{"id":"https://openalex.org/W4392902886","doi":"https://doi.org/10.1109/icassp48485.2024.10447795","title":"Dual Parameter-Efficient Fine-Tuning for Speaker Representation Via Speaker Prompt Tuning and Adapters","display_name":"Dual Parameter-Efficient Fine-Tuning for Speaker Representation Via Speaker Prompt Tuning and Adapters","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902886","doi":"https://doi.org/10.1109/icassp48485.2024.10447795"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5100356635","display_name":"Zhe Li","orcid":"https://orcid.org/0000-0002-0519-7434"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Zhe Li","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019458385","display_name":"Helen Meng","orcid":"https://orcid.org/0000-0002-4427-3532"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Helen Mei-Ling Meng","raw_affiliation_strings":["The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management","Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong"],"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,Department of Systems Engineering and Engineering Management","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Department of Systems Engineering and Engineering Management, The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100356635"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":2.9096,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.91490719,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10751","last_page":"10755"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9990000128746033,"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":0.9983999729156494,"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/computer-science","display_name":"Computer science","score":0.7948585748672485},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.7191935777664185},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5272226333618164},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4993751049041748},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.486606240272522},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4826708137989044},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.45118197798728943},{"id":"https://openalex.org/keywords/extractor","display_name":"Extractor","score":0.4310040771961212},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4221421480178833},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.411480575799942},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38572418689727783},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38447242975234985},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12340420484542847},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.09817564487457275},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07741507887840271}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7948585748672485},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.7191935777664185},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5272226333618164},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4993751049041748},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.486606240272522},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4826708137989044},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.45118197798728943},{"id":"https://openalex.org/C117978034","wikidata":"https://www.wikidata.org/wiki/Q5422192","display_name":"Extractor","level":2,"score":0.4310040771961212},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4221421480178833},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.411480575799942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38572418689727783},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38447242975234985},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12340420484542847},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.09817564487457275},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07741507887840271},{"id":"https://openalex.org/C21880701","wikidata":"https://www.wikidata.org/wiki/Q2144042","display_name":"Process engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2969985801","https://openalex.org/W3024869864","https://openalex.org/W3094374485","https://openalex.org/W3174770825","https://openalex.org/W3206252155","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4205991051","https://openalex.org/W4212774754","https://openalex.org/W4226162428","https://openalex.org/W4319862271","https://openalex.org/W4322825254","https://openalex.org/W4372266902","https://openalex.org/W4372270069","https://openalex.org/W4385822760","https://openalex.org/W4385822890","https://openalex.org/W6759579507","https://openalex.org/W6780218876","https://openalex.org/W6796581206","https://openalex.org/W6847363464","https://openalex.org/W6850477478"],"related_works":["https://openalex.org/W2133028525","https://openalex.org/W4229060448","https://openalex.org/W4306381730","https://openalex.org/W2981692913","https://openalex.org/W3044188621","https://openalex.org/W3184035966","https://openalex.org/W2485605994","https://openalex.org/W2160602540","https://openalex.org/W4385571108","https://openalex.org/W4200251711"],"abstract_inverted_index":{"Fine-tuning":[0],"a":[1,10,54,93],"pre-trained":[2],"Transformer":[3,71,120],"model":[4,160],"(PTM)":[5],"for":[6,142],"speech":[7],"applications":[8],"in":[9,26,101],"parameter-efficient":[11,32],"manner":[12],"offers":[13],"the":[14,22,37,41,49,58,63,89,102,106,119,129,134,143,163,167],"dual":[15],"benefits":[16],"of":[17,66,92,162],"reducing":[18],"memory":[19],"and":[20,57,110,122,152,158],"leveraging":[21],"rich":[23],"feature":[24,55,67,99],"representations":[25],"massive":[27],"unlabeled":[28],"datasets.":[29],"However,":[30],"existing":[31,168],"fine-tuning":[33],"approaches":[34],"either":[35],"adapt":[36],"classification":[38],"head":[39],"or":[40],"whole":[42],"PTM.":[43,94],"The":[44,95],"former":[45],"is":[46,51],"unsuitable":[47],"when":[48],"PTM":[50,131],"used":[52],"as":[53],"extractor,":[56],"latter":[59],"does":[60],"not":[61],"leverage":[62],"different":[64,70],"degrees":[65],"abstraction":[68],"at":[69],"layers.":[72],"We":[73],"propose":[74],"two":[75],"solutions":[76],"to":[77,87,132,138],"address":[78],"these":[79],"limitations.":[80],"First,":[81],"we":[82,114],"apply":[83],"speaker":[84,98,103,111,147],"prompt":[85,109],"tuning":[86,96],"update":[88],"task-specific":[90],"embeddings":[91,104],"enhances":[97],"relevance":[100],"through":[105],"cross-attention":[107],"between":[108],"features.":[112],"Second,":[113],"insert":[115],"adapter":[116],"blocks":[117],"into":[118],"encoders":[121],"their":[123],"outputs.":[124],"This":[125],"novel":[126],"arrangement":[127],"enables":[128],"fine-tuned":[130],"determine":[133],"most":[135],"suitable":[136],"layers":[137],"extract":[139],"relevant":[140],"information":[141],"downstream":[144],"task.":[145],"Extensive":[146],"verification":[148],"experiments":[149],"on":[150],"Voxceleb":[151],"CU-MARVEL":[153],"demonstrate":[154],"higher":[155],"parameter":[156],"efficiency":[157],"better":[159],"adaptability":[161],"proposed":[164],"methods":[165],"than":[166],"ones.":[169]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}