{"id":"https://openalex.org/W4392909895","doi":"https://doi.org/10.1109/icassp48485.2024.10446072","title":"Prompt-Driven Target Speech Diarization","display_name":"Prompt-Driven Target Speech Diarization","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909895","doi":"https://doi.org/10.1109/icassp48485.2024.10446072"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446072","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/A5016187230","display_name":"Yidi Jiang","orcid":"https://orcid.org/0000-0001-9013-0869"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yidi Jiang","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101416769","display_name":"Zhengyang Chen","orcid":"https://orcid.org/0000-0003-1293-8146"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhengyang Chen","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026034735","display_name":"Ruijie Tao","orcid":"https://orcid.org/0000-0003-0021-5661"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ruijie Tao","raw_affiliation_strings":["National University of Singapore,Singapore","National University of Singapore, Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044738402","display_name":"Liqun Deng","orcid":"https://orcid.org/0009-0006-7242-0794"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":["Huawei Noah&#x2019;s Ark Lab,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah&#x2019;s Ark Lab,China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100341993","display_name":"Yanmin Qian","orcid":"https://orcid.org/0000-0002-0314-3790"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanmin Qian","raw_affiliation_strings":["Shanghai Jiao Tong University,China","Shanghai Jiao Tong University, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University,China","institution_ids":["https://openalex.org/I183067930"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5032690182","display_name":"Haizhou Li","orcid":"https://orcid.org/0000-0001-9158-9401"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]},{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Haizhou Li","raw_affiliation_strings":["The Chinese University of Hong Kong,School of Data Science,Shenzhen,China","Shenzhen Research Institute of Big Data, Shenzhen, China","National University of Singapore, Singapore","School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong,School of Data Science,Shenzhen,China","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Shenzhen Research Institute of Big Data, Shenzhen, China","institution_ids":["https://openalex.org/I4210099586"]},{"raw_affiliation_string":"National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"School of Data Science, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"11086","last_page":"11090"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9878000020980835,"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":0.9878000020980835,"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":0.6884937882423401},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5640377402305603},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5552055835723877},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.1704462170600891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6884937882423401},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5640377402305603},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5552055835723877},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.1704462170600891}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446072","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446072","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":[{"score":0.7699999809265137,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[{"id":"https://openalex.org/G2799040894","display_name":null,"funder_award_id":"62271432","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5088964179","display_name":null,"funder_award_id":"T00120220002","funder_id":"https://openalex.org/F4320331102","funder_display_name":"Shenzhen Research Institute of Big Data"}],"funders":[{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320331102","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89"},{"id":"https://openalex.org/F4320333998","display_name":"Shenzhen Research Institute, City University of Hong Kong","ror":"https://ror.org/00xc0ma20"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1991139021","https://openalex.org/W2001571181","https://openalex.org/W2082183045","https://openalex.org/W2972449503","https://openalex.org/W3015598461","https://openalex.org/W3015780472","https://openalex.org/W3016361963","https://openalex.org/W3024869864","https://openalex.org/W3025260599","https://openalex.org/W3095212884","https://openalex.org/W3097653961","https://openalex.org/W3103434036","https://openalex.org/W3197326126","https://openalex.org/W3198827946","https://openalex.org/W3209984917","https://openalex.org/W4205991051","https://openalex.org/W4224871700","https://openalex.org/W4285108271","https://openalex.org/W4285819380","https://openalex.org/W4295365513","https://openalex.org/W4296069305","https://openalex.org/W4372267289","https://openalex.org/W4375868885","https://openalex.org/W4385245566","https://openalex.org/W4385822320","https://openalex.org/W4385822391","https://openalex.org/W4385822749","https://openalex.org/W4386083031","https://openalex.org/W4390874575","https://openalex.org/W4391021638","https://openalex.org/W4392902746","https://openalex.org/W4394744939","https://openalex.org/W4402778510","https://openalex.org/W6857495872","https://openalex.org/W6859383537"],"related_works":["https://openalex.org/W4389984014","https://openalex.org/W2144208207","https://openalex.org/W2111874347","https://openalex.org/W3120512183","https://openalex.org/W2118860825","https://openalex.org/W1509309911","https://openalex.org/W2096510939","https://openalex.org/W2041797852","https://openalex.org/W1940231550","https://openalex.org/W1813780412"],"abstract_inverted_index":{"We":[0,21,45,62],"introduce":[1],"a":[2,23,119],"novel":[3],"task":[4],"named":[5],"\u2018target":[6],"speech":[7,41,71,92,129],"diarization\u2019,":[8],"which":[9,56],"seeks":[10],"to":[11,103],"determine":[12],"\u2018when":[13],"target":[14,40,70,86,128],"event":[15],"occurred\u2019":[16],"within":[17],"an":[18],"audio":[19],"signal.":[20],"devise":[22],"neural":[24],"architecture":[25],"called":[26],"Prompt-driven":[27],"Target":[28],"Speech":[29],"Diarization":[30],"(PTSD),":[31],"that":[32,37,64],"works":[33],"with":[34],"diverse":[35],"prompts":[36],"specify":[38],"the":[39,60,65],"events":[42],"of":[43],"interest.":[44],"train":[46],"and":[47,53,94,112,122],"evaluate":[48],"PTSD":[49,99],"using":[50],"sim2spk,":[51],"sim3spk":[52],"sim4spk":[54],"datasets,":[55],"are":[57],"derived":[58],"from":[59],"Librispeech.":[61],"show":[63],"proposed":[66],"framework":[67,75],"accurately":[68],"localizes":[69],"events.":[72],"Furthermore,":[73],"our":[74],"exhibits":[76],"versatility":[77],"through":[78],"its":[79],"impressive":[80],"performance":[81,102],"in":[82],"three":[83],"diarization-related":[84],"tasks:":[85],"speaker":[87],"voice":[88],"activity":[89],"detection,":[90],"overlapped":[91],"detection":[93],"gender":[95],"diarization.":[96],"In":[97],"particular,":[98],"achieves":[100],"comparable":[101],"specialized":[104],"models":[105],"across":[106],"these":[107],"tasks":[108],"on":[109],"both":[110],"real":[111],"simulated":[113],"data.":[114],"This":[115],"work":[116],"serves":[117],"as":[118],"reference":[120],"benchmark":[121],"provides":[123],"valuable":[124],"insights":[125],"into":[126],"prompt-driven":[127],"processing.":[130]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
