{"id":"https://openalex.org/W2940787599","doi":"https://doi.org/10.1109/vcip.2018.8698617","title":"Synthesizing 3D Acoustic-Articulatory Mapping Trajectories: Predicting Articulatory Movements by Long-Term Recurrent Convolutional Neural Network","display_name":"Synthesizing 3D Acoustic-Articulatory Mapping Trajectories: Predicting Articulatory Movements by Long-Term Recurrent Convolutional Neural Network","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2940787599","doi":"https://doi.org/10.1109/vcip.2018.8698617","mag":"2940787599"},"language":"en","primary_location":{"id":"doi:10.1109/vcip.2018.8698617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2018.8698617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Visual Communications and Image Processing (VCIP)","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/A5089799495","display_name":"Lingyun Yu","orcid":"https://orcid.org/0000-0001-6403-761X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingyun Yu","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048818071","display_name":"Jun Yu","orcid":"https://orcid.org/0000-0002-3197-8103"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Yu","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007719477","display_name":"Qiang Ling","orcid":"https://orcid.org/0000-0001-5688-4130"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qiang Ling","raw_affiliation_strings":["Department of Automation, University of Science and Technology of China, Anhui, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Automation, University of Science and Technology of China, Anhui, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.5412,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65833013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"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":0.9965000152587891,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech 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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955000281333923,"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/T12290","display_name":"Human Motion and Animation","score":0.9922999739646912,"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/recurrent-neural-network","display_name":"Recurrent neural network","score":0.8279404044151306},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8121786117553711},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.643581748008728},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6282444000244141},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6063008904457092},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5463985204696655},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5284777879714966},{"id":"https://openalex.org/keywords/mean-squared-error","display_name":"Mean squared error","score":0.5106325745582581},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.503783643245697},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4728819727897644},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.4724307954311371},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.4500312805175781},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.44686359167099},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4230327010154724},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.4146794080734253},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08827868103981018}],"concepts":[{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.8279404044151306},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121786117553711},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.643581748008728},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6282444000244141},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6063008904457092},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5463985204696655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5284777879714966},{"id":"https://openalex.org/C139945424","wikidata":"https://www.wikidata.org/wiki/Q1940696","display_name":"Mean squared error","level":2,"score":0.5106325745582581},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.503783643245697},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4728819727897644},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.4724307954311371},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.4500312805175781},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.44686359167099},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4230327010154724},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4146794080734253},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08827868103981018},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/vcip.2018.8698617","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vcip.2018.8698617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Visual Communications and Image Processing (VCIP)","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":22,"referenced_works":["https://openalex.org/W1531956331","https://openalex.org/W1538131130","https://openalex.org/W1543471089","https://openalex.org/W1947481528","https://openalex.org/W1982854652","https://openalex.org/W2002802259","https://openalex.org/W2107739094","https://openalex.org/W2131770202","https://openalex.org/W2132733106","https://openalex.org/W2194775991","https://openalex.org/W2395955767","https://openalex.org/W2511730936","https://openalex.org/W2541674938","https://openalex.org/W2596135543","https://openalex.org/W2963410064","https://openalex.org/W2963446712","https://openalex.org/W4285719527","https://openalex.org/W6632100814","https://openalex.org/W6711834147","https://openalex.org/W6729059855","https://openalex.org/W6735255722","https://openalex.org/W7045481054"],"related_works":["https://openalex.org/W2964006806","https://openalex.org/W2109916967","https://openalex.org/W2965782936","https://openalex.org/W2890297197","https://openalex.org/W4377697116","https://openalex.org/W4387022695","https://openalex.org/W4289083005","https://openalex.org/W2906722931","https://openalex.org/W2101697354","https://openalex.org/W1538193578"],"abstract_inverted_index":{"Robust":[0],"and":[1,16,47,59,87,146],"accurate":[2],"predicting":[3],"of":[4,84],"articulatory":[5,14],"movements":[6],"has":[7,52],"various":[8],"important":[9],"applications,":[10],"such":[11],"as":[12],"3D":[13],"animations":[15],"visual":[17],"communication.":[18],"Various":[19],"approaches":[20],"have":[21],"been":[22],"proposed":[23],"to":[24,128],"solve":[25],"the":[26,63,94,109,122,130,138,147],"acoustic-articulatory":[27,72],"mapping":[28],"problem.":[29],"However,":[30],"their":[31],"precision":[32],"is":[33],"not":[34],"high":[35],"enough.":[36],"Recently,":[37],"deep":[38],"neural":[39,44,49,78],"network":[40,45,50,69,79,82],"(DNN),":[41],"especially":[42],"convolutional":[43,77],"(CNN)":[46],"recurrent":[48,76],"(RNN),":[51],"brought":[53],"tremendous":[54],"success":[55],"in":[56,152],"speech":[57],"recognition":[58],"synthesis.":[60],"To":[61],"increase":[62,121],"accuracy,":[64],"we":[65],"propose":[66],"a":[67,88],"new":[68],"architecture":[70],"for":[71],"mapping,":[73],"called":[74],"long-term":[75],"(LTRCNN).":[80],"The":[81],"consists":[83],"CNN,":[85],"RNN":[86],"skip":[89,118],"connection.":[90],"CNN":[91],"can":[92,107,120],"model":[93],"spectral":[95],"correlation":[96,148],"among":[97],"acoustic":[98],"features":[99],"efficiently.":[100],"RNN,":[101],"like":[102],"long":[103],"short-term":[104],"memory":[105],"(LSTM),":[106],"learn":[108],"temporal":[110],"context":[111],"information":[112],"from":[113,125],"sequential":[114],"data":[115],"powerfully.":[116],"Besides,":[117],"connections":[119],"input":[123],"representation":[124],"different":[126],"levels":[127],"preserve":[129],"feature":[131],"information.":[132],"Experiments":[133],"show":[134],"that":[135],"LTRCNN":[136],"achieves":[137],"state-of-the-art":[139],"root-mean-squared":[140],"error":[141],"(RMSE)":[142],"with":[143,150],"0.690":[144],"mm":[145],"coefficient":[149],"0.949":[151],"this":[153],"prediction":[154],"task.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}