{"id":"https://openalex.org/W4297841334","doi":"https://doi.org/10.21437/interspeech.2022-10876","title":"Self-supervised speech unit discovery from articulatory and acoustic features using VQ-VAE","display_name":"Self-supervised speech unit discovery from articulatory and acoustic features using VQ-VAE","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841334","doi":"https://doi.org/10.21437/interspeech.2022-10876"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10876","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10876","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-03800013","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/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210100433","display_name":"Laboratoire de Psychologie et NeuroCognition","ror":"https://ror.org/014p6mg26","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I4210100433","https://openalex.org/I70900168","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I4210124956","display_name":"Grenoble Images Parole Signal Automatique","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":true,"raw_author_name":"Marc-Antoine Georges","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","GIPSA-PCMD - GIPSA - Perception, Contr\u00f4le, Multimodalit\u00e9 et Dynamiques de la parole (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","LPNC - Laboratoire de Psychologie et NeuroCognition (LPNC - Laboratoire de Psychologie et NeuroCognition\r\nCNRS UMR 5105 - UGA\r\nB\u00e2timent Michel Dubois (BMD) - 1251 Av Centrale\r\nCS40700\r\n38058 Grenoble Cedex 9 - France)"],"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]},{"raw_affiliation_string":"GIPSA-PCMD - GIPSA - Perception, Contr\u00f4le, Multimodalit\u00e9 et Dynamiques de la parole (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]},{"raw_affiliation_string":"LPNC - Laboratoire de Psychologie et NeuroCognition (LPNC - Laboratoire de Psychologie et NeuroCognition\r\nCNRS UMR 5105 - UGA\r\nB\u00e2timent Michel Dubois (BMD) - 1251 Av Centrale\r\nCS40700\r\n38058 Grenoble Cedex 9 - France)","institution_ids":["https://openalex.org/I4210100433","https://openalex.org/I1294671590","https://openalex.org/I899635006"]}]},{"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":"Grenoble Images Parole Signal Automatique","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-PCMD - GIPSA - Perception, Contr\u00f4le, Multimodalit\u00e9 et Dynamiques de la parole (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"GIPSA-PCMD - GIPSA - Perception, Contr\u00f4le, Multimodalit\u00e9 et Dynamiques de la parole (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","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":[{"id":"https://openalex.org/I4210124956","display_name":"Grenoble Images Parole Signal Automatique","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":"Thomas Hueber","raw_affiliation_strings":["GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)"],"affiliations":[{"raw_affiliation_string":"GIPSA-CRISSP - GIPSA - Cognitive Robotics, Interactive Systems, & Speech Processing (GIPSA-lab, 11 rue des Math\u00e9matiques, Grenoble Campus BP46, F-38402 SAINT MARTIN D'HERES CEDEX - France)","institution_ids":["https://openalex.org/I4210124956"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5061153464"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210100433","https://openalex.org/I4210124956","https://openalex.org/I899635006"],"apc_list":null,"apc_paid":null,"fwci":0.1039,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.29093945,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"774","last_page":"778"},"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":0.9986000061035156,"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":0.9983999729156494,"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/speech-recognition","display_name":"Speech recognition","score":0.7611267566680908},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7360663414001465},{"id":"https://openalex.org/keywords/unit","display_name":"Unit (ring theory)","score":0.5012161731719971},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.427074670791626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4181627035140991},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4175386428833008},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1457703411579132}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7611267566680908},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360663414001465},{"id":"https://openalex.org/C122637931","wikidata":"https://www.wikidata.org/wiki/Q118084","display_name":"Unit (ring theory)","level":2,"score":0.5012161731719971},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.427074670791626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4181627035140991},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4175386428833008},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1457703411579132},{"id":"https://openalex.org/C145420912","wikidata":"https://www.wikidata.org/wiki/Q853077","display_name":"Mathematics education","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2022-10876","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10876","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03800013v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03800013","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.interspeech2022.org/","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03800013v1","is_oa":true,"landing_page_url":"https://hal.science/hal-03800013","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.interspeech2022.org/","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W60202269","https://openalex.org/W123135133","https://openalex.org/W1562842113","https://openalex.org/W1909320841","https://openalex.org/W1945090009","https://openalex.org/W1959608418","https://openalex.org/W1966120736","https://openalex.org/W1982854652","https://openalex.org/W2020607164","https://openalex.org/W2043199434","https://openalex.org/W2052697931","https://openalex.org/W2068247585","https://openalex.org/W2068595942","https://openalex.org/W2100768664","https://openalex.org/W2150423550","https://openalex.org/W2395899413","https://openalex.org/W2402366697","https://openalex.org/W2576152124","https://openalex.org/W2593779438","https://openalex.org/W2963799213","https://openalex.org/W2972374322","https://openalex.org/W3095361818","https://openalex.org/W3196458264","https://openalex.org/W4252379885","https://openalex.org/W4288107125","https://openalex.org/W4295312788","https://openalex.org/W4300047444"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"International":[0],"audience":[1]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}