{"id":"https://openalex.org/W4403780831","doi":"https://doi.org/10.1145/3664647.3681688","title":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","display_name":"Tango 2: Aligning Diffusion-based Text-to-Audio Generations through Direct Preference Optimization","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403780831","doi":"https://doi.org/10.1145/3664647.3681688"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3681688","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","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/A5007003459","display_name":"Navonil Majumder","orcid":"https://orcid.org/0000-0002-1449-617X"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Navonil Majumder","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093760924","display_name":"Chia-Yu Hung","orcid":"https://orcid.org/0009-0006-5252-0763"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chia-Yu Hung","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086877005","display_name":"Deepanway Ghosal","orcid":"https://orcid.org/0000-0002-3858-4449"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deepanway Ghosal","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051950818","display_name":"Wei-Ning Hsu","orcid":"https://orcid.org/0000-0001-5546-5217"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei-Ning Hsu","raw_affiliation_strings":["Meta AI, New York, USA"],"affiliations":[{"raw_affiliation_string":"Meta AI, New York, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082450455","display_name":"Rada Mihalcea","orcid":"https://orcid.org/0000-0002-0767-6703"},"institutions":[{"id":"https://openalex.org/I27837315","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291","country_code":"US","type":"education","lineage":["https://openalex.org/I27837315"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rada Mihalcea","raw_affiliation_strings":["University of Michigan, Ann Arbor, USA"],"affiliations":[{"raw_affiliation_string":"University of Michigan, Ann Arbor, USA","institution_ids":["https://openalex.org/I27837315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033376109","display_name":"Soujanya Poria","orcid":"https://orcid.org/0000-0001-6924-7931"},"institutions":[{"id":"https://openalex.org/I152815399","display_name":"Singapore University of Technology and Design","ror":"https://ror.org/05j6fvn87","country_code":"SG","type":"education","lineage":["https://openalex.org/I152815399"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Soujanya Poria","raw_affiliation_strings":["Singapore University of Technology and Design, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Singapore University of Technology and Design, Singapore, Singapore","institution_ids":["https://openalex.org/I152815399"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5007003459"],"corresponding_institution_ids":["https://openalex.org/I152815399"],"apc_list":null,"apc_paid":null,"fwci":12.4388,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.99273864,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"564","last_page":"572"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9970999956130981,"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/T10860","display_name":"Speech and Audio Processing","score":0.9890000224113464,"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/computer-science","display_name":"Computer science","score":0.6326842904090881},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.6288411021232605},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.523850679397583},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.431589812040329},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12363883852958679},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1016874611377716},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.06584864854812622}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6326842904090881},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.6288411021232605},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.523850679397583},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.431589812040329},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12363883852958679},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1016874611377716},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.06584864854812622},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3681688","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3681688","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:deepblue.lib.umich.edu:2027.42/198158","is_oa":false,"landing_page_url":"https://hdl.handle.net/2027.42/198158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.4099999964237213,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W3215615641","https://openalex.org/W4226033575","https://openalex.org/W4312933868","https://openalex.org/W4372260310","https://openalex.org/W4381786045","https://openalex.org/W4402753790"],"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/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Peer":[0],"Reviewed":[1]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":30},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-03T22:45:19.894376","created_date":"2025-10-10T00:00:00"}
