengfu Wang","orcid":"https://orcid.org/0000-0003-1859-900X"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210099079","display_name":"Institute of Intelligent Machines","ror":"https://ror.org/00w0qep84","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I2802624667","https://openalex.org/I4210099079"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zengfu Wang","raw_affiliation_strings":["Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Intelligent Machines, Chinese Academy of Sciences, Hefei, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210099079"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":null,"first_page":"633","last_page":"638"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9986000061035156,"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/T10860","display_name":"Speech and Audio Processing","score":0.9977999925613403,"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":0.8451448678970337},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6754063367843628},{"id":"https://openalex.org/keywords/coarticulation","display_name":"Coarticulation","score":0.6150557994842529},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5639237761497498},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.49640804529190063},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49054545164108276},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4873245656490326},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4328058362007141},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4324125647544861},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4282156527042389},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4262833595275879},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.418410986661911},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4104020297527313},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1393853724002838}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8451448678970337},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6754063367843628},{"id":"https://openalex.org/C130727458","wikidata":"https://www.wikidata.org/wiki/Q1639109","display_name":"Coarticulation","level":3,"score":0.6150557994842529},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5639237761497498},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.49640804529190063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49054545164108276},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4873245656490326},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4328058362007141},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4324125647544861},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4282156527042389},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4262833595275879},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.418410986661911},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4104020297527313},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1393853724002838},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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":1,"locations":[{"id":"doi:10.1109/icpr.2018.8545744","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2018.8545744","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 24th International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1531956331","https://openalex.org/W1543471089","https://openalex.org/W1857884451","https://openalex.org/W1891702304","https://openalex.org/W2015394094","https://openalex.org/W2038891881","https://openalex.org/W2047871412","https://openalex.org/W2064675550","https://openalex.org/W2105063344","https://openalex.org/W2113774076","https://openalex.org/W2124020686","https://openalex.org/W2152754093","https://openalex.org/W2231075402","https://openalex.org/W2289286917","https://openalex.org/W2295661697","https://openalex.org/W2395955767","https://openalex.org/W2423557781","https://openalex.org/W2515372520","https://openalex.org/W2737658251","https://openalex.org/W2738406145","https://openalex.org/W2739192055","https://openalex.org/W2963446712","https://openalex.org/W2963636093","https://openalex.org/W6726406164"],"related_works":["https://openalex.org/W2368824897","https://openalex.org/W1508050556","https://openalex.org/W1910862367","https://openalex.org/W2379365082","https://openalex.org/W2370747590","https://openalex.org/W2030109976","https://openalex.org/W3031223029","https://openalex.org/W3167704465","https://openalex.org/W2369260257","https://openalex.org/W2389120450"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,19,30,55,120],"novel":[4],"automated":[5],"speech":[6,24],"animation":[7],"approach":[8,17,130,140],"named":[9],"Dense":[10],"Convolutional":[11],"Recurrent":[12],"Neural":[13],"Network":[14],"(DenseCRNN).":[15],"The":[16],"learns":[18],"non-linear":[20],"mapping":[21],"from":[22,67],"acoustic":[23],"to":[25,33,63,82,89,99],"multiple":[26],"articulator":[27],"movements":[28],"in":[29],"unified":[31],"framework":[32],"which":[34],"feature":[35],"extraction,":[36],"context":[37,85],"encoding":[38],"and":[39,109,147],"multi-parameter":[40],"decoding":[41],"are":[42],"integrated.":[43],"We":[44],"propose":[45],"DenseCRNN":[46],"based":[47],"on":[48,103,125,153],"three":[49],"insights:":[50],"(1)":[51],"One":[52],"can":[53,96],"use":[54],"convolutional":[56],"neural":[57,78],"network":[58,79],"incorporated":[59],"with":[60,87],"dense":[61],"connectivity":[62],"extract":[64],"speaker-independent":[65],"features":[66],"arbitrary":[68],"spoken":[69],"audio":[70],"effectively.":[71],"(2)":[72],"A":[73],"bidirectional":[74],"long":[75],"short-term":[76],"memory":[77],"is":[80,117],"able":[81],"model":[83],"the":[84,90,106,138,149],"information":[86],"respect":[88],"phoneme":[91],"coarticulation.":[92],"(3)":[93],"Multi-domain":[94],"learning":[95],"be":[97],"implemented":[98],"achieve":[100],"better":[101],"performance":[102],"account":[104],"of":[105,151],"implicit":[107],"correlation":[108],"explicit":[110],"difference":[111],"among":[112],"outputs,":[113],"where":[114],"each":[115],"domain":[116],"responsible":[118],"for":[119],"single":[121],"visual":[122],"parameter.":[123],"Experiments":[124],"MNGU0":[126],"dataset":[127],"demonstrate":[128],"our":[129],"achieves":[131],"significant":[132],"improvements":[133],"over":[134,142],"state-of-the-art":[135],"methods.":[136],"Moreover,":[137],"proposed":[139],"generalizes":[141],"different":[143],"gender":[144],"or":[145],"accent,":[146],"has":[148],"capability":[150],"deploying":[152],"various":[154],"character":[155],"models.":[156]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}