{"id":"https://openalex.org/W2944489095","doi":"https://doi.org/10.1109/iscslp.2018.8706709","title":"Investigation of Stacked Deep Neural Networks and Mixture Density Networks for Acoustic-to-Articulatory Inversion","display_name":"Investigation of Stacked Deep Neural Networks and Mixture Density Networks for Acoustic-to-Articulatory Inversion","publication_year":2018,"publication_date":"2018-11-01","ids":{"openalex":"https://openalex.org/W2944489095","doi":"https://doi.org/10.1109/iscslp.2018.8706709","mag":"2944489095"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2018.8706709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5035857878","display_name":"Xurong Xie","orcid":"https://orcid.org/0000-0002-6714-6296"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xurong Xie","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037109470","display_name":"Xunying Liu","orcid":"https://orcid.org/0000-0001-6725-1160"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xunying Liu","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001795601","display_name":"Tan Lee","orcid":"https://orcid.org/0000-0002-7089-3436"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Tan Lee","raw_affiliation_strings":["Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363653","display_name":"Lan Wang","orcid":"https://orcid.org/0000-0002-7341-4904"},"institutions":[{"id":"https://openalex.org/I4210145761","display_name":"Shenzhen Institutes of Advanced Technology","ror":"https://ror.org/04gh4er46","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210145761"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lan Wang","raw_affiliation_strings":["Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China","institution_ids":["https://openalex.org/I4210145761"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8448,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.81487967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"1","issue":null,"first_page":"36","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/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/T10403","display_name":"Phonetics and Phonology Research","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.7675168514251709},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6095575094223022},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5881535410881042},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.586358368396759},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5801715850830078},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48657310009002686},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.47866925597190857},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4387274384498596},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4259563684463501},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3950343728065491},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.09091684222221375}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7675168514251709},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6095575094223022},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5881535410881042},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.586358368396759},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5801715850830078},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48657310009002686},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.47866925597190857},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4387274384498596},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4259563684463501},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3950343728065491},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.09091684222221375},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.0},{"id":"https://openalex.org/C109007969","wikidata":"https://www.wikidata.org/wiki/Q749565","display_name":"Structural basin","level":2,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2018.8706709","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2018.8706709","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W1499332833","https://openalex.org/W1524333225","https://openalex.org/W1531956331","https://openalex.org/W1579853615","https://openalex.org/W2012897754","https://openalex.org/W2013317861","https://openalex.org/W2093960627","https://openalex.org/W2117671523","https://openalex.org/W2134973740","https://openalex.org/W2154920538","https://openalex.org/W2173629880","https://openalex.org/W2231075402","https://openalex.org/W2395955767","https://openalex.org/W2402610474","https://openalex.org/W2507804770","https://openalex.org/W2749659443","https://openalex.org/W6631362777","https://openalex.org/W6631967750","https://openalex.org/W6634817459","https://openalex.org/W6677326886","https://openalex.org/W6682918086","https://openalex.org/W6689608924","https://openalex.org/W6711834147","https://openalex.org/W6713398208"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W4382618745","https://openalex.org/W2885125400","https://openalex.org/W1989889224","https://openalex.org/W1987128138","https://openalex.org/W2748922771"],"abstract_inverted_index":{"Acoustic-to-articulatory":[0],"inversion":[1],"predicting":[2],"articulatory":[3,69],"movement":[4],"based":[5,23],"on":[6,95,108],"the":[7,27,31,76,81,97,109,119,141],"acoustic":[8,117],"signal":[9],"is":[10,138],"useful":[11],"for":[12,40],"many":[13],"applications":[14],"like":[15],"talking":[16],"head,":[17],"speech":[18],"recognition,":[19],"and":[20,67,91,102,129,143,149],"education.":[21],"DNN":[22],"technologies":[24],"have":[25],"achieved":[26],"state-of-the-art":[28],"performance":[29],"in":[30,135],"area.":[32],"This":[33],"paper":[34],"investigates":[35],"different":[36,56],"stacked":[37,83,121],"network":[38],"architectures":[39],"acoustic-to-articulatory":[41],"inversion.":[42],"Two":[43],"levels":[44],"of":[45,58,112],"DNNs":[46,88],"or":[47],"mixture":[48],"density":[49],"networks":[50],"(MDNs)":[51],"can":[52],"be":[53],"connected":[54],"using":[55,85,115,123],"types":[57],"auxiliary":[59],"features,":[60,63,66,118],"including":[61],"bottleneck":[62],"directly":[64],"generated":[65,131],"predicted":[68],"features":[70,132],"via":[71],"MLPG":[72,130],"algorithm":[73],"extracted":[74],"from":[75],"first":[77],"level":[78],"network.":[79],"For":[80],"experiments,":[82],"systems":[84,146],"DNNs,":[86],"time-delay":[87],"(TDNNs),":[89],"RNNs":[90],"MDNs":[92,125],"were":[93],"evaluated":[94],"both":[96],"MNGU0":[98,113],"English":[99],"EMA":[100,105],"database":[101],"AIMSL":[103],"Chinese":[104],"database.":[106],"Finally,":[107],"default":[110],"configurations":[111],"data":[114],"LSF":[116],"proposed":[120],"system":[122],"feed-forward":[124],"with":[126,147],"ellipsoid":[127],"variance":[128],"got":[133],"0.718mm":[134],"RMSE,":[136],"which":[137],"similar":[139],"to":[140],"RNN":[142],"RNN-MDN":[144],"BLSTM":[145],"slower":[148],"more":[150],"difficult":[151],"training":[152],"stage.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}