{"id":"https://openalex.org/W4414593086","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1157","title":"DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration","display_name":"DiTReducio: A Training-Free Acceleration for DiT-Based TTS via Progressive Calibration","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4414593086","doi":"https://doi.org/10.18653/v1/2026.findings-acl.1157"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1157","pdf_url":"https://aclanthology.org/2026.findings-acl.1157.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.1157.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yanru Huo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanru Huo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073215052","display_name":"Ziyue Jiang","orcid":"https://orcid.org/0009-0005-1358-8098"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziyue Jiang","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030274499","display_name":"Zuoli Tang","orcid":"https://orcid.org/0009-0006-8335-1157"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zuoli Tang","raw_affiliation_strings":["Wuhan University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Wuhan University","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011997254","display_name":"Qingyang Hong","orcid":"https://orcid.org/0000-0001-7380-8690"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qingyang Hong","raw_affiliation_strings":["Xiamen University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University ,","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079260216","display_name":"Zhou Zhao","orcid":"https://orcid.org/0000-0001-6121-0384"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Zhao","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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":0.00747474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"23101","last_page":"23116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9398999810218811,"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/T10320","display_name":"Neural Networks and Applications","score":0.9398999810218811,"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/computation","display_name":"Computation","score":0.7027000188827515},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.620199978351593},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5245000123977661},{"id":"https://openalex.org/keywords/compression","display_name":"Compression (physics)","score":0.503000020980835},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.46129998564720154},{"id":"https://openalex.org/keywords/flops","display_name":"FLOPS","score":0.4489000141620636},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.423799991607666},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4178999960422516}],"concepts":[{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7027000188827515},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7016000151634216},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.620199978351593},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5245000123977661},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.503000020980835},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.46129998564720154},{"id":"https://openalex.org/C3826847","wikidata":"https://www.wikidata.org/wiki/Q188768","display_name":"FLOPS","level":2,"score":0.4489000141620636},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.43140000104904175},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4178999960422516},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.40639999508857727},{"id":"https://openalex.org/C25797200","wikidata":"https://www.wikidata.org/wiki/Q828137","display_name":"Compression ratio","level":3,"score":0.3797999918460846},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.32260000705718994},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.321399986743927},{"id":"https://openalex.org/C123079801","wikidata":"https://www.wikidata.org/wiki/Q750240","display_name":"Modulation (music)","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C134835016","wikidata":"https://www.wikidata.org/wiki/Q690265","display_name":"Lookup table","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26499998569488525},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.2556000053882599},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2515999972820282}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1157","pdf_url":"https://aclanthology.org/2026.findings-acl.1157.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2509.09748","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.09748","pdf_url":"https://arxiv.org/pdf/2509.09748","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2509.09748","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.09748","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.1157","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.1157","pdf_url":"https://aclanthology.org/2026.findings-acl.1157.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414593086.pdf","grobid_xml":"https://content.openalex.org/works/W4414593086.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"While":[0],"Diffusion":[1],"Transformers":[2],"(DiT)":[3],"have":[4],"advanced":[5],"non-autoregressive":[6],"(NAR)":[7],"speech":[8],"synthesis,":[9],"their":[10],"high":[11],"computational":[12,99],"demands":[13],"remain":[14,34],"a":[15,41,82,116],"limitation.Existing":[16],"DiT-based":[17,49],"text-tospeech":[18],"(TTS)":[19],"model":[20],"acceleration":[21,43],"approaches":[22],"mainly":[23],"focus":[24],"on":[25,71,107],"reducing":[26],"sampling":[27],"steps":[28],"through":[29,101],"distillation":[30],"techniques,":[31],"yet":[32],"they":[33],"constrained":[35],"by":[36,127],"training":[37],"costs.We":[38],"introduce":[39],"DiTReducio,":[40],"training-free":[42],"framework":[44],"that":[45,113],"compresses":[46],"computations":[47,67],"in":[48,119],"TTS":[50],"models":[51],"via":[52],"progressive":[53],"calibration.We":[54],"propose":[55],"two":[56,72],"compression":[57,89,103],"methods,":[58],"Temporal":[59],"Skipping":[60],"and":[61,98,109,121],"Branch":[62],"Skipping,":[63],"to":[64,85],"eliminate":[65],"redundant":[66],"during":[68],"inference.Moreover,":[69],"based":[70],"characteristic":[73],"attention":[74],"patterns":[75],"identified":[76],"within":[77],"DiT":[78],"layers,":[79],"we":[80],"devise":[81],"pattern-guided":[83],"strategy":[84],"selectively":[86],"apply":[87],"the":[88,123],"methods.Our":[90],"method":[91],"allows":[92],"flexible":[93],"modulation":[94],"between":[95],"generation":[96,131],"quality":[97],"efficiency":[100],"adjustable":[102],"thresholds.Experimental":[104],"evaluations":[105],"conducted":[106],"F5-TTS":[108],"MegaTTS":[110],"3":[111],"demonstrate":[112],"DiTReducio":[114],"achieves":[115],"75.4%":[117],"reduction":[118],"FLOPs":[120],"improves":[122],"Real-Time":[124],"Factor":[125],"(RTF)":[126],"37.1%,":[128],"while":[129],"preserving":[130],"quality.The":[132],"code":[133],"is":[134],"available":[135],"at":[136],"https://github.com/":[137],"iHateTheWorld555/DiTReducio.":[138]},"counts_by_year":[],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}