{"id":"https://openalex.org/W4392904451","doi":"https://doi.org/10.1109/icassp48485.2024.10447492","title":"Extending Whisper with Prompt Tuning to Target-Speaker ASR","display_name":"Extending Whisper with Prompt Tuning to Target-Speaker ASR","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904451","doi":"https://doi.org/10.1109/icassp48485.2024.10447492"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10447492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447492","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":"conference-paper","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/A5064804308","display_name":"Hao Ma","orcid":"https://orcid.org/0000-0001-9593-4102"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Ma","raw_affiliation_strings":["Shandong University,School of Information Science and Engineering,Qingdao,China","School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075223216","display_name":"Zhiyuan Peng","orcid":"https://orcid.org/0000-0002-9870-4422"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiyuan Peng","raw_affiliation_strings":["North Carolina State University,Department of Computer Science,North Carolina,USA","Department of Computer Science, North Carolina State University, North Carolina, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University,Department of Computer Science,North Carolina,USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Department of Computer Science, North Carolina State University, North Carolina, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056971813","display_name":"Mingjie Shao","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Shao","raw_affiliation_strings":["Shandong University,School of Information Science and Engineering,Qingdao,China","School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100313293","display_name":"Jing Li","orcid":"https://orcid.org/0000-0002-8446-6072"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jing Li","raw_affiliation_strings":["Shandong Normal University,School of Journalism and Communication,Jinan,China","School of Journalism and Communication, Shandong Normal University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong Normal University,School of Journalism and Communication,Jinan,China","institution_ids":["https://openalex.org/I28006308"]},{"raw_affiliation_string":"School of Journalism and Communication, Shandong Normal University, Jinan, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100763011","display_name":"Ju Liu","orcid":"https://orcid.org/0000-0003-3160-9233"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ju Liu","raw_affiliation_strings":["Shandong University,School of Information Science and Engineering,Qingdao,China","School of Information Science and Engineering, Shandong University, Qingdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shandong University,School of Information Science and Engineering,Qingdao,China","institution_ids":["https://openalex.org/I154099455"]},{"raw_affiliation_string":"School of Information Science and Engineering, Shandong University, Qingdao, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12516","last_page":"12520"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9962999820709229,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9940999746322632,"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/computer-science","display_name":"Computer science","score":0.8767281770706177},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.707452654838562},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.6482189297676086},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6047865152359009},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4419274926185608},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.42118164896965027},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3943387567996979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8767281770706177},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.707452654838562},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.6482189297676086},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6047865152359009},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4419274926185608},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.42118164896965027},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3943387567996979},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10447492","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10447492","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":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337504","display_name":"Research and Development","ror":"https://ror.org/027s68j25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W2460742184","https://openalex.org/W2748488820","https://openalex.org/W2963843276","https://openalex.org/W2972541922","https://openalex.org/W2995181338","https://openalex.org/W3027008958","https://openalex.org/W3094821064","https://openalex.org/W3098267758","https://openalex.org/W3154262773","https://openalex.org/W3174770825","https://openalex.org/W3196194966","https://openalex.org/W3205270560","https://openalex.org/W4205991051","https://openalex.org/W4322825254","https://openalex.org/W4372259971","https://openalex.org/W4372342485","https://openalex.org/W4372349800","https://openalex.org/W4385570529","https://openalex.org/W4385822321","https://openalex.org/W4385822775","https://openalex.org/W4385822890","https://openalex.org/W4403635980","https://openalex.org/W6757817989","https://openalex.org/W6759579507","https://openalex.org/W6777776875","https://openalex.org/W6778883912","https://openalex.org/W6796581206","https://openalex.org/W6802386650","https://openalex.org/W6847363464","https://openalex.org/W6849622896","https://openalex.org/W6850477478"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W1491159402","https://openalex.org/W4297807400","https://openalex.org/W4313854686","https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W1509309911","https://openalex.org/W1599425004","https://openalex.org/W2118860825","https://openalex.org/W2096510939"],"abstract_inverted_index":{"Target-speaker":[0],"automatic":[1],"speech":[2,10],"recognition":[3],"(ASR)":[4],"aims":[5],"to":[6,39,46,59,67,94],"transcribe":[7],"the":[8,21,109,127],"desired":[9],"of":[11,20,70,104],"a":[12,35,55,62],"target":[13],"speaker":[14],"from":[15,30],"multi-talker":[16],"overlapped":[17],"utterances.":[18],"Most":[19],"existing":[22],"target-speaker":[23,124],"ASR":[24,65],"(TS-ASR)":[25],"methods":[26],"involve":[27],"either":[28],"training":[29,41,97],"scratch":[31],"or":[32],"fully":[33],"finetuning":[34],"pre-trained":[36],"model,":[37,66],"leading":[38],"significant":[40],"costs":[42],"and":[43,80,118,131],"becoming":[44],"inapplicable":[45],"large":[47],"foundation":[48],"models.":[49],"This":[50],"work":[51],"leverages":[52],"prompt":[53,71,88],"tuning,":[54],"parameter-efficient":[56],"fine-tuning":[57],"approach,":[58],"extend":[60],"Whisper,":[61],"large-scale":[63],"single-talker":[64],"TS-ASR.":[68,83],"Variants":[69],"tuning":[72,89],"approaches":[73,98],"along":[74],"with":[75],"their":[76],"configurations":[77],"are":[78,121],"explored":[79],"optimized":[81],"for":[82],"Experimental":[84],"results":[85],"show":[86],"that":[87],"can":[90],"achieve":[91],"performance":[92],"comparable":[93],"state-of-the-art":[95],"full":[96],"while":[99],"only":[100],"requiring":[101],"about":[102],"1%":[103],"task-specific":[105],"model":[106],"parameters.":[107],"Notably,":[108],"original":[110],"Whisper\u2019s":[111],"features,":[112],"such":[113],"as":[114],"inverse":[115],"text":[116],"normalization":[117],"timestamp":[119],"tagging,":[120],"retained":[122],"in":[123],"ASR,":[125],"keeping":[126],"generated":[128],"transcriptions":[129],"natural":[130],"informative.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
