{"id":"https://openalex.org/W4412888807","doi":"https://doi.org/10.18653/v1/2025.findings-acl.127","title":"Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation","display_name":"Eta-WavLM: Efficient Speaker Identity Removal in Self-Supervised Speech Representations Using a Simple Linear Equation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888807","doi":"https://doi.org/10.18653/v1/2025.findings-acl.127"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.127","pdf_url":"https://aclanthology.org/2025.findings-acl.127.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.127.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073805327","display_name":"G. Ruggiero","orcid":"https://orcid.org/0000-0001-6605-4739"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Giuseppe Ruggiero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009932489","display_name":"Matteo Testa","orcid":"https://orcid.org/0000-0003-2628-6433"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Testa","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114420635","display_name":"Jurgen Van de Walle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jurgen Van De Walle","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5057833935","display_name":"Luigi Di","orcid":"https://orcid.org/0000-0002-7570-637X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luigi Di Caro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14458392,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2494","last_page":"2504"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9860000014305115,"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":0.9596999883651733,"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/simple","display_name":"Simple (philosophy)","score":0.6485615968704224},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.6198610067367554},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6177238821983337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5974833369255066},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5461704134941101},{"id":"https://openalex.org/keywords/linear-prediction","display_name":"Linear prediction","score":0.5014834403991699},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41513940691947937},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3378010392189026},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.14220118522644043}],"concepts":[{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.6485615968704224},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.6198610067367554},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6177238821983337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5974833369255066},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5461704134941101},{"id":"https://openalex.org/C131109320","wikidata":"https://www.wikidata.org/wiki/Q581012","display_name":"Linear prediction","level":2,"score":0.5014834403991699},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41513940691947937},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3378010392189026},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.14220118522644043},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.127","pdf_url":"https://aclanthology.org/2025.findings-acl.127.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.127","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.127","pdf_url":"https://aclanthology.org/2025.findings-acl.127.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888807.pdf","grobid_xml":"https://content.openalex.org/works/W4412888807.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W2249138175","https://openalex.org/W4313854686","https://openalex.org/W3162054169","https://openalex.org/W1813780412","https://openalex.org/W289407349","https://openalex.org/W2368768466","https://openalex.org/W2757081366","https://openalex.org/W2640905660"],"abstract_inverted_index":{"Self-supervised":[0],"learning":[1,14],"(SSL)":[2],"has":[3],"reduced":[4],"the":[5,41],"reliance":[6],"on":[7],"expensive":[8],"labeling":[9],"in":[10,27,40],"speech":[11,50],"technologies":[12],"by":[13],"meaningful":[15],"representations":[16,30,78,110],"from":[17,34],"unannotated":[18],"data.Since":[19],"most":[20],"SSLbased":[21],"downstream":[22],"tasks":[23,104],"prioritize":[24],"content":[25,33],"information":[26,46],"speech,":[28],"ideal":[29],"should":[31],"disentangle":[32,59],"unwanted":[35],"variations":[36],"like":[37],"speaker":[38,45,60,86,95],"characteristics":[39],"SSL":[42,77],"representations.However,":[43],"removing":[44],"often":[47],"degrades":[48],"other":[49],"components,":[51,83],"and":[52,81,97],"existing":[53],"methods":[54],"either":[55],"fail":[56],"to":[57,102],"fully":[58],"identity":[61],"or":[62],"require":[63],"resourceintensive":[64],"models.In":[65],"this":[66],"paper,":[67],"we":[68],"propose":[69],"a":[70],"novel":[71],"disentanglement":[72],"method":[73],"that":[74,91],"linearly":[75],"decomposes":[76],"into":[79],"speakerspecific":[80],"speaker-independent":[82],"effectively":[84],"generating":[85],"disentangled":[87],"representations.Comprehensive":[88],"experiments":[89],"show":[90],"our":[92,109],"approach":[93],"achieves":[94],"independence":[96],"as":[98,106],"such,":[99],"when":[100],"applied":[101],"contentdriven":[103],"such":[105],"voice":[107],"conversion,":[108],"yield":[111],"significant":[112],"improvements":[113],"over":[114],"state-of-the-art":[115],"methods.":[116],"1":[117]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}