{"id":"https://openalex.org/W7140131476","doi":"https://doi.org/10.18653/v1/2026.eacl-long.138","title":"Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding","display_name":"Guided by the Plan: Enhancing Faithful Autoregressive Text-to-Audio Generation with Guided Decoding","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140131476","doi":"https://doi.org/10.18653/v1/2026.eacl-long.138"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.eacl-long.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.138","pdf_url":"https://aclanthology.org/2026.eacl-long.138.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 19th Conference of the European Chapter 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/2026.eacl-long.138.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100693499","display_name":"Juncheng Wang","orcid":"https://orcid.org/0009-0008-2387-8904"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Juncheng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049636322","display_name":"Zhe Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhe Hu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130336123","display_name":"Chao Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chao Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130378912","display_name":"Siyue Ren","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Siyue Ren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130362561","display_name":"Yuxiang Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiang Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130404215","display_name":"Yang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130358349","display_name":"Baigui Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baigui Sun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130365377","display_name":"Shujun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujun Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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":0.39990647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3005","last_page":"3018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.2102999985218048,"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":0.2102999985218048,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.043699998408555984,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.04280000180006027,"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/autoregressive-model","display_name":"Autoregressive model","score":0.5353000164031982},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5338000059127808},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.35850000381469727},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3343000113964081},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.29350000619888306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.597599983215332},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5353000164031982},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5338000059127808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4993000030517578},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49619999527931213},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3472999930381775},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3343000113964081},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26910001039505005},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.26579999923706055},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2646999955177307}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.eacl-long.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.138","pdf_url":"https://aclanthology.org/2026.eacl-long.138.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.eacl-long.138","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.eacl-long.138","pdf_url":"https://aclanthology.org/2026.eacl-long.138.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 19th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.582165539264679,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322598","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140131476.pdf","grobid_xml":"https://content.openalex.org/works/W7140131476.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Juncheng":[0],"Wang,":[1],"Zhe":[2],"Hu,":[3],"Chao":[4],"Xu,":[5],"Siyue":[6],"Ren,":[7],"Yuxiang":[8],"Feng,":[9],"Yang":[10],"Liu,":[11],"Baigui":[12],"Sun,":[13],"Shujun":[14],"Wang.":[15],"Proceedings":[16],"of":[17,21,25],"the":[18,22,26],"19th":[19],"Conference":[20],"European":[23],"Chapter":[24],"Association":[27],"for":[28],"Computational":[29],"Linguistics":[30],"(Volume":[31],"1:":[32],"Long":[33],"Papers).":[34],"2026.":[35]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}
