{"id":"https://openalex.org/W4408353373","doi":"https://doi.org/10.1109/icassp49660.2025.10889205","title":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","display_name":"SpeechCaps: Advancing Instruction-Based Universal Speech Models with Multi-Talker Speaking Style Captioning","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353373","doi":"https://doi.org/10.1109/icassp49660.2025.10889205"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889205","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":"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/A5102875860","display_name":"Chien-Yu Huang","orcid":"https://orcid.org/0000-0002-4024-9906"},"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":"Chien-Yu Huang","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091407588","display_name":"Min-Han Shih","orcid":null},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Min-Han Shih","raw_affiliation_strings":["University of Southern California,California,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Southern California,California,USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013041579","display_name":"Ke-Han Lu","orcid":"https://orcid.org/0000-0002-5331-0534"},"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":"Ke-Han Lu","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104171295","display_name":"Chi-Yuan Hsiao","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":"Chi-Yuan Hsiao","raw_affiliation_strings":["National Taiwan University,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","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":["National Taiwan University,Taipei,Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,Taipei,Taiwan","institution_ids":["https://openalex.org/I16733864"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"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":0.91967313,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.995199978351593,"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/T12031","display_name":"Speech and dialogue systems","score":0.9947999715805054,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9839000105857849,"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/closed-captioning","display_name":"Closed captioning","score":0.8239272832870483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7648223042488098},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6254155039787292},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.6078656911849976},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.42213213443756104},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3075673580169678},{"id":"https://openalex.org/keywords/history","display_name":"History","score":0.0504382848739624}],"concepts":[{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.8239272832870483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7648223042488098},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6254155039787292},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.6078656911849976},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42213213443756104},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3075673580169678},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0504382848739624},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889205","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889205","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":[{"display_name":"Quality Education","score":0.6899999976158142,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W3153451655","https://openalex.org/W3176693010","https://openalex.org/W4375869257","https://openalex.org/W4385571232","https://openalex.org/W4389519239","https://openalex.org/W4389519254","https://openalex.org/W4391021623","https://openalex.org/W4391021627","https://openalex.org/W4391021666","https://openalex.org/W4392902623","https://openalex.org/W4402112110","https://openalex.org/W4404781855","https://openalex.org/W6774569510","https://openalex.org/W6796581206","https://openalex.org/W6800875267","https://openalex.org/W6847363464","https://openalex.org/W6848208918","https://openalex.org/W6849177959","https://openalex.org/W6850625674","https://openalex.org/W6853249747","https://openalex.org/W6853530687","https://openalex.org/W6854866820","https://openalex.org/W6855801281","https://openalex.org/W6857054612","https://openalex.org/W6859099255","https://openalex.org/W6861859833"],"related_works":["https://openalex.org/W4210416330","https://openalex.org/W2775506363","https://openalex.org/W3088136942","https://openalex.org/W2963177403","https://openalex.org/W4290852288","https://openalex.org/W2949362007","https://openalex.org/W4283207562","https://openalex.org/W2330246314","https://openalex.org/W2949522393","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Instruction-based":[0],"speech":[1],"processing":[2],"is":[3,22,26],"becoming":[4],"popular.":[5],"Studies":[6],"show":[7],"that":[8,34],"training":[9],"with":[10,73],"multiple":[11],"tasks":[12,19],"boosts":[13],"performance,":[14],"but":[15],"collecting":[16],"diverse,":[17],"large-scale":[18],"and":[20,54,100,105],"datasets":[21],"expensive.":[23],"Thus,":[24],"it":[25],"highly":[27],"desirable":[28],"to":[29,48,62],"design":[30],"a":[31,42],"fundamental":[32],"task":[33,47,78],"benefits":[35],"other":[36],"downstream":[37],"tasks.":[38],"This":[39],"paper":[40],"introduces":[41],"multi-talker":[43,66],"speaking":[44],"style":[45],"captioning":[46,77],"enhance":[49],"the":[50,90],"understanding":[51],"of":[52],"speaker":[53,99],"prosodic":[55],"information.":[56],"We":[57],"used":[58],"large":[59],"language":[60],"models":[61],"generate":[63],"descriptions":[64],"for":[65],"speech.":[67],"Then,":[68],"we":[69],"trained":[70],"our":[71,87],"model":[72,88],"pre-training":[74],"on":[75,84,94],"this":[76],"followed":[79],"by":[80],"instruction":[81],"tuning.":[82],"Evaluation":[83],"Dynamic-SUPERB":[85],"shows":[86],"outperforming":[89],"baseline":[91],"pre-trained":[92],"only":[93],"single-talker":[95],"tasks,":[96],"particularly":[97],"in":[98],"emotion":[101],"recognition.":[102],"The":[103],"code":[104],"dataset":[106],"are":[107],"available":[108],"at":[109],"https://github.com/cyhuang-tw/speechcaps.":[110]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
