{"id":"https://openalex.org/W7166830657","doi":"https://doi.org/10.18653/v1/2026.acl-long.1293","title":"UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions","display_name":"UniSonate: A Unified Model for Speech, Music, and Sound Effect Generation with Text Instructions","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166830657","doi":"https://doi.org/10.18653/v1/2026.acl-long.1293"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1293","doi":"https://doi.org/10.18653/v1/2026.acl-long.1293","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1293","pdf_url":"https://aclanthology.org/2026.acl-long.1293.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.1293.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028353824","display_name":"Chunyu Qiang","orcid":"https://orcid.org/0009-0007-2290-3074","observed_orcids":["https://orcid.org/0009-0007-2290-3074"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]},{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyu Qiang","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China","Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]},{"raw_affiliation_string":"Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134790284","display_name":"Xiaopeng Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Wang","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122015331","display_name":"Kang Yin","orcid":"https://orcid.org/0000-0002-0855-7140","observed_orcids":["https://orcid.org/0000-0002-0855-7140"]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang Yin","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134784358","display_name":"Yuzhe Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuzhe Liang","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139852281","display_name":"Yuxin Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuxin Guo","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134779542","display_name":"Teng Ma","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Teng Ma","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771892","display_name":"Ziyu Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyu Zhang","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134140039","display_name":"Tianrui Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":["Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122896960","display_name":"Cheng Gong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":["Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079946802","display_name":"Yushen Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726859","display_name":"Kuaishou (China)","ror":"https://ror.org/0258as409","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726859"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yushen Chen","raw_affiliation_strings":["Kuaishou Technology Co., Ltd. , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kuaishou Technology Co., Ltd. , Beijing , China","institution_ids":["https://openalex.org/I4401726859"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073918837","display_name":"Ruibo Fu","orcid":"https://orcid.org/0000-0001-9598-1881","observed_orcids":["https://orcid.org/0000-0001-9598-1881"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":["Institute of Automation , Chinese Academy of Sciences , Beijing , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation , Chinese Academy of Sciences , Beijing , China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105269944","display_name":"Longbiao Wang","orcid":"https://orcid.org/0000-0002-8094-6861","observed_orcids":["https://orcid.org/0000-0002-8094-6861"]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":["Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5135909674","display_name":"Jianwu Dang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":["Tianjin University , Tianjin , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tianjin University , Tianjin , China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.44842428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"28043","last_page":"28054"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9731000065803528,"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":0.9731000065803528,"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/T11309","display_name":"Music and Audio Processing","score":0.013399999588727951,"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/T11349","display_name":"Music Technology and Sound Studies","score":0.004999999888241291,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/speech-synthesis","display_name":"speech synthesis","score":0.7120000123977661},{"id":"https://openalex.org/keywords/music-generation","display_name":"music generation","score":0.9139999747276306},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.8050000071525574},{"id":"https://openalex.org/keywords/text-to-music","display_name":"text-to-music","score":0.8930000066757202},{"id":"https://openalex.org/keywords/text-instructions","display_name":"text instructions","score":0.4749999940395355}],"concepts":[{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.7222999930381775},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.60589998960495},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4738999903202057},{"id":"https://openalex.org/C142853389","wikidata":"https://www.wikidata.org/wiki/Q744778","display_name":"Association (psychology)","level":2,"score":0.47209998965263367},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4575999975204468},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3986000120639801},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C46451288","wikidata":"https://www.wikidata.org/wiki/Q1080745","display_name":"Unified field theory","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.322299987077713},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28299999237060547},{"id":"https://openalex.org/C151051286","wikidata":"https://www.wikidata.org/wiki/Q3258398","display_name":"Unified Process","level":4,"score":0.26429998874664307},{"id":"https://openalex.org/C203718221","wikidata":"https://www.wikidata.org/wiki/Q491713","display_name":"Sound (geography)","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1293","doi":"https://doi.org/10.18653/v1/2026.acl-long.1293","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1293","pdf_url":"https://aclanthology.org/2026.acl-long.1293.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1293","doi":"https://doi.org/10.18653/v1/2026.acl-long.1293","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1293","pdf_url":"https://aclanthology.org/2026.acl-long.1293.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[{"score":0.7817938923835754,"id":"https://metadata.un.org/sdg/4","display_name":"Quality education"}],"study_designs":[],"awards":[{"id":"https://openalex.org/G2883670753","display_name":null,"funder_award_id":"U23B2053","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166830657.pdf","grobid_xml":"https://content.openalex.org/works/W7166830657.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166867464","https://openalex.org/W7106703693","https://openalex.org/W7163055123","https://openalex.org/W2808342999","https://openalex.org/W4367359628","https://openalex.org/W7104370238","https://openalex.org/W4402671802","https://openalex.org/W2985969781","https://openalex.org/W7202213288","https://openalex.org/W4416422381"],"abstract_inverted_index":{"Chunyu":[0],"Qiang,":[1],"Xiaopeng":[2],"Wang,":[3,15,23],"Kang":[4],"Yin,":[5],"Yuzhe":[6],"Liang,":[7],"Yuxin":[8],"Guo,":[9],"Teng":[10],"Ma,":[11],"Ziyu":[12],"Zhang,":[13],"Tianrui":[14],"Cheng":[16],"Gong,":[17],"Yushen":[18],"Chen,":[19],"Ruibo":[20],"Fu,":[21],"Longbiao":[22],"Jianwu":[24],"Dang.":[25],"Proceedings":[26],"of":[27,32],"the":[28,33],"64th":[29],"Annual":[30],"Meeting":[31],"Association":[34],"for":[35],"Computational":[36],"Linguistics":[37],"(Volume":[38],"1:":[39],"Long":[40],"Papers).":[41],"2026.":[42]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-07-02T00:00:00"}
