{"id":"https://openalex.org/W4391287394","doi":"https://doi.org/10.1109/icasspw62465.2024.10669904","title":"Exploring the Multidimensional Representation of Unidimensional Speech Acoustic Parameters Extracted by Deep Unsupervised Models","display_name":"Exploring the Multidimensional Representation of Unidimensional Speech Acoustic Parameters Extracted by Deep Unsupervised Models","publication_year":2024,"publication_date":"2024-04-14","ids":{"openalex":"https://openalex.org/W4391287394","doi":"https://doi.org/10.1109/icasspw62465.2024.10669904"},"language":"en","primary_location":{"id":"doi:10.1109/icasspw62465.2024.10669904","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10669904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hal.science/hal-04683650/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093246598","display_name":"Maxime Jacquelin","orcid":null},"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"]},{"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":"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"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Maxime Jacquelin","raw_affiliation_strings":["Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I1294671590","https://openalex.org/I899635006","https://openalex.org/I106785703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047376365","display_name":"Ma\u00ebva Garnier","orcid":"https://orcid.org/0000-0001-9454-3820"},"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/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/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"]},{"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":"Ma\u00ebva Garnier","raw_affiliation_strings":["Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I1294671590","https://openalex.org/I899635006","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":[{"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/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/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"]},{"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"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Laurent Girin","raw_affiliation_strings":["Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I1294671590","https://openalex.org/I899635006","https://openalex.org/I106785703"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111119672","display_name":"R\u00e9my Vincent","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R\u00e9my Vincent","raw_affiliation_strings":["Vogo,Bernin,France,F-38190"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vogo,Bernin,France,F-38190","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013177566","display_name":"Olivier Perrotin","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"]},{"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/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":"Olivier Perrotin","raw_affiliation_strings":["Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Univ. Grenoble Alpes, CNRS, Grenoble INP, GIPSA-Lab,Grenoble,France,F-38000","institution_ids":["https://openalex.org/I4210124956","https://openalex.org/I1294671590","https://openalex.org/I899635006","https://openalex.org/I106785703"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5093246598"],"corresponding_institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210124956","https://openalex.org/I899635006"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00756577,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"858","last_page":"862"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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":0.707526683807373},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6610236167907715},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5403788685798645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5165151953697205},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4704277515411377},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32046979665756226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.707526683807373},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6610236167907715},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5403788685798645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5165151953697205},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4704277515411377},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32046979665756226},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icasspw62465.2024.10669904","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icasspw62465.2024.10669904","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04683650v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04683650","pdf_url":"https://hal.science/hal-04683650/document","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://xai-sa-workshop.github.io/Home.html","raw_type":"Conference papers"},{"id":"pmh:oai:HAL:hal-04416200v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04416200","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":"Journ\u00e9e commune AFIA-TLH / AFCP \u2013 \u201cExtraction de connaissances interpr\u00e9tables pour l\u2019\u00e9tude de la communication parl\u00e9e\u201d, AFIA-TLH; AFCP, Dec 2023, Avignon, France","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04683650v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04683650","pdf_url":"https://hal.science/hal-04683650/document","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://xai-sa-workshop.github.io/Home.html","raw_type":"Conference papers"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6499999761581421,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4391287394.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1875231349","https://openalex.org/W1984818181","https://openalex.org/W2061349560","https://openalex.org/W2090042521","https://openalex.org/W2515020857","https://openalex.org/W2752796333","https://openalex.org/W2883879995","https://openalex.org/W2904459034","https://openalex.org/W2962850167","https://openalex.org/W2963830550","https://openalex.org/W2972699445","https://openalex.org/W2972921407","https://openalex.org/W2998572311","https://openalex.org/W3015935472","https://openalex.org/W3026640763","https://openalex.org/W3140429000","https://openalex.org/W3194172310","https://openalex.org/W3209059054","https://openalex.org/W4206319965","https://openalex.org/W4212774754","https://openalex.org/W4213428484","https://openalex.org/W4225272861","https://openalex.org/W4296069362","https://openalex.org/W4297841537","https://openalex.org/W4313146578","https://openalex.org/W4394671563","https://openalex.org/W6631190155","https://openalex.org/W6639350448","https://openalex.org/W6640963894","https://openalex.org/W6750489868","https://openalex.org/W6772349387","https://openalex.org/W6773240189","https://openalex.org/W6780218876","https://openalex.org/W6790356757","https://openalex.org/W6838662218"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W1983629434","https://openalex.org/W2055929693","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Understanding":[0],"the":[1,28,56,79,99,111,118,133,137,140,148],"latent":[2,47,67,80,107],"representation":[3],"of":[4,24,30,32,58,82,117,139,154],"speech":[5,34],"obtained":[6],"by":[7,65,104],"a":[8,13,45,72,151],"deep":[9,46],"unsupervised":[10],"model":[11],"is":[12,51,62,102,113],"key":[14],"to":[15,150],"powerful":[16],"signal":[17],"analysis,":[18],"transformation,":[19],"and":[20,143],"generation.":[21],"A":[22],"number":[23],"studies":[25],"have":[26,131],"identified":[27,132],"directions":[29,134],"variation":[31,57,138],"individual":[33],"acoustic":[35,94,119],"features":[36],"such":[37,59,155],"as":[38],"fundamental":[39],"frequency":[40,43],"or":[41],"formant":[42],"in":[44,78,98,123],"space,":[48],"but":[49],"it":[50],"not":[52],"well":[53],"understood":[54],"why":[55],"one-dimensional":[60],"feature":[61,120,141],"often":[63],"explained":[64],"multiple":[66],"dimensions.":[68,125],"This":[69],"paper":[70],"proposes":[71],"methodology":[73],"for":[74,92],"interpreting":[75],"these":[76],"dimensions,":[77],"space":[81,108],"variational":[83],"autoencoders":[84],"trained":[85],"on":[86],"multi-speaker":[87],"datasets.":[88],"We":[89],"show":[90],"that":[91,127,135],"each":[93],"feature,":[95],"its":[96],"distribution":[97,112],"training":[100],"set":[101],"encoded":[103,122],"one":[105],"dedicated":[106],"direction.":[109],"When":[110],"multimodal,":[114],"different":[115],"modes":[116],"are":[121],"separate":[124],"In":[126],"case,":[128],"we":[129],"also":[130],"explain":[136],"within":[142],"across":[144],"modes,":[145],"which":[146],"paves":[147],"way":[149],"finer":[152],"control":[153],"models.":[156]},"counts_by_year":[],"updated_date":"2026-05-07T13:39:58.223016","created_date":"2025-10-10T00:00:00"}