{"id":"https://openalex.org/W7119210508","doi":"https://doi.org/10.48550/arxiv.2601.03170","title":"TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis","display_name":"TED-TTS: Training-Free Intra-Utterance Emotion and Duration Control for Text-to-Speech Synthesis","publication_year":2026,"publication_date":"2026-01-06","ids":{"openalex":"https://openalex.org/W7119210508","doi":"https://doi.org/10.48550/arxiv.2601.03170"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.03170","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.03170","pdf_url":"https://arxiv.org/pdf/2601.03170","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.03170","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101302348","display_name":"Qifan Liang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Qifan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036688868","display_name":"Yuansen Liu","orcid":"https://orcid.org/0009-0009-3756-0363","observed_orcids":["https://orcid.org/0009-0009-3756-0363"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuansen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012994588","display_name":"Ruixin Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Ruixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122012774","display_name":"Nan Lu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Nan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104290513","display_name":"Junchuan Zhao","orcid":"https://orcid.org/0009-0008-2616-6590","observed_orcids":["https://orcid.org/0009-0008-2616-6590"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Junchuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5121985539","display_name":"Ye Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Ye","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":0.9994999766349792,"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":0.9994999766349792,"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/T10860","display_name":"Speech and Audio Processing","score":9.999999747378752e-05,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10403","display_name":"Phonetics and Phonology Research","score":0.0,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/causal-masking","display_name":"causal masking","score":0.8389999866485596}],"concepts":[{"id":"https://openalex.org/C112758219","wikidata":"https://www.wikidata.org/wiki/Q16038819","display_name":"Duration (music)","level":2,"score":0.8054999709129333},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6277999877929688},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.565500020980835},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5349000096321106},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5166000127792358},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5009999871253967},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4828000068664551},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45080000162124634},{"id":"https://openalex.org/C45262634","wikidata":"https://www.wikidata.org/wiki/Q5159291","display_name":"Conditioning","level":2,"score":0.4077000021934509},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3806000053882599},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.3506999909877777},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3476000130176544},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.33149999380111694},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3314000070095062},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C72169020","wikidata":"https://www.wikidata.org/wiki/Q194404","display_name":"Monotonic function","level":2,"score":0.2759000062942505},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2743000090122223},{"id":"https://openalex.org/C2777098013","wikidata":"https://www.wikidata.org/wiki/Q5468626","display_name":"Foreknowledge","level":2,"score":0.2741999924182892}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.03170","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.03170","pdf_url":"https://arxiv.org/pdf/2601.03170","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,"listed_in":[],"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.2601.03170","doi":"https://doi.org/10.48550/arxiv.2601.03170","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.03170","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.03170","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.03170","pdf_url":"https://arxiv.org/pdf/2601.03170","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,"listed_in":[],"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"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7212323836","https://openalex.org/W7077061760","https://openalex.org/W4415348544","https://openalex.org/W7156571141","https://openalex.org/W7220897651","https://openalex.org/W4372340836","https://openalex.org/W4408354026","https://openalex.org/W7163124116","https://openalex.org/W4417092535","https://openalex.org/W7107866763"],"abstract_inverted_index":{"While":[0],"controllable":[1,40],"Text-to-Speech":[2],"(TTS)":[3],"has":[4],"achieved":[5],"notable":[6],"progress,":[7],"most":[8],"existing":[9],"methods":[10],"remain":[11],"limited":[12],"to":[13,22,46,70,99,137],"inter-utterance-level":[14],"control,":[15,160],"making":[16],"fine-grained":[17],"intra-utterance":[18,48,80,154],"expression":[19],"challenging":[20],"due":[21],"their":[23],"reliance":[24],"on":[25,89],"non-public":[26],"datasets":[27],"or":[28],"complex":[29],"multi-stage":[30],"training.":[31],"In":[32],"this":[33],"paper,":[34],"we":[35,54,91,128],"propose":[36,55,93],"TED-TTS,":[37],"a":[38,56,94,130],"training-free":[39,148],"framework":[41],"for":[42,123],"pretrained":[43],"zero-shot":[44],"TTS":[45,170],"enable":[47,138],"emotion":[49,58,72,81],"and":[50,74,133,158,173],"duration":[51,96,102,112,159],"expression.":[52],"Specifically,":[53],"segment-aware":[57,95],"conditioning":[59,73],"strategy":[60,98],"that":[61,146],"combines":[62],"causal":[63],"masking":[64],"with":[65,105],"monotonic":[66],"stream":[67],"alignment":[68],"filtering":[69],"isolate":[71],"schedule":[75],"mask":[76],"transitions,":[77],"enabling":[78],"smooth":[79],"shifts":[82],"while":[83,114],"preserving":[84],"global":[85,106],"semantic":[86],"coherence.":[87],"Based":[88],"this,":[90],"further":[92],"steering":[97,104],"combine":[100],"local":[101,111],"embedding":[103],"EOS":[107],"logit":[108],"modulation,":[109],"allowing":[110],"adjustment":[113],"ensuring":[115],"globally":[116],"consistent":[117],"termination.":[118],"To":[119],"eliminate":[120],"the":[121,168],"need":[122],"segment-level":[124],"manual":[125],"prompt":[126,141],"engineering,":[127],"construct":[129],"30,000-sample":[131],"multi-emotion":[132,157],"duration-annotated":[134],"text":[135],"dataset":[136],"LLM-based":[139],"automatic":[140],"construction.":[142],"Extensive":[143],"experiments":[144],"demonstrate":[145],"our":[147],"method":[149],"not":[150],"only":[151],"achieves":[152],"state-of-the-art":[153],"consistency":[155],"in":[156],"but":[161],"also":[162],"maintains":[163],"baseline-level":[164],"speech":[165],"quality":[166],"of":[167],"underlying":[169],"model.":[171],"Code":[172],"audio":[174],"samples":[175],"are":[176],"available.":[177]},"counts_by_year":[],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2026-01-08T00:00:00"}