{"id":"https://openalex.org/W7143359437","doi":"https://doi.org/10.48550/arxiv.2603.26364","title":"LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling","display_name":"LLaDA-TTS: Unifying Speech Synthesis and Zero-Shot Editing via Masked Diffusion Modeling","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143359437","doi":"https://doi.org/10.48550/arxiv.2603.26364"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26364","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.26364","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130974564","display_name":"Xiaoyu Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130993326","display_name":"Huizhi Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Huizhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130976761","display_name":"Wei Zou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zou, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5051629064","display_name":"Yunzhang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yunzhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.7093999981880188,"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":0.7093999981880188,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.04439999908208847,"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/T10028","display_name":"Topic Modeling","score":0.038100000470876694,"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/naturalness","display_name":"Naturalness","score":0.6876999735832214},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5370000004768372},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.520799994468689},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5141000151634216},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4410000145435333},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.41429999470710754},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.3993000090122223},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.3950999975204468}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7699000239372253},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.6876999735832214},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6402000188827515},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.520799994468689},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5141000151634216},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4410000145435333},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.41429999470710754},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3993000090122223},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.3950999975204468},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3582000136375427},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3564000129699707},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.3427000045776367},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.34209999442100525},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.33730000257492065},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.313400000333786},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C134652429","wikidata":"https://www.wikidata.org/wiki/Q1052698","display_name":"Jitter","level":2,"score":0.2964000105857849},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.28600001335144043},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2851000130176544},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C2776175482","wikidata":"https://www.wikidata.org/wiki/Q1195816","display_name":"Transfer (computing)","level":2,"score":0.25769999623298645}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26364","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.26364","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26364","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"language":[1],"model":[2,36],"(LLM)-based":[3],"text-to-speech":[4],"(TTS)":[5],"systems":[6],"achieve":[7],"remarkable":[8],"naturalness":[9],"via":[10,73],"autoregressive":[11],"(AR)":[12],"decoding,":[13],"but":[14],"require":[15],"N":[16,21],"sequential":[17],"steps":[18],"to":[19,68,173],"generate":[20],"speech":[22,128],"tokens.":[23],"We":[24],"present":[25],"LLaDA-TTS,":[26],"which":[27],"replaces":[28],"the":[29,69,91,107,114,122,151,166],"AR":[30,66,115,176],"LLM":[31],"with":[32],"a":[33,41,64,99],"masked":[34,70,148],"diffusion":[35,71],"that":[37,141],"completes":[38],"generation":[39],"in":[40],"fixed":[42],"number":[43],"of":[44,58,109,154],"parallel":[45],"steps,":[46,78],"decoupling":[47],"inference":[48],"latency":[49],"from":[50],"sequence":[51],"length.":[52],"Remarkably,":[53],"using":[54],"only":[55,165],"50":[56],"hours":[57],"fine-tuning":[59],"data,":[60],"we":[61,139],"successfully":[62],"transfer":[63],"pretrained":[65],"checkpoint":[67],"paradigm":[72],"bidirectional":[74,123,147],"attention.":[75],"At":[76],"64":[77],"LLaDA-TTS":[79],"achieves":[80],"0.98%":[81],"CER":[82],"(zh)":[83],"and":[84,133,169,180],"1.96%":[85],"WER":[86],"(en)":[87],"on":[88],"Seed-TTS-Eval,":[89],"matching":[90],"original":[92],"CosyVoice":[93],"3":[94],"baseline":[95,116],"performance":[96],"while":[97],"delivering":[98],"2x":[100],"LLM-stage":[101],"speedup--a":[102],"notable":[103],"acceleration":[104],"achieved":[105],"despite":[106],"absence":[108],"KV":[110],"cache,":[111],"an":[112],"optimization":[113],"heavily":[117],"relies":[118],"on.":[119],"Beyond":[120],"acceleration,":[121],"architecture":[124],"naturally":[125],"enables":[126],"zero-shot":[127],"editing--including":[129],"word-level":[130],"insertion,":[131],"deletion,":[132],"substitution--without":[134],"any":[135,174],"additional":[136],"training.":[137],"Theoretically,":[138],"prove":[140],"AR-pretrained":[142],"weights":[143],"are":[144],"near-optimal":[145],"for":[146],"prediction":[149],"under":[150],"locality":[152],"property":[153],"acoustic":[155],"tokens,":[156],"explaining":[157],"this":[158],"rapid":[159],"convergence.":[160],"This":[161],"general":[162],"method":[163],"modifies":[164],"attention":[167],"mask":[168],"objective,":[170],"applying":[171],"seamlessly":[172],"LLM-based":[175],"TTS":[177],"system.":[178],"Code":[179],"audio":[181],"samples":[182],"will":[183],"be":[184],"available":[185],"at":[186],"https://deft-piroshki-b652b5.netlify.app/.":[187]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-31T00:00:00"}