{"id":"https://openalex.org/W3140455833","doi":"https://doi.org/10.1109/slt48900.2021.9383554","title":"Unsupervised Acoustic-to-Articulatory Inversion Neural Network Learning Based on Deterministic Policy Gradient","display_name":"Unsupervised Acoustic-to-Articulatory Inversion Neural Network Learning Based on Deterministic Policy Gradient","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3140455833","doi":"https://doi.org/10.1109/slt48900.2021.9383554","mag":"3140455833"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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/A5003049061","display_name":"Hayato Shibata","orcid":null},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayato Shibata","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700673","display_name":"Mingxin Zhang","orcid":"https://orcid.org/0000-0002-7313-9172"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mingxin Zhang","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103015161","display_name":"Takahiro Shinozaki","orcid":"https://orcid.org/0000-0001-8114-8450"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Shinozaki","raw_affiliation_strings":["Tokyo Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology","institution_ids":["https://openalex.org/I114531698"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I114531698"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":null,"first_page":"530","last_page":"537"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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/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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.7713994979858398},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6848725080490112},{"id":"https://openalex.org/keywords/inversion","display_name":"Inversion (geology)","score":0.624823272228241},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.6154230833053589},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5642438530921936},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4058547914028168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40564417839050293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7713994979858398},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6848725080490112},{"id":"https://openalex.org/C1893757","wikidata":"https://www.wikidata.org/wiki/Q3653001","display_name":"Inversion (geology)","level":3,"score":0.624823272228241},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.6154230833053589},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5642438530921936},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4058547914028168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40564417839050293},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383554","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383554","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W46188241","https://openalex.org/W1494198834","https://openalex.org/W1531956331","https://openalex.org/W1595153059","https://openalex.org/W1965378753","https://openalex.org/W1969229349","https://openalex.org/W1990394889","https://openalex.org/W2006775235","https://openalex.org/W2027933203","https://openalex.org/W2030671974","https://openalex.org/W2043968544","https://openalex.org/W2067295501","https://openalex.org/W2105478683","https://openalex.org/W2119717200","https://openalex.org/W2154920538","https://openalex.org/W2155027007","https://openalex.org/W2156718681","https://openalex.org/W2165150801","https://openalex.org/W2191779130","https://openalex.org/W2231075402","https://openalex.org/W2286699414","https://openalex.org/W2395955767","https://openalex.org/W2407378606","https://openalex.org/W2509129594","https://openalex.org/W2623491082","https://openalex.org/W2797583228","https://openalex.org/W2888898948","https://openalex.org/W4302570325","https://openalex.org/W6682888085","https://openalex.org/W6683204974","https://openalex.org/W6684205842","https://openalex.org/W6689608924","https://openalex.org/W6711834147","https://openalex.org/W6713843360","https://openalex.org/W6739193204","https://openalex.org/W6750665317"],"related_works":["https://openalex.org/W1980470275","https://openalex.org/W2086322839","https://openalex.org/W2344971351","https://openalex.org/W2363509351","https://openalex.org/W2377084220","https://openalex.org/W1990581988","https://openalex.org/W2384206310","https://openalex.org/W2354391290","https://openalex.org/W2112313195","https://openalex.org/W2378498423"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"an":[3,64],"unsupervised":[4,19,85],"learning":[5,55,72,86,114],"method":[6,131,164],"of":[7,102,120],"deep":[8],"neural":[9,92],"networks":[10,93],"that":[11,36,94,128,165],"perform":[12],"acoustic-to-articulatory":[13,20,90],"inversion":[14,21,91],"for":[15,46,88,138,144,151],"arbitrary":[16],"utterances.":[17,146],"Conventional":[18],"methods":[22,69],"are":[23,155],"based":[24,84],"on":[25],"the":[26,89,103,107,118,121,129,162,168],"analysis-by-synthesis":[27],"approach":[28],"and":[29,73,76,116],"non-linear":[30],"optimization":[31],"algorithms.":[32],"One":[33],"limitation":[34],"is":[35,105],"they":[37],"require":[38],"time-consuming":[39],"iterative":[40,65],"optimizations":[41],"to":[42,157],"obtain":[43,59],"articulatory":[44,61,77,134,169],"parameters":[45,62,135,170],"a":[47,81,172],"given":[48],"target":[49],"speech":[50],"segment.":[51],"Neural":[52],"networks,":[53],"after":[54],"their":[56],"relationship,":[57],"can":[58,95,132],"these":[60],"without":[63],"optimization.":[66],"However,":[67],"conventional":[68,163],"need":[70],"supervised":[71],"paired":[74],"acoustic":[75],"samples.":[78],"We":[79,110],"propose":[80],"hybrid":[82],"auto-encoder":[83],"framework":[87,104],"capture":[96],"context":[97],"information.":[98],"The":[99],"essential":[100],"point":[101],"making":[106],"training":[108,139],"effective.":[109],"investigate":[111],"several":[112],"reinforcement":[113],"algorithms":[115],"show":[117],"usefulness":[119],"deterministic":[122],"policy":[123],"gradient.":[124],"Experimental":[125],"results":[126],"demonstrate":[127],"proposed":[130],"infer":[133],"not":[136],"only":[137],"set":[140],"segments":[141],"but":[142],"also":[143],"unseen":[145],"Averaged":[147],"reconstruction":[148],"errors":[149],"achieved":[150],"open":[152],"test":[153],"samples":[154],"similar":[156],"or":[158],"even":[159],"lower":[160],"than":[161],"directly":[166],"optimizes":[167],"in":[171],"closed":[173],"condition.":[174]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}