{"id":"https://openalex.org/W4372266101","doi":"https://doi.org/10.1109/icassp49357.2023.10096800","title":"Articulation GAN: Unsupervised Modeling of Articulatory Learning","display_name":"Articulation GAN: Unsupervised Modeling of Articulatory Learning","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372266101","doi":"https://doi.org/10.1109/icassp49357.2023.10096800"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","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/A5090898601","display_name":"Ga\u0161per Begu\u0161","orcid":"https://orcid.org/0000-0002-6459-0551"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ga\u0161per Begu\u0161","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083294042","display_name":"Alan Zhou","orcid":"https://orcid.org/0000-0003-3126-7552"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan Zhou","raw_affiliation_strings":["Johns Hopkins University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081837203","display_name":"Peter Wu","orcid":"https://orcid.org/0000-0001-6503-3936"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Wu","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068922218","display_name":"Gopala K. Anumanchipalli","orcid":"https://orcid.org/0000-0002-9714-7740"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopala K. Anumanchipalli","raw_affiliation_strings":["University of California,Berkeley","University of California, Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California,Berkeley","institution_ids":["https://openalex.org/I95457486"]},{"raw_affiliation_string":"University of California, Berkeley","institution_ids":["https://openalex.org/I95457486"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5090898601"],"corresponding_institution_ids":["https://openalex.org/I95457486"],"apc_list":null,"apc_paid":null,"fwci":0.9914,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76084553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9975000023841858,"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":0.7762467861175537},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.6863688230514526},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6516101360321045},{"id":"https://openalex.org/keywords/discriminator","display_name":"Discriminator","score":0.6418907642364502},{"id":"https://openalex.org/keywords/manner-of-articulation","display_name":"Manner of articulation","score":0.5923004746437073},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5465672612190247},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5401524305343628},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.5315123796463013},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.523071825504303},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47246432304382324},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.46318814158439636},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4437675476074219}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762467861175537},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.6863688230514526},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6516101360321045},{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.6418907642364502},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.5923004746437073},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5465672612190247},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5401524305343628},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.5315123796463013},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.523071825504303},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47246432304382324},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.46318814158439636},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4437675476074219},{"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/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096800","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096800","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W2015075592","https://openalex.org/W2023407680","https://openalex.org/W2068447135","https://openalex.org/W2231075402","https://openalex.org/W2295969124","https://openalex.org/W2402366697","https://openalex.org/W2889194909","https://openalex.org/W2963684088","https://openalex.org/W3031894486","https://openalex.org/W3033010920","https://openalex.org/W3092028330","https://openalex.org/W3106255532","https://openalex.org/W3108801622","https://openalex.org/W3127686677","https://openalex.org/W3139146258","https://openalex.org/W3159506701","https://openalex.org/W3175673202","https://openalex.org/W3205586509","https://openalex.org/W4200371243","https://openalex.org/W4210416677","https://openalex.org/W4221155059","https://openalex.org/W4226017879","https://openalex.org/W4247626952","https://openalex.org/W4295521014","https://openalex.org/W4297817572","https://openalex.org/W4297841334","https://openalex.org/W4297841848","https://openalex.org/W4320013936","https://openalex.org/W6685352114","https://openalex.org/W6735913928","https://openalex.org/W6755257315","https://openalex.org/W6783867762","https://openalex.org/W6786310916","https://openalex.org/W6789826613","https://openalex.org/W6791817011","https://openalex.org/W6797957363"],"related_works":["https://openalex.org/W2334129531","https://openalex.org/W2777500320","https://openalex.org/W2515097069","https://openalex.org/W2164147372","https://openalex.org/W1544536563","https://openalex.org/W2550171623","https://openalex.org/W4300049944","https://openalex.org/W4253660971","https://openalex.org/W2748448327","https://openalex.org/W1909292483"],"abstract_inverted_index":{"Generative":[0,48],"deep":[1],"neural":[2],"networks":[3],"are":[4,140],"widely":[5],"used":[6],"for":[7,105,156],"speech":[8,23,33,58,67,97,124,163],"synthesis,":[9],"but":[10],"most":[11],"existing":[12],"models":[13,158],"directly":[14],"generate":[15,72,137],"waveforms":[16],"or":[17,77],"spectral":[18],"outputs.":[19],"Humans,":[20],"however,":[21],"produce":[22],"by":[24,69],"controlling":[25],"articulators,":[26],"which":[27,99],"results":[28],"in":[29,79,117,145,165],"the":[30,43,47,92,103,111,129,133,146],"production":[31,68],"of":[32,38,57,128,153,159],"sounds":[34],"through":[35],"physical":[36,87],"properties":[37],"sound":[39],"propagation.":[40],"We":[41,149],"introduce":[42],"Articulatory":[44,61,107],"Generator":[45,62],"to":[46,71,96,102,114,121,136],"Adversarial":[49],"Network":[50],"paradigm,":[51],"a":[52,80,118],"new":[53],"unsupervised":[54,82],"generative":[55],"model":[56,88],"production/synthesis.":[59],"The":[60],"more":[63],"closely":[64],"mimics":[65],"human":[66,160],"learning":[70],"articulatory":[73,154],"representations":[74,95,155],"(electromagnetic":[75],"articulography":[76],"EMA)":[78],"fully":[81],"manner.":[83],"A":[84],"separate":[85],"pre-trained":[86],"(ema2wav)":[89],"then":[90],"transforms":[91],"generated":[93],"EMA":[94],"waveforms,":[98],"get":[100],"sent":[101],"Discriminator":[104],"evaluation.":[106],"analysis":[108,127],"suggests":[109,131],"that":[110,132,139],"network":[112,134],"learns":[113,135],"control":[115],"articulators":[116],"similar":[119],"manner":[120],"humans":[122],"during":[123],"production.":[125],"Acoustic":[126],"outputs":[130],"words":[138],"both":[141],"present":[142],"and":[143,162],"absent":[144],"training":[147],"distribution.":[148],"additionally":[150],"discuss":[151],"implications":[152],"cognitive":[157],"language":[161],"technology":[164],"general.":[166]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-05-04T08:30:34.212998","created_date":"2025-10-10T00:00:00"}