{"id":"https://openalex.org/W2787248829","doi":"https://doi.org/10.1109/apsipa.2017.8282219","title":"Deep acoustic-to-articulatory inversion mapping with latent trajectory modeling","display_name":"Deep acoustic-to-articulatory inversion mapping with latent trajectory modeling","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787248829","doi":"https://doi.org/10.1109/apsipa.2017.8282219","mag":"2787248829"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5050897938","display_name":"Patrick Lumban Tobing","orcid":"https://orcid.org/0000-0003-2792-8418"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Patrick Lumban Tobing","raw_affiliation_strings":["Nagoya Daigaku, Nagoya, Aichi, JP"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya Daigaku, Nagoya, Aichi, JP","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001243214","display_name":"Hirokazu Kameoka","orcid":"https://orcid.org/0000-0003-3102-0162"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirokazu Kameoka","raw_affiliation_strings":["NTT Communication Science Laboratories, NTT Corporation, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NTT Communication Science Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Information Technology Center, Nagoya University, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Technology Center, Nagoya University, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1274","last_page":"1277"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994999766349792,"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":0.9994000196456909,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7251657247543335},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.7022483348846436},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6510758399963379},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5830190181732178},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.5441925525665283},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5209199786186218},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4760679602622986},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16196554899215698}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7251657247543335},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.7022483348846436},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6510758399963379},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5830190181732178},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.5441925525665283},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5209199786186218},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4760679602622986},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16196554899215698},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/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},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipa.2017.8282219","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/W275819404","https://openalex.org/W1488772215","https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1564657563","https://openalex.org/W1935012542","https://openalex.org/W1982854652","https://openalex.org/W1986174057","https://openalex.org/W2034829178","https://openalex.org/W2035329354","https://openalex.org/W2049686551","https://openalex.org/W2054764113","https://openalex.org/W2105478683","https://openalex.org/W2395700867","https://openalex.org/W2406009389","https://openalex.org/W2514160413","https://openalex.org/W2964121744","https://openalex.org/W6609917237","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6711832335","https://openalex.org/W6714339243"],"related_works":["https://openalex.org/W2023407680","https://openalex.org/W2116257577","https://openalex.org/W2121171378","https://openalex.org/W1585071156","https://openalex.org/W2775589536","https://openalex.org/W1531956331","https://openalex.org/W2169184169","https://openalex.org/W3150863438","https://openalex.org/W2290463584","https://openalex.org/W2103588662","https://openalex.org/W2095731437","https://openalex.org/W2167535584","https://openalex.org/W2160955451","https://openalex.org/W2125956490","https://openalex.org/W2151989153","https://openalex.org/W2063621534","https://openalex.org/W78597487","https://openalex.org/W2164243880","https://openalex.org/W1529602138","https://openalex.org/W2890182968"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,11,65,91,119],"novel":[4],"implementation":[5],"of":[6,50],"latent":[7,92,102,133],"trajectory":[8,93,103,134],"modeling":[9,94],"in":[10,60,112],"deep":[12,29],"acoustic-to-articulatory":[13],"inversion":[14,34,98,137,145],"mapping":[15,80,138,146],"framework.":[16],"In":[17,82,100],"the":[18,22,28,36,48,72,79,96,101,105,131,140,143],"conventional":[19,141],"methods,":[20],"i.e.,":[21],"Gaussian":[23],"mixture":[24],"model":[25,74],"(GMM)-":[26],"and":[27,56,70,115,123,142],"neural":[30],"network":[31],"(DNN)-":[32],"based":[33],"mappings,":[35],"frame":[37,106],"interdependency":[38,107],"can":[39,108],"be":[40,109],"considered":[41],"while":[42],"generating":[43],"articulatory":[44],"parameter":[45],"trajectories":[46],"with":[47],"use":[49],"an":[51],"explicit":[52],"constraint":[53,66],"between":[54,121],"static":[55,122],"dynamic":[57,124],"features.":[58,125],"However,":[59],"training":[61,114],"these":[62],"models,":[63],"such":[64],"is":[67,75],"not":[68,76],"considered,":[69,111],"therefore,":[71],"trained":[73],"optimum":[77],"for":[78],"procedure.":[81],"this":[83,87],"paper,":[84],"we":[85],"address":[86],"problem":[88],"by":[89,117],"introducing":[90],"into":[95],"DNN-based":[97],"mapping.":[99],"model,":[104],"well":[110],"both":[113],"mapping,":[116],"using":[118],"soft-constraint":[120],"The":[126],"experimental":[127],"results":[128],"demonstrate":[129],"that":[130],"proposed":[132],"DNN":[135],"(LTDNN)-based":[136],"outperforms":[139],"state-of-the-art":[144],"systems.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}