{"id":"https://openalex.org/W4408346050","doi":"https://doi.org/10.1109/icassp49660.2025.10887683","title":"Target Speaker ASR with Whisper","display_name":"Target Speaker ASR with Whisper","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408346050","doi":"https://doi.org/10.1109/icassp49660.2025.10887683"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10887683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5114369422","display_name":"Alexander Polok","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Alexander Polok","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090369622","display_name":"Dominik Klement","orcid":null},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Dominik Klement","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014455067","display_name":"Matthew Wiesner","orcid":"https://orcid.org/0000-0001-8653-7738"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Wiesner","raw_affiliation_strings":["Johns Hopkins University,Baltimore,United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,United States of America","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014580424","display_name":"Sanjeev Khudanpur","orcid":"https://orcid.org/0000-0001-5976-0897"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjeev Khudanpur","raw_affiliation_strings":["Johns Hopkins University,Baltimore,United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Johns Hopkins University,Baltimore,United States of America","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045539248","display_name":"Ja\u0148 \u010cernock\u00fd","orcid":"https://orcid.org/0000-0002-8800-0210"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan \u010cernock\u00fd","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042273299","display_name":"Luk\u00e1\u0161 Burget","orcid":"https://orcid.org/0000-0002-4951-5908"},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Luk\u00e1\u0161 Burget","raw_affiliation_strings":["Brno University of Technology,Brno,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brno University of Technology,Brno,Czech Republic","institution_ids":["https://openalex.org/I60587646"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":33.2528,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.99706852,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"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/T13191","display_name":"Dispute Resolution and Class Actions","score":0.22300000488758087,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13191","display_name":"Dispute Resolution and Class Actions","score":0.22300000488758087,"subfield":{"id":"https://openalex.org/subfields/1408","display_name":"Strategy and Management"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10651","display_name":"IPv6, Mobility, Handover, Networks, Security","score":0.20990000665187836,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11504","display_name":"Advanced Authentication Protocols Security","score":0.19529999792575836,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8089368343353271},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.505549430847168}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8089368343353271},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.505549430847168}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10887683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10887683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W2150769028","https://openalex.org/W2164240571","https://openalex.org/W2890964092","https://openalex.org/W2963843276","https://openalex.org/W3013139777","https://openalex.org/W3154262773","https://openalex.org/W3160799772","https://openalex.org/W3207834622","https://openalex.org/W3209984917","https://openalex.org/W4372259971","https://openalex.org/W4372340947","https://openalex.org/W4372342485","https://openalex.org/W4385822321","https://openalex.org/W4385822775","https://openalex.org/W4387010481","https://openalex.org/W4389315122","https://openalex.org/W4391021675","https://openalex.org/W4392904451","https://openalex.org/W4402111631","https://openalex.org/W4402116591","https://openalex.org/W4403640495","https://openalex.org/W4408352169","https://openalex.org/W6633847657","https://openalex.org/W6741672453","https://openalex.org/W6757817989","https://openalex.org/W6769243733","https://openalex.org/W6777776875","https://openalex.org/W6847363464","https://openalex.org/W6850625674","https://openalex.org/W6852909395","https://openalex.org/W6875906937"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"We":[0,56],"propose":[1],"a":[2,61,97],"novel":[3],"approach":[4,84],"to":[5,33,41,48],"enable":[6],"the":[7,50,70,116],"use":[8],"of":[9,24,52],"large,":[10],"single-speaker":[11,76],"ASR":[12,77,81,88],"models,":[13],"such":[14],"as":[15],"Whisper,":[16],"for":[17,93],"target":[18],"speaker":[19,54,95],"ASR.":[20],"The":[21],"key":[22],"claim":[23],"this":[25],"method":[26,102],"is":[27,30],"that":[28,58],"it":[29],"much":[31],"easier":[32],"model":[34],"relative":[35],"differences":[36],"among":[37],"speakers":[38],"by":[39,89,110],"learning":[40],"condition":[42],"on":[43,115],"frame-level":[44],"diarization":[45,66,98,108],"outputs":[46],"than":[47],"learn":[49],"space":[51],"all":[53],"embeddings.":[55],"find":[57],"adding":[59],"even":[60],"single":[62],"bias":[63],"term":[64],"per":[65],"output":[67],"type":[68],"before":[69],"first":[71],"transformer":[72],"block":[73],"can":[74],"transform":[75],"models":[78],"into":[79],"target-speaker":[80],"models.":[82],"Our":[83],"also":[85],"supports":[86],"speaker-attributed":[87],"sequentially":[90],"generating":[91],"transcripts":[92],"each":[94],"in":[96],"output.":[99],"This":[100],"simplified":[101],"outperforms":[103],"baseline":[104],"speech":[105],"separation":[106],"and":[107],"cascade":[109],"12.9":[111],"%":[112],"absolute":[113],"ORC-WER":[114],"NOTSOFAR-1":[117],"dataset.":[118]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}