{"id":"https://openalex.org/W4415433986","doi":"https://doi.org/10.21437/interspeech.2025-437","title":"Universal Semantic Disentangled Privacy-preserving Speech Representation Learning","display_name":"Universal Semantic Disentangled Privacy-preserving Speech Representation Learning","publication_year":2025,"publication_date":"2025-08-17","ids":{"openalex":"https://openalex.org/W4415433986","doi":"https://doi.org/10.21437/interspeech.2025-437"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2025-437","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://hdl.handle.net/2117/462201","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092579799","display_name":"Biel Tura-Vecino","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Biel Tura-Vecino","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049933494","display_name":"Subhadeep Maji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Subhadeep Maji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037913405","display_name":"Aravind Varier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aravind Varier","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000405202","display_name":"Antonio Bonafonte","orcid":"https://orcid.org/0000-0002-6240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Antonio Bonafonte","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088779129","display_name":"Ivan Valles","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Valles","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026352442","display_name":"Michael J. Owen","orcid":"https://orcid.org/0000-0003-4798-0862"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael Owen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076143510","display_name":"Constantinos Papayiannis","orcid":"https://orcid.org/0000-0001-6448-3767"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Constantinos Papayiannis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018372535","display_name":"Leif Radel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leif Radel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023708721","display_name":"Grant P. Strimel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grant Strimel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021612761","display_name":"Oluwaseyi Feyisetan","orcid":"https://orcid.org/0000-0002-0786-9505"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oluwaseyi Feyisetan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027755752","display_name":"Roberto Barra-Chicote","orcid":"https://orcid.org/0000-0003-0844-7037"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Roberto Barra-Chicote","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110230355","display_name":"Ariya Rastrow","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ariya Rastrow","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034723709","display_name":"Volker Leutnant","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Volker Leutnant","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5016874926","display_name":"Trevor Wood","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Trevor Wood","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":14,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14206794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3633","last_page":"3637"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9908000230789185,"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":0.9908000230789185,"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":0.9653000235557556,"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":0.9315999746322632,"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/representation","display_name":"Representation (politics)","score":0.5210000276565552},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3783999979496002},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.33980000019073486},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.28679999709129333},{"id":"https://openalex.org/keywords/knowledge-representation-and-reasoning","display_name":"Knowledge representation and reasoning","score":0.2822999954223633}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6791999936103821},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5601000189781189},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.54830002784729},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5210000276565552},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3783999979496002},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3650999963283539},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2924000024795532},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28679999709129333},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2025-437","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2025-437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2025","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/462201","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/462201","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference lecture"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/462201","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/462201","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference lecture"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"use":[1],"of":[2],"human":[3],"speech":[4,47,57,100],"to":[5,12,16],"train":[6],"LLMs":[7],"poses":[8],"privacy":[9],"concerns":[10],"due":[11],"these":[13],"models'":[14],"ability":[15],"generate":[17],"samples":[18],"that":[19,45,66,72],"closely":[20],"resemble":[21],"artifacts":[22],"in":[23],"the":[24,36,111],"training":[25],"data.":[26],"We":[27,95],"propose":[28],"a":[29,41],"speaker":[30,64,114],"privacy-preserving":[31,50,93,107],"representation":[32,75,108],"learning":[33],"method":[34],"through":[35],"Universal":[37],"Speech":[38],"Codec":[39],"(USC),":[40],"computationally":[42],"efficient":[43],"codec":[44],"disentangles":[46],"into:":[48],"(i)":[49],"semantically":[51],"rich":[52],"representations,":[53],"capturing":[54],"content":[55],"and":[56,59,63,79,102,116],"paralinguistics,":[58],"(ii)":[60],"residual":[61],"acoustic":[62],"representations":[65],"enable":[67],"high-fidelity":[68],"reconstruction.":[69],"Evaluations":[70],"show":[71],"USC's":[73],"semantic":[74],"preserves":[76],"content,":[77],"prosody,":[78],"sentiment,":[80],"while":[81],"removing":[82],"identifiable":[83],"traits.":[84],"Additionally,":[85],"we":[86],"present":[87],"an":[88],"evaluation":[89],"methodology":[90],"for":[91],"measuring":[92],"properties.":[94],"compare":[96],"USC":[97],"against":[98],"other":[99],"codecs":[101],"demonstrate":[103],"its":[104],"effectiveness":[105],"on":[106],"learning,":[109],"showcasing":[110],"trade-offs":[112],"between":[113],"anonymization":[115],"paralinguistics":[117],"retention.1":[118]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-24T00:00:00"}
