{"id":"https://openalex.org/W4400621987","doi":"https://doi.org/10.21437/odyssey.2024-27","title":"Automatic Voice Identification after Speech Resynthesis using PPG","display_name":"Automatic Voice Identification after Speech Resynthesis using PPG","publication_year":2024,"publication_date":"2024-06-18","ids":{"openalex":"https://openalex.org/W4400621987","doi":"https://doi.org/10.21437/odyssey.2024-27"},"language":"en","primary_location":{"id":"doi:10.21437/odyssey.2024-27","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/odyssey.2024-27","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2408.02712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092834976","display_name":"Thibault Gaudier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Thibault Gaudier","raw_affiliation_strings":["LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","LST - Equipe Language and Speech Technology (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]},{"raw_affiliation_string":"LST - Equipe Language and Speech Technology (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028709353","display_name":"Marie Tahon","orcid":"https://orcid.org/0000-0002-6782-0332"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Marie Tahon","raw_affiliation_strings":["LST - Equipe Language and Speech Technology (Avenue Laennec 72085 Le Mans cedex 9 - France)","LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LST - Equipe Language and Speech Technology (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":[]},{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002979461","display_name":"Anthony Larcher","orcid":"https://orcid.org/0000-0003-4398-0224"},"institutions":[{"id":"https://openalex.org/I4210108471","display_name":"Le Mans Universit\u00e9","ror":"https://ror.org/01mtcc283","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210108471"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Anthony Larcher","raw_affiliation_strings":["LST - Equipe Language and Speech Technology (Avenue Laennec 72085 Le Mans cedex 9 - France)","LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LST - Equipe Language and Speech Technology (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":[]},{"raw_affiliation_string":"LIUM - Laboratoire d'Informatique de l'Universit\u00e9 du Mans (Avenue Laennec 72085 Le Mans cedex 9 - France)","institution_ids":["https://openalex.org/I4210108471"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081852717","display_name":"Yannick Est\u00e8ve","orcid":"https://orcid.org/0000-0002-3656-8883"},"institutions":[{"id":"https://openalex.org/I4210119991","display_name":"Laboratoire Informatique d'Avignon","ror":"https://ror.org/02n399288","country_code":"FR","type":"facility","lineage":["https://openalex.org/I198415970","https://openalex.org/I4210119991"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Yannick Est\u00e8ve","raw_affiliation_strings":["LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LIA - Laboratoire Informatique d'Avignon (339 Chemin des Meinajaries Agroparc BP 1228 84911 Avignon cedex 9 - France)","institution_ids":["https://openalex.org/I4210119991"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5092834976"],"corresponding_institution_ids":["https://openalex.org/I4210108471"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08311753,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"187","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8557999730110168,"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":0.8557999730110168,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7389385104179382},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7380356788635254},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.6100181937217712},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4180455207824707}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7389385104179382},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7380356788635254},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.6100181937217712},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4180455207824707},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/odyssey.2024-27","is_oa":false,"landing_page_url":"http://dx.doi.org/10.21437/odyssey.2024-27","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The Speaker and Language Recognition Workshop (Odyssey 2024)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2408.02712","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.02712","pdf_url":"https://arxiv.org/pdf/2408.02712","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"pmh:oai:HAL:hal-04638686v1","is_oa":true,"landing_page_url":"https://hal.science/hal-04638686","pdf_url":"https://hal.science/hal-04638686/file/Odyssey_PPG_Conversion.pdf","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":"Speaker and Language Recognition Workshop - Odyssey, Jun 2024, Qu\u00e9bec (Canada), Canada","raw_type":"Conference papers"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2408.02712","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2408.02712","pdf_url":"https://arxiv.org/pdf/2408.02712","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.49000000953674316,"display_name":"Gender equality"}],"awards":[{"id":"https://openalex.org/G1454328438","display_name":null,"funder_award_id":"101007666","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G309983124","display_name":"Stream Learning for Multilingual Knowledge Transfer","funder_award_id":"957017","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4400621987.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["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","https://openalex.org/W114661351"],"abstract_inverted_index":{"Speech":[0],"resynthesis":[1],"is":[2,114],"a":[3,80],"generic":[4],"task":[5],"for":[6,20],"which":[7,17],"we":[8,56,92],"want":[9],"to":[10,58,102],"synthesize":[11],"audio\\nwith":[12],"another":[13],"audio":[14],"as":[15],"input,":[16],"finds":[18],"applications":[19],"media":[21],"monitors":[22],"and\\njournalists.Among":[23],"different":[24],"tasks":[25],"addressed":[26],"by":[27],"speech":[28,42],"resynthesis,":[29],"voice\\nconversion":[30],"preserves":[31,44],"the":[32,37,45,48,104,112],"linguistic":[33],"information":[34],"while":[35],"modifying":[36],"identity":[38,46],"of\\nthe":[39],"speaker,":[40],"and":[41,61,74],"edition":[43],"of":[47,72],"speaker":[49,60,97,106],"but":[50],"some\\nwords":[51],"are":[52,68,75],"modified.In":[53],"both":[54],"cases,":[55],"need":[57],"disentangle":[59],"phonetic\\ncontents":[62],"in":[63],"intermediate":[64],"representations.Phonetic":[65],"PosteriorGrams":[66],"(PPG)":[67],"a\\nframe-level":[69],"probabilistic":[70],"representation":[71],"phonemes,":[73],"usually\\nconsidered":[76],"speaker-independent.This":[77],"paper":[78],"presents":[79],"PPG-based":[81],"speech\\nresynthesis":[82],"system.A":[83],"perceptive":[84],"evaluation":[85],"assesses":[86],"that":[87,94],"it":[88],"produces":[89],"correct\\naudio":[90],"quality.Then,":[91],"demonstrate":[93],"an":[95],"automatic":[96],"verification":[98],"model\\nis":[99],"not":[100],"able":[101],"recover":[103],"source":[105],"after":[107],"re-synthesis":[108],"with":[109],"PPG,":[110],"even\\nwhen":[111],"model":[113],"trained":[115],"on":[116],"synthetic":[117],"data.\\n":[118]},"counts_by_year":[],"updated_date":"2026-06-04T09:04:59.091469","created_date":"2025-10-10T00:00:00"}
