{"id":"https://openalex.org/W4412944867","doi":"https://doi.org/10.18653/v1/2025.acl-long.997","title":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","display_name":"Align-SLM: Textless Spoken Language Models with Reinforcement Learning from AI Feedback","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944867","doi":"https://doi.org/10.18653/v1/2025.acl-long.997"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.997","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.997","pdf_url":"https://aclanthology.org/2025.acl-long.997.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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.997.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108124525","display_name":"Guan-Ting Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guan-Ting Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088032905","display_name":"Prashanth Gurunath Shivakumar","orcid":"https://orcid.org/0000-0003-1632-3309"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prashanth Gurunath Shivakumar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050696303","display_name":"Aditya Gourav","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aditya Gourav","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022646825","display_name":"Yile Gu","orcid":"https://orcid.org/0000-0003-3662-5056"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yile Gu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014054572","display_name":"Ankur Gandhe","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ankur Gandhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040508737","display_name":"Hung-yi Lee","orcid":"https://orcid.org/0000-0002-9654-5747"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hung-yi Lee","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5109934165","display_name":"Ivan Bulyko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Bulyko","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":null,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20395","last_page":"20411"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9509999752044678,"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":0.9509999752044678,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9399999976158142,"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":0.9276000261306763,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7417198419570923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.685629665851593},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5216727256774902},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.49363481998443604},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4668745696544647},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.3562176525592804},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16148313879966736},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.061129242181777954}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7417198419570923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685629665851593},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5216727256774902},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.49363481998443604},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4668745696544647},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3562176525592804},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16148313879966736},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.061129242181777954},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.997","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.997","pdf_url":"https://aclanthology.org/2025.acl-long.997.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.997","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.997","pdf_url":"https://aclanthology.org/2025.acl-long.997.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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944867.pdf","grobid_xml":"https://content.openalex.org/works/W4412944867.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Guan-Ting":[0],"Lin,":[1],"Prashanth":[2],"Gurunath":[3],"Shivakumar,":[4],"Aditya":[5],"Gourav,":[6],"Yile":[7],"Gu,":[8],"Ankur":[9],"Gandhe,":[10],"Hung-yi":[11],"Lee,":[12],"Ivan":[13],"Bulyko.":[14],"Proceedings":[15],"of":[16,21],"the":[17,22],"63rd":[18],"Annual":[19],"Meeting":[20],"Association":[23],"for":[24],"Computational":[25],"Linguistics":[26],"(Volume":[27],"1:":[28],"Long":[29],"Papers).":[30],"2025.":[31]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}