{"id":"https://openalex.org/W4375869343","doi":"https://doi.org/10.1109/icassp49357.2023.10096751","title":"Speech Modeling with a Hierarchical Transformer Dynamical VAE","display_name":"Speech Modeling with a Hierarchical Transformer Dynamical VAE","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375869343","doi":"https://doi.org/10.1109/icassp49357.2023.10096751"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096751","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096751","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-04132313","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087031558","display_name":"Xiaoyu Lin","orcid":"https://orcid.org/0000-0001-7486-9452"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xiaoyu Lin","raw_affiliation_strings":["Univ. Grenoble Alpes,Inria Grenoble Rh&#x00F4;ne-Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes,Inria Grenoble Rh&#x00F4;ne-Alpes,France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041909571","display_name":"Xiaoyu Bie","orcid":"https://orcid.org/0000-0003-1480-0538"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xiaoyu Bie","raw_affiliation_strings":["Univ. Grenoble Alpes,Inria Grenoble Rh&#x00F4;ne-Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes,Inria Grenoble Rh&#x00F4;ne-Alpes,France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045593473","display_name":"Simon Leglaive","orcid":"https://orcid.org/0000-0002-8219-1298"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I4210107720","display_name":"CentraleSup\u00e9lec","ror":"https://ror.org/019tcpt25","country_code":"FR","type":"facility","lineage":["https://openalex.org/I277688954","https://openalex.org/I4210107720"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Simon Leglaive","raw_affiliation_strings":["IETR (UMR CNRS 6164),CentraleSup&#x00E9;lec,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IETR (UMR CNRS 6164),CentraleSup&#x00E9;lec,France","institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I4210100151","https://openalex.org/I4210107720"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020392160","display_name":"Laurent Girin","orcid":"https://orcid.org/0000-0002-9214-8760"},"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"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"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"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["Univ. Grenoble Alpes,CNRS, Grenoble-INP, GIPSA-Lab,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes,CNRS, Grenoble-INP, GIPSA-Lab,France","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066621495","display_name":"Xavier Alameda-Pineda","orcid":"https://orcid.org/0000-0002-5354-1084"},"institutions":[{"id":"https://openalex.org/I4210101348","display_name":"Centre Inria de l'Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/00n8d6z93","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1326498283","https://openalex.org/I4210101348"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["Univ. Grenoble Alpes,Inria Grenoble Rh&#x00F4;ne-Alpes,France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes,Inria Grenoble Rh&#x00F4;ne-Alpes,France","institution_ids":["https://openalex.org/I4210101348","https://openalex.org/I899635006"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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/T11309","display_name":"Music and Audio Processing","score":0.9997000098228455,"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":0.9994000196456909,"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":0.9993000030517578,"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/transformer","display_name":"Transformer","score":0.7645646333694458},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7345641851425171},{"id":"https://openalex.org/keywords/latent-variable","display_name":"Latent variable","score":0.5948153734207153},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.5843327641487122},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5279012322425842},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5076905488967896},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5012500286102295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4760715365409851},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.47517886757850647},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.47052323818206787},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4559221863746643},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.443869948387146},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35572683811187744},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0800132155418396}],"concepts":[{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7645646333694458},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345641851425171},{"id":"https://openalex.org/C51167844","wikidata":"https://www.wikidata.org/wiki/Q4422623","display_name":"Latent variable","level":2,"score":0.5948153734207153},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.5843327641487122},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5279012322425842},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5076905488967896},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5012500286102295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4760715365409851},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.47517886757850647},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.47052323818206787},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4559221863746643},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.443869948387146},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35572683811187744},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0800132155418396},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096751","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096751","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"},{"id":"pmh:oai:HAL:hal-04132313v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04132313","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://2023.ieeeicassp.org/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04132313v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-04132313","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://2023.ieeeicassp.org/","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5}],"awards":[{"id":"https://openalex.org/G1041279674","display_name":"MIAI @ Grenoble Alpes","funder_award_id":"ANR-19-P3IA-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5495492380","display_name":"Multi-Modal Multi-person Low-Level Learning for Robot Interaction","funder_award_id":"ANR-19-CE33-0008","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W592244745","https://openalex.org/W648786980","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1909320841","https://openalex.org/W1959608418","https://openalex.org/W2016589492","https://openalex.org/W2039844283","https://openalex.org/W2120847449","https://openalex.org/W2141998673","https://openalex.org/W2149273154","https://openalex.org/W2193413348","https://openalex.org/W2396566817","https://openalex.org/W2514828952","https://openalex.org/W2758785877","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2963263347","https://openalex.org/W2975414524","https://openalex.org/W2996286887","https://openalex.org/W3005621653","https://openalex.org/W3094502228","https://openalex.org/W3174264304","https://openalex.org/W3185637724","https://openalex.org/W3207551191","https://openalex.org/W3217536461","https://openalex.org/W4225706358","https://openalex.org/W4385245566","https://openalex.org/W6617744952","https://openalex.org/W6621543089","https://openalex.org/W6631190155","https://openalex.org/W6639732818","https://openalex.org/W6640963894","https://openalex.org/W6685152286","https://openalex.org/W6687566353","https://openalex.org/W6712395597","https://openalex.org/W6726497184","https://openalex.org/W6739901393","https://openalex.org/W6745117592","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6784333009","https://openalex.org/W6811270123"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2616125534","https://openalex.org/W2963987720","https://openalex.org/W3022187094","https://openalex.org/W2146310005","https://openalex.org/W2963790827","https://openalex.org/W2786010873","https://openalex.org/W4293659211"],"abstract_inverted_index":{"The":[0],"dynamical":[1],"variational":[2],"autoencoders":[3],"(DVAEs)":[4],"are":[5,50,90],"a":[6,19,25,73,110],"family":[7],"of":[8,21,28,36,78],"latent-variable":[9],"deep":[10],"generative":[11],"models":[12],"that":[13,98],"extends":[14],"the":[15,34,37,39,47,66,87,93],"VAE":[16],"to":[17,61],"model":[18,62],"sequence":[20,27,44],"observed":[22],"data":[23],"and":[24,45,82,84],"corresponding":[26],"latent":[29,79],"vectors.":[30],"In":[31,56],"almost":[32],"all":[33],"DVAEs":[35,103],"literature,":[38],"temporal":[40,88],"dependencies":[41,89],"within":[42],"each":[43],"across":[46],"two":[48,76],"sequences":[49],"modeled":[51],"with":[52,65,75,92],"recurrent":[53],"neural":[54],"networks.":[55],"this":[57],"paper,":[58],"we":[59],"propose":[60],"speech":[63,105,121,126],"signals":[64],"Hierarchical":[67],"Transformer":[68,94],"DVAE":[69,74],"(HiT-DVAE),":[70],"which":[71,86],"is":[72],"levels":[77],"variable":[80],"(sequence-wise":[81],"frame-wise)":[83],"in":[85],"implemented":[91],"architecture.":[95],"We":[96],"show":[97],"HiT-DVAE":[99],"outperforms":[100],"several":[101],"other":[102],"for":[104,118],"spectrogram":[106],"modeling,":[107],"while":[108],"enabling":[109],"simpler":[111],"training":[112],"procedure,":[113],"revealing":[114],"its":[115],"high":[116],"potential":[117],"downstream":[119],"low-level":[120],"processing":[122],"tasks":[123],"such":[124],"as":[125],"enhancement.":[127]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}
