{"id":"https://openalex.org/W4416800207","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249191","title":"Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers","display_name":"Identifying Speaker Information in Feed-Forward Layers of Self-Supervised Speech Transformers","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W4416800207","doi":"https://doi.org/10.1109/apsipaasc65261.2025.11249191"},"language":null,"primary_location":{"id":"doi:10.1109/apsipaasc65261.2025.11249191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5015439080","display_name":"Tzu-Quan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tzu-Quan Lin","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hsi-Chun Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsi-Chun Cheng","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":["Graduate Institute of Communication Engineering, National Taiwan University,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate Institute of Communication Engineering, National Taiwan University,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050748634","display_name":"Hao Tang","orcid":"https://orcid.org/0000-0002-2077-1246"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Hao Tang","raw_affiliation_strings":["Centre of Speech Technology Research, University of Edinburgh,United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre of Speech Technology Research, University of Edinburgh,United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.5175,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.93781545,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"525","last_page":"530"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.34610000252723694,"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":0.34610000252723694,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.08940000087022781,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.08780000358819962,"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/encode","display_name":"ENCODE","score":0.6811000108718872},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6284999847412109},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.47119998931884766},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.4228000044822693},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.34860000014305115},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.3450999855995178}],"concepts":[{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.6811000108718872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6769000291824341},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6284999847412109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6043000221252441},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.47119998931884766},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.4228000044822693},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.34860000014305115},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.3450999855995178},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3018999993801117},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.29980000853538513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27469998598098755},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.2703000009059906},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/apsipaasc65261.2025.11249191","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipaasc65261.2025.11249191","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2150769028","https://openalex.org/W2890964092","https://openalex.org/W2964247977","https://openalex.org/W2972943112","https://openalex.org/W2993724474","https://openalex.org/W2997949714","https://openalex.org/W3015356564","https://openalex.org/W3041561163","https://openalex.org/W3173970713","https://openalex.org/W3197580070","https://openalex.org/W3198275944","https://openalex.org/W3206189675","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205460703","https://openalex.org/W4285203343","https://openalex.org/W4297841405","https://openalex.org/W4385822337","https://openalex.org/W4391021746","https://openalex.org/W4402112125","https://openalex.org/W4402112198","https://openalex.org/W4402112366","https://openalex.org/W4406461695"],"related_works":[],"abstract_inverted_index":{"In":[0,25],"recent":[1],"years,":[2],"the":[3,36],"impact":[4],"of":[5,53],"self-supervised":[6,54],"speech":[7],"Transformers":[8],"has":[9,17],"extended":[10],"to":[11,65],"speaker-related":[12,92],"applications.":[13],"However,":[14],"little":[15],"research":[16],"explored":[18],"how":[19],"these":[20,62,82],"models":[21],"encode":[22],"speaker":[23,43,100],"information.":[24,44,101],"this":[26,30],"work,":[27],"we":[28,46,86],"address":[29],"gap":[31],"by":[32],"identifying":[33,75],"neurons":[34,48,76,83],"in":[35,98],"feed-forward":[37],"layers":[38],"that":[39,61,77],"are":[40],"correlated":[41],"with":[42,50],"Specifically,":[45],"analyze":[47],"associated":[49],"k-means":[51],"clusters":[52,63],"features":[55],"and":[56,68],"i-vectors.":[57],"Our":[58],"analysis":[59],"reveals":[60],"correspond":[64],"broad":[66],"phonetic":[67],"gender":[69],"classes,":[70],"making":[71],"them":[72],"suitable":[73],"for":[74],"represent":[78],"speakers.":[79],"By":[80],"protecting":[81],"during":[84],"pruning,":[85],"can":[87],"significantly":[88],"preserve":[89],"performance":[90],"on":[91],"task,":[93],"demonstrating":[94],"their":[95],"crucial":[96],"role":[97],"encoding":[99]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-28T00:00:00"}