{"id":"https://openalex.org/W4412944743","doi":"https://doi.org/10.18653/v1/2025.acl-long.1147","title":"T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback","display_name":"T2A-Feedback: Improving Basic Capabilities of Text-to-Audio Generation via Fine-grained AI Feedback","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944743","doi":"https://doi.org/10.18653/v1/2025.acl-long.1147"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1147","pdf_url":"https://aclanthology.org/2025.acl-long.1147.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.1147.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111185441","display_name":"Z.Y. Wang","orcid":"https://orcid.org/0009-0007-6426-3749"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehan Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077165692","display_name":"Lei Ke","orcid":"https://orcid.org/0000-0002-1978-2562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ke Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016227748","display_name":"Chen Zhu","orcid":"https://orcid.org/0000-0002-3256-7330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083398904","display_name":"Jiawei Huang","orcid":"https://orcid.org/0000-0002-5184-2510"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiawei Huang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060861535","display_name":"S. Zhou","orcid":"https://orcid.org/0000-0002-7517-9653"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sashuai Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113150465","display_name":"Luping Liu","orcid":"https://orcid.org/0000-0003-2424-3560"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luping Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009897266","display_name":"Xize Cheng","orcid":"https://orcid.org/0000-0001-9708-3225"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xize Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102904447","display_name":"Shengpeng Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shengpeng Ji","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016502904","display_name":"Zhenhui Ye","orcid":"https://orcid.org/0000-0002-7105-014X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenhui Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102011966","display_name":"Tao Jin","orcid":"https://orcid.org/0000-0003-3564-1628"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Jin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":11,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.064,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.78098318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"23535","last_page":"23547"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9452000260353088,"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"}},"topics":[{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9452000260353088,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9144999980926514,"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":0.8098793029785156},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.49569880962371826},{"id":"https://openalex.org/keywords/audio-feedback","display_name":"Audio feedback","score":0.4801632761955261},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.366191029548645},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34321361780166626},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0681610107421875}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098793029785156},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.49569880962371826},{"id":"https://openalex.org/C38956757","wikidata":"https://www.wikidata.org/wiki/Q716215","display_name":"Audio feedback","level":2,"score":0.4801632761955261},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.366191029548645},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34321361780166626},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0681610107421875},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1147","pdf_url":"https://aclanthology.org/2025.acl-long.1147.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.1147","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1147","pdf_url":"https://aclanthology.org/2025.acl-long.1147.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 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1101031052","display_name":null,"funder_award_id":"U24A20326","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/W4412944743.pdf","grobid_xml":"https://content.openalex.org/works/W4412944743.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"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/W2398920710","https://openalex.org/W1498719563","https://openalex.org/W2166266522"],"abstract_inverted_index":{"Zehan":[0],"Wang,":[1],"Ke":[2],"Lei,":[3],"Chen":[4],"Zhu,":[5],"Jiawei":[6],"Huang,":[7],"Sashuai":[8],"Zhou,":[9],"Luping":[10],"Liu,":[11],"Xize":[12],"Cheng,":[13],"Shengpeng":[14],"Ji,":[15],"Zhenhui":[16],"Ye,":[17],"Tao":[18],"Jin,":[19],"Zhou":[20],"Zhao.":[21],"Proceedings":[22],"of":[23,28],"the":[24,29],"63rd":[25],"Annual":[26],"Meeting":[27],"Association":[30],"for":[31],"Computational":[32],"Linguistics":[33],"(Volume":[34],"1:":[35],"Long":[36],"Papers).":[37],"2025.":[38]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
