{"id":"https://openalex.org/W3146195244","doi":"https://doi.org/10.21437/interspeech.2021-1604","title":"Learning Robust Speech Representation with an Articulatory-Regularized Variational Autoencoder","display_name":"Learning Robust Speech Representation with an Articulatory-Regularized Variational Autoencoder","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3146195244","doi":"https://doi.org/10.21437/interspeech.2021-1604","mag":"3146195244"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-1604","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2104.03204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061153464","display_name":"Marc-Antoine Georges","orcid":null},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marc-Antoine Georges","raw_affiliation_strings":["Grenoble Institute of Technology#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Grenoble Institute of Technology#TAB#","institution_ids":["https://openalex.org/I106785703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001142101","display_name":"Jean\u2010Luc Schwartz","orcid":"https://orcid.org/0000-0001-8969-9185"},"institutions":[{"id":"https://openalex.org/I4210124956","display_name":"GIPSA-Lab","ror":"https://ror.org/02wrme198","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006","https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Jean-Luc Schwartz","raw_affiliation_strings":["GIPSA - Perception, Contr\u00f4le, Multimodalit\u00e9 et Dynamiques de la parole"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA - Perception, Contr\u00f4le, Multimodalit\u00e9 et Dynamiques de la parole","institution_ids":["https://openalex.org/I4210124956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060372031","display_name":"Thomas Hueber","orcid":"https://orcid.org/0000-0002-8296-5177"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Hueber","raw_affiliation_strings":["GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1543,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.40903614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"3345","last_page":"3349"},"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":0.9997000098228455,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9991000294685364,"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/vocal-tract","display_name":"Vocal tract","score":0.8234802484512329},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8084774613380432},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6154831051826477},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5833100080490112},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.561474084854126},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5254492163658142},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4850679934024811},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.48103052377700806},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.480352520942688},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4790309965610504},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.4582594335079193},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4251285493373871},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.33328384160995483},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.26296234130859375},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24751412868499756}],"concepts":[{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.8234802484512329},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8084774613380432},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6154831051826477},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5833100080490112},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.561474084854126},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5254492163658142},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4850679934024811},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.48103052377700806},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.480352520942688},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4790309965610504},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.4582594335079193},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4251285493373871},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.33328384160995483},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.26296234130859375},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24751412868499756},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2021-1604","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-1604","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2021","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2104.03204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.03204","pdf_url":"https://arxiv.org/pdf/2104.03204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:HAL:hal-03373252v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03373252","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://www.interspeech2021.org/","raw_type":"Conference papers"},{"id":"doi:10.48550/arxiv.2104.03204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2104.03204","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"mag:3146195244","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2104.03204","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2104.03204","pdf_url":"https://arxiv.org/pdf/2104.03204","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.4099999964237213}],"awards":[{"id":"https://openalex.org/G1041279674","display_name":null,"funder_award_id":"ANR-19-P3IA-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W123135133","https://openalex.org/W1959608418","https://openalex.org/W1966120736","https://openalex.org/W1972387079","https://openalex.org/W2011192906","https://openalex.org/W2037506348","https://openalex.org/W2051740312","https://openalex.org/W2052382192","https://openalex.org/W2068247585","https://openalex.org/W2089012997","https://openalex.org/W2090393855","https://openalex.org/W2091288983","https://openalex.org/W2135707066","https://openalex.org/W2150423550","https://openalex.org/W2515020857","https://openalex.org/W2532494225","https://openalex.org/W2548604699","https://openalex.org/W2595771591","https://openalex.org/W2766672686","https://openalex.org/W2768153200","https://openalex.org/W2779206865","https://openalex.org/W2804722844","https://openalex.org/W2889412120","https://openalex.org/W2890669918","https://openalex.org/W2901552243","https://openalex.org/W2962691331","https://openalex.org/W2962850167","https://openalex.org/W2962897886","https://openalex.org/W2963091184","https://openalex.org/W2970971581","https://openalex.org/W2999130843","https://openalex.org/W3094929307","https://openalex.org/W3160669408"],"related_works":["https://openalex.org/W3196458264","https://openalex.org/W2108828451","https://openalex.org/W2039636789","https://openalex.org/W2089329752","https://openalex.org/W1543281296","https://openalex.org/W2473380315","https://openalex.org/W2122407890","https://openalex.org/W2404570131","https://openalex.org/W2125157818","https://openalex.org/W2911726185","https://openalex.org/W2291998724","https://openalex.org/W2034031956","https://openalex.org/W19151215","https://openalex.org/W192752013","https://openalex.org/W1503769282","https://openalex.org/W900447646","https://openalex.org/W2543752677","https://openalex.org/W2128149235","https://openalex.org/W2793399581","https://openalex.org/W1973016470"],"abstract_inverted_index":{"It":[0],"is":[1],"increasingly":[2],"considered":[3],"that":[4,91,104],"human":[5],"speech":[6,44,127],"perception":[7],"and":[8,41,62,69,116,121],"production":[9],"both":[10],"rely":[11],"on":[12,83],"articulatory":[13,50,55,76,100,106],"representations.":[14],"In":[15],"this":[16,21,105],"paper,":[17],"we":[18,47,73],"investigate":[19],"whether":[20],"type":[22],"of":[23,29,94],"representation":[24],"could":[25],"improve":[26],"the":[27,58,95],"performances":[28],"a":[30,35,79,88,126],"deep":[31],"generative":[32],"model":[33,51,109],"(here":[34],"variational":[36,80],"autoencoder)":[37],"trained":[38],"to":[39,53,98,114],"encode":[40],"decode":[42],"acoustic":[43],"features.":[45,71],"First":[46],"develop":[48],"an":[49],"able":[52],"associate":[54],"parameters":[56,77],"describing":[57],"jaw,":[59],"tongue,":[60],"lips":[61],"velum":[63],"configurations":[64],"with":[65],"vocal":[66],"tract":[67],"shapes":[68],"spectral":[70,84],"Then":[72],"incorporate":[74],"these":[75],"into":[78],"autoencoder":[81],"applied":[82],"features":[85],"by":[86,111],"using":[87],"regularization":[89],"technique":[90],"constraints":[92],"part":[93],"latent":[96],"space":[97],"follow":[99],"trajectories.":[101],"We":[102],"show":[103],"constraint":[107],"improves":[108],"training":[110],"decreasing":[112],"time":[113],"convergence":[115],"reconstruction":[117],"loss":[118],"at":[119],"convergence,":[120],"yields":[122],"better":[123],"performance":[124],"in":[125],"denoising":[128],"task.":[129]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-20T22:02:38.213706","created_date":"2025-10-10T00:00:00"}