{"id":"https://openalex.org/W3185637724","doi":"https://doi.org/10.21437/interspeech.2021-256","title":"A Benchmark of Dynamical Variational Autoencoders Applied to Speech Spectrogram Modeling","display_name":"A Benchmark of Dynamical Variational Autoencoders Applied to Speech Spectrogram Modeling","publication_year":2021,"publication_date":"2021-08-27","ids":{"openalex":"https://openalex.org/W3185637724","doi":"https://doi.org/10.21437/interspeech.2021-256","mag":"3185637724"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2021-256","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-256","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/hal-03295657","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5041909571","display_name":"Xiaoyu Bie","orcid":"https://orcid.org/0000-0003-1480-0538"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xiaoyu Bie","raw_affiliation_strings":["ROBOTLEARN - Vers des robots \u00e0 l\u2019intelligence sociale au travers de l\u2019apprentissage, de la perception et de la commande (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ROBOTLEARN - Vers des robots \u00e0 l\u2019intelligence sociale au travers de l\u2019apprentissage, de la perception et de la commande (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot - France)","institution_ids":["https://openalex.org/I1326498283"]}]},{"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/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":"Laurent Girin","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)"],"raw_orcid":null,"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"]}]},{"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/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":["CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CentraleSup\u00e9lec [campus de Rennes] (Campus de Rennes, Av. de la Boulaie, 35510 Cesson-S\u00e9vign\u00e9 - France)","institution_ids":["https://openalex.org/I4210107720"]},{"raw_affiliation_string":"IETR - Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique (Campus de Beaulieu B\u00e2timent 11D 263 Av.G\u00e9n\u00e9ral Leclerc-CS 74205 35042 Rennes Cedex - France)","institution_ids":["https://openalex.org/I4210100151"]}]},{"author_position":"middle","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":"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":"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)"],"raw_orcid":null,"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"]}]},{"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/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Xavier Alameda-Pineda","raw_affiliation_strings":["ROBOTLEARN - Vers des robots \u00e0 l\u2019intelligence sociale au travers de l\u2019apprentissage, de la perception et de la commande (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ROBOTLEARN - Vers des robots \u00e0 l\u2019intelligence sociale au travers de l\u2019apprentissage, de la perception et de la commande (INRIA Rh\u00f4ne-Alpes 655 avenue de l'Europe 38330 Montbonnot - France)","institution_ids":["https://openalex.org/I1326498283"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"46","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9994999766349792,"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":0.9988999962806702,"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/autoencoder","display_name":"Autoencoder","score":0.8815463781356812},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7253608703613281},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6645515561103821},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5768353343009949},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.48897993564605713},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.4682788848876953},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.43123912811279297},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.427670955657959},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4215801954269409},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4113413095474243},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4019832909107208},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3416552245616913},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.25049591064453125}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8815463781356812},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7253608703613281},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6645515561103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5768353343009949},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.48897993564605713},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.4682788848876953},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.43123912811279297},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.427670955657959},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4215801954269409},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4113413095474243},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4019832909107208},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3416552245616913},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.25049591064453125},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2021-256","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2021-256","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:HAL:hal-03295657v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03295657","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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-03295657v1","is_oa":true,"landing_page_url":"https://inria.hal.science/hal-03295657","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":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"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":36,"referenced_works":["https://openalex.org/W592244745","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1824523713","https://openalex.org/W1884859883","https://openalex.org/W1909320841","https://openalex.org/W1933340426","https://openalex.org/W1959608418","https://openalex.org/W2009086942","https://openalex.org/W2034009564","https://openalex.org/W2039844283","https://openalex.org/W2067295501","https://openalex.org/W2120575676","https://openalex.org/W2149273154","https://openalex.org/W2396566817","https://openalex.org/W2515020857","https://openalex.org/W2532494225","https://openalex.org/W2751471435","https://openalex.org/W2758785877","https://openalex.org/W2766672686","https://openalex.org/W2901552243","https://openalex.org/W2911579794","https://openalex.org/W2922391058","https://openalex.org/W2952161038","https://openalex.org/W2962691331","https://openalex.org/W2962850167","https://openalex.org/W2964232608","https://openalex.org/W2999890176","https://openalex.org/W3015214864","https://openalex.org/W3082851515","https://openalex.org/W3100968126","https://openalex.org/W3147539069","https://openalex.org/W4288089383","https://openalex.org/W4294107275","https://openalex.org/W4295312788","https://openalex.org/W4394635430"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W4309969736","https://openalex.org/W4394785709","https://openalex.org/W2953501176","https://openalex.org/W2965095304","https://openalex.org/W2470043383","https://openalex.org/W3034474024","https://openalex.org/W2770818364","https://openalex.org/W4317242571"],"abstract_inverted_index":{"Accepted":[0],"to":[1],"Interspeech":[2],"2021.":[3],"arXiv":[4],"admin":[5],"note:":[6],"text":[7],"overlap":[8],"with":[9],"arXiv:2008.12595":[10]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}