{"id":"https://openalex.org/W7155014716","doi":"https://doi.org/10.48550/arxiv.2604.16056","title":"AST: Adaptive, Seamless, and Training-Free Precise Speech Editing","display_name":"AST: Adaptive, Seamless, and Training-Free Precise Speech Editing","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7155014716","doi":"https://doi.org/10.48550/arxiv.2604.16056"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.16056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16056","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.16056","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134051746","display_name":"Sihan Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Sihan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121136238","display_name":"Yechen Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Yechen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134075032","display_name":"Zhen Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134029337","display_name":"Jintao Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jintao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134029651","display_name":"Jinshan Zhang","orcid":"https://orcid.org/0009-0000-8412-2424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jinshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134075442","display_name":"Ying Li","orcid":"https://orcid.org/0009-0004-5197-4152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Ying","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134036349","display_name":"Jianwei Yin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin, Jianwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5123889466","display_name":"Meng Xi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi, Meng","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":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":0.8148999810218811,"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":0.8148999810218811,"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/T10028","display_name":"Topic Modeling","score":0.03709999844431877,"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":0.030300000682473183,"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/consistency","display_name":"Consistency (knowledge bases)","score":0.5896000266075134},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.3970000147819519},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3889999985694885},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.38339999318122864},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.37630000710487366},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.3560999929904938},{"id":"https://openalex.org/keywords/identity","display_name":"Identity (music)","score":0.35179999470710754},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.3508000075817108}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8303999900817871},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6358000040054321},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5896000266075134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40119999647140503},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3560999929904938},{"id":"https://openalex.org/C2778355321","wikidata":"https://www.wikidata.org/wiki/Q17079427","display_name":"Identity (music)","level":2,"score":0.35179999470710754},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3508000075817108},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3334999978542328},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.326200008392334},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.3237999975681305},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.31060001254081726},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.27140000462532043},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.2676999866962433},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.16056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16056","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.16056","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.16056","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":"Preprint"},"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":{"Text-based":[0],"speech":[1,61,97,147],"editing":[2,44,62,94,148],"aims":[3],"to":[4,74,90,180,201],"modify":[5],"specific":[6,96],"segments":[7,79],"while":[8,190],"preserving":[9],"speaker":[10,212],"identity":[11],"and":[12,26,46,58,145,214],"acoustic":[13],"context.":[14],"Existing":[15],"methods":[16],"rely":[17],"on":[18],"task-specific":[19],"training,":[20],"which":[21],"incurs":[22],"high":[23],"data":[24],"costs":[25],"struggles":[27],"with":[28,80],"temporal":[29,155,215],"fidelity":[30],"in":[31,157],"unedited":[32,158],"regions.":[33],"Meanwhile,":[34],"adapting":[35],"Text-to-Speech":[36],"(TTS)":[37],"models":[38],"often":[39],"faces":[40],"a":[41,65,117,143,202],"trade-off":[42,175],"between":[43],"quality":[45],"consistency.":[47],"To":[48,99,132],"address":[49],"these":[50,103],"issues,":[51],"we":[52,140,160],"propose":[53,161],"AST,":[54],"an":[55],"Adaptive,":[56],"Seamless,":[57],"Training-free":[59],"precise":[60,92],"framework.":[63],"Leveraging":[64],"pre-trained":[66],"autoregressive":[67],"TTS":[68,204],"model,":[69],"AST":[70,85,171,187,200],"introduces":[71],"Latent":[72],"Recomposition":[73],"selectively":[75],"stitch":[76],"preserved":[77],"source":[78],"newly":[81],"synthesized":[82],"targets.":[83],"Furthermore,":[84],"extends":[86],"this":[87],"latent":[88],"manipulation":[89],"enable":[91],"style":[93],"for":[95],"segments.":[98],"prevent":[100],"artifacts":[101],"at":[102],"edit":[104],"boundaries,":[105],"the":[106,129,134,173,181],"framework":[107],"incorporates":[108],"Adaptive":[109],"Weak":[110],"Fact":[111],"Guidance":[112],"(AWFG).":[113],"AWFG":[114],"dynamically":[115],"modulates":[116],"mel-space":[118],"guidance":[119],"signal,":[120],"enforcing":[121],"structural":[122],"constraints":[123],"only":[124],"where":[125],"necessary":[126],"without":[127,176],"disrupting":[128],"generative":[130],"manifold.":[131],"fill":[133],"gap":[135],"of":[136],"publicly":[137],"accessible":[138],"benchmarks,":[139],"introduce":[141],"LibriSpeech-Edit,":[142],"new":[144],"larger":[146],"dataset.":[149],"As":[150],"existing":[151],"metrics":[152],"poorly":[153],"evaluate":[154],"consistency":[156,189],"regions,":[159],"Word-level":[162],"Dynamic":[163],"Time":[164],"Warping":[165],"(WDTW).":[166],"Extensive":[167],"experiments":[168],"demonstrate":[169],"that":[170],"resolves":[172],"controllability-quality":[174],"extra":[177],"training.":[178],"Compared":[179],"previous":[182],"most":[183],"temporally":[184],"consistent":[185],"baseline,":[186],"improves":[188],"reducing":[191],"Word":[192],"Error":[193],"Rate":[194],"by":[195,208],"nearly":[196],"70%.":[197],"Moreover,":[198],"applying":[199],"foundation":[203],"model":[205],"reduces":[206],"WDTW":[207],"27%,":[209],"achieving":[210],"state-of-the-art":[211],"preservation":[213],"fidelity.":[216]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-21T00:00:00"}