{"id":"https://openalex.org/W4416250686","doi":"https://doi.org/10.1109/waspaa66052.2025.11230949","title":"Contrastive Representation Learning for Privacy-Preserving Fine-Tuning of Audio-Visual Speech Recognition","display_name":"Contrastive Representation Learning for Privacy-Preserving Fine-Tuning of Audio-Visual Speech Recognition","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W4416250686","doi":"https://doi.org/10.1109/waspaa66052.2025.11230949"},"language":null,"primary_location":{"id":"doi:10.1109/waspaa66052.2025.11230949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","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/A5030293327","display_name":"Luca Becker","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Luca Becker","raw_affiliation_strings":["Ruhr-Universität Bochum,Institute of Communication Acoustics,Bochum,Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr-Universität Bochum,Institute of Communication Acoustics,Bochum,Germany","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064880163","display_name":"Rainer Martin","orcid":"https://orcid.org/0000-0002-9587-4215"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rainer Martin","raw_affiliation_strings":["Ruhr-Universität Bochum,Institute of Communication Acoustics,Bochum,Germany"],"affiliations":[{"raw_affiliation_string":"Ruhr-Universität Bochum,Institute of Communication Acoustics,Bochum,Germany","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5030293327"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41898208,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.6175000071525574,"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":0.6175000071525574,"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":0.3050999939441681,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.012500000186264515,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/word-error-rate","display_name":"Word error rate","score":0.5975000262260437},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.5551000237464905},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.519599974155426},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.445499986410141},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.42309999465942383},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4174000024795532},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3831000030040741}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7016000151634216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6840000152587891},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5975000262260437},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.5551000237464905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5406000018119812},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.519599974155426},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.445499986410141},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.42309999465942383},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4174000024795532},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3977999985218048},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C42747912","wikidata":"https://www.wikidata.org/wiki/Q1048447","display_name":"Multiplicative function","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.32359999418258667},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.26649999618530273},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2587999999523163}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa66052.2025.11230949","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa66052.2025.11230949","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2132172731","https://openalex.org/W2760103357","https://openalex.org/W2784163702","https://openalex.org/W2808631503","https://openalex.org/W2911978475","https://openalex.org/W3156636935","https://openalex.org/W3200431187","https://openalex.org/W4205228770","https://openalex.org/W4385245566","https://openalex.org/W4385822729","https://openalex.org/W4400527955","https://openalex.org/W4402660094","https://openalex.org/W4408355320"],"related_works":[],"abstract_inverted_index":{"In":[0],"this":[1,35],"work,":[2],"we":[3],"propose":[4],"a":[5,26,68,127],"novel":[6],"approach":[7,106],"towards":[8],"privacy-preserving":[9,142],"audio-visual":[10,129],"speech":[11],"recognition":[12],"(AV-ASR).":[13],"We":[14,54],"apply":[15],"feature-wise":[16],"additive":[17],"and":[18,30,64,101],"multiplicative":[19],"masks":[20,40],"to":[21,43,90],"the":[22,56,61,82,88,96,136],"latent":[23],"embeddings":[24],"of":[25,34,81,92,138],"pre-trained":[27],"AV-ASR":[28,143],"model":[29,36],"fine-tune":[31],"subsequent":[32],"layers":[33],"using":[37],"AdaLoRA.":[38],"The":[39,74],"are":[41],"trained":[42],"preserve":[44],"linguistic":[45],"content":[46],"necessary":[47],"for":[48,141,144],"ASR":[49],"while":[50,85,113],"degrading":[51],"speaker-discriminative":[52],"cues.":[53],"derive":[55],"masking":[57],"mechanism":[58],"directly":[59],"from":[60,95],"sequential":[62],"input":[63],"optimize":[65],"it":[66],"via":[67],"contrastive":[69,139],"representation":[70],"learning":[71],"(CRL)":[72],"objective.":[73],"method":[75],"closely":[76],"aggregates":[77],"slightly":[78],"perturbed":[79],"representations":[80,91],"same":[83,97],"utterance":[84],"simultaneously":[86],"increasing":[87],"distance":[89],"different":[93],"utterances":[94],"speaker.Experiments":[98],"on":[99],"LRS3":[100],"VoxCeleb2":[102],"show":[103],"that":[104],"our":[105],"maintains":[107],"competitive":[108],"word":[109],"error":[110],"rates":[111],"(WER)":[112],"significantly":[114],"reducing":[115],"speaker":[116,130],"identification":[117],"performance,":[118],"as":[119],"measured":[120],"by":[121],"Equal":[122],"Error":[123],"Rate":[124],"(EER)":[125],"under":[126],"strong":[128],"verification":[131],"attack.":[132],"These":[133],"results":[134],"demonstrate":[135],"potential":[137],"fine-tuning":[140],"edge":[145],"devices.":[146]},"counts_by_year":[],"updated_date":"2026-04-09T08:11:56.329763","created_date":"2025-11-14T00:00:00"}