{"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":null,"primary_location":{"id":"doi: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":null,"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"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.1293.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139715930","display_name":"Chunyu Qiang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyu Qiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139785980","display_name":"Xiaopeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaopeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139762729","display_name":"Kang Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139768399","display_name":"Yuzhe Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuzhe Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139852281","display_name":"Yuxin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxin Guo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139811705","display_name":"Teng Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Teng Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139771892","display_name":"Ziyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ziyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139852535","display_name":"Tianrui Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianrui Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139804939","display_name":"Cheng Gong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng Gong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079946802","display_name":"Yushen Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yushen Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139770106","display_name":"Ruibo Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruibo Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139760248","display_name":"Longbiao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Longbiao Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139758459","display_name":"Jianwu Dang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jianwu Dang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.82043302,"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/T10028","display_name":"Topic Modeling","score":0.21580000221729279,"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/T10028","display_name":"Topic Modeling","score":0.21580000221729279,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.12240000069141388,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.04410000145435333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.7222999930381775},{"id":"https://openalex.org/keywords/association","display_name":"Association (psychology)","score":0.47209998965263367},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.366100013256073},{"id":"https://openalex.org/keywords/unified-field-theory","display_name":"Unified field theory","score":0.3337000012397766},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.322299987077713},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.28299999237060547}],"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","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":null,"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","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":null,"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":[{"id":"https://metadata.un.org/sdg/4","score":0.7817938923835754,"display_name":"Quality Education"}],"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":{"grobid_xml":true,"pdf":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":[],"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":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
