{"id":"https://openalex.org/W4224925034","doi":"https://doi.org/10.1109/icassp43922.2022.9747011","title":"Dispeech: A Synthetic Toy Dataset for Speech Disentangling","display_name":"Dispeech: A Synthetic Toy Dataset for Speech Disentangling","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224925034","doi":"https://doi.org/10.1109/icassp43922.2022.9747011"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747011","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042878348","display_name":"Olivier Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]},{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR","US"],"is_corresponding":true,"raw_author_name":"Olivier Zhang","raw_affiliation_strings":["Orange Innovation,France","Expressiveness in Human Centered Data/Media"],"affiliations":[{"raw_affiliation_string":"Orange Innovation,France","institution_ids":["https://openalex.org/I19370010"]},{"raw_affiliation_string":"Expressiveness in Human Centered Data/Media","institution_ids":["https://openalex.org/I4210142372"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023246311","display_name":"Nicolas Gengembre","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Nicolas Gengembre","raw_affiliation_strings":["Orange Innovation,France"],"affiliations":[{"raw_affiliation_string":"Orange Innovation,France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010074905","display_name":"Olivier Le Blouch","orcid":null},"institutions":[{"id":"https://openalex.org/I19370010","display_name":"Orange (France)","ror":"https://ror.org/035j0tq82","country_code":"FR","type":"company","lineage":["https://openalex.org/I19370010"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Olivier Le Blouch","raw_affiliation_strings":["Orange Innovation,France"],"affiliations":[{"raw_affiliation_string":"Orange Innovation,France","institution_ids":["https://openalex.org/I19370010"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003200234","display_name":"Damien Lolive","orcid":"https://orcid.org/0000-0002-1110-5444"},"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/I4210142372","display_name":"Human Media","ror":"https://ror.org/04072nk43","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210142372"]},{"id":"https://openalex.org/I2802519937","display_name":"Institut de Recherche en Informatique et Syst\u00e8mes Al\u00e9atoires","ror":"https://ror.org/00myn0z94","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I205703379","https://openalex.org/I2802204017","https://openalex.org/I2802519937","https://openalex.org/I28221208","https://openalex.org/I4210127572","https://openalex.org/I4210159245","https://openalex.org/I56067802"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR","US"],"is_corresponding":false,"raw_author_name":"Damien Lolive","raw_affiliation_strings":["Université de Rennes 1,CNRS, IRISA,Lannion,France","Expressiveness in Human Centered Data/Media"],"affiliations":[{"raw_affiliation_string":"Université de Rennes 1,CNRS, IRISA,Lannion,France","institution_ids":["https://openalex.org/I56067802","https://openalex.org/I2802519937","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"Expressiveness in Human Centered Data/Media","institution_ids":["https://openalex.org/I4210142372"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5042878348"],"corresponding_institution_ids":["https://openalex.org/I19370010","https://openalex.org/I4210142372"],"apc_list":null,"apc_paid":null,"fwci":0.2458,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34628752,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"8557","last_page":"8561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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":0.9994999766349792,"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":0.998199999332428,"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/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":0.6523625254631042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5190656781196594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44082069396972656},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.34857606887817383}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6523625254631042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5190656781196594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44082069396972656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34857606887817383}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747011","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747011","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-03975832v1","is_oa":false,"landing_page_url":"https://hal.science/hal-03975832","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://2022.ieeeicassp.org/","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1959608418","https://openalex.org/W1999885698","https://openalex.org/W2134557905","https://openalex.org/W2184218725","https://openalex.org/W2396366106","https://openalex.org/W2752796333","https://openalex.org/W2785519580","https://openalex.org/W2785961484","https://openalex.org/W2786385136","https://openalex.org/W2950662112","https://openalex.org/W2951428711","https://openalex.org/W2962780374","https://openalex.org/W2963226019","https://openalex.org/W2963799213","https://openalex.org/W2964127395","https://openalex.org/W3015212100","https://openalex.org/W3015699566","https://openalex.org/W3045863681","https://openalex.org/W3112497262","https://openalex.org/W3160584619","https://openalex.org/W4287551786","https://openalex.org/W4295112158","https://openalex.org/W6640963894","https://openalex.org/W6686131816","https://openalex.org/W6712235671","https://openalex.org/W6718140377","https://openalex.org/W6745687250","https://openalex.org/W6747786891","https://openalex.org/W6748223763","https://openalex.org/W6748391871","https://openalex.org/W6748445624","https://openalex.org/W6756663807","https://openalex.org/W6762931136","https://openalex.org/W6781009690","https://openalex.org/W6955712162"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Recently,":[0],"a":[1,39,51,64,113],"growing":[2],"interest":[3],"in":[4],"unsupervised":[5],"learning":[6],"of":[7,42,66,94,106,126],"disentangled":[8],"representations":[9],"has":[10],"been":[11,28],"observed,":[12],"with":[13,69,81],"successful":[14],"applications":[15],"to":[16,30,54,78,97,111,115,133,144],"both":[17],"synthetic":[18,44],"and":[19,57,88,102],"real":[20,129],"data.":[21],"In":[22,109],"speech":[23,67,117],"processing,":[24],"such":[25],"methods":[26],"have":[27,38],"able":[29],"disentangle":[31,98],"speakers\u2019":[32],"attributes":[33],"from":[34],"verbal":[35],"content.":[36],"To":[37,137],"better":[40],"understanding":[41],"disentanglement,":[43],"data":[45],"is":[46,76,132],"necessary,":[47],"as":[48],"it":[49,143],"provides":[50],"controllable":[52],"framework":[53],"train":[55],"models":[56],"evaluate":[58],"disentanglement.":[59],"Thus,":[60],"we":[61,141],"introduce":[62],"diSpeech,":[63],"corpus":[65],"synthesized":[68,80],"the":[70,92,104,123],"Klatt":[71],"synthesizer.":[72],"Its":[73],"first":[74],"version":[75],"constrained":[77],"vowels":[79],"5":[82],"generative":[83,100],"factors":[84,101],"relying":[85],"on":[86,128],"pitch":[87],"formants.":[89],"Experiments":[90],"show":[91],"ability":[93],"variational":[95],"autoencoders":[96],"these":[99],"assess":[103],"reliability":[105],"disentanglement":[107,118,127],"metrics.":[108],"addition":[110],"provide":[112],"support":[114],"benchmark":[116],"methods,":[119],"diSpeech":[120],"also":[121],"enables":[122],"objective":[124],"evaluation":[125],"speech,":[130],"which":[131],"our":[134],"knowledge":[135],"unprecedented.":[136],"illustrate":[138],"this":[139],"methodology,":[140],"apply":[142],"TIMIT\u2019s":[145],"isolated":[146],"vowels.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}