{"id":"https://openalex.org/W7212282965","doi":"https://doi.org/10.48550/arxiv.2609.11725","title":"Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations","display_name":"Continuous-Time Acoustic Modelling with Neural Controlled Differential Equations","publication_year":2026,"publication_date":"2026-09-10","ids":{"openalex":"https://openalex.org/W7212282965","doi":"https://doi.org/10.48550/arxiv.2609.11725"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.11725","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.11725","pdf_url":"https://arxiv.org/pdf/2609.11725","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.11725","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5099137208","display_name":"Mattias Cross","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Cross, Mattias","raw_affiliation_strings":["Speech and Hearing Group University of Sheffield Sheffield , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group University of Sheffield Sheffield , United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123043392","display_name":"Minghui Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhao, Minghui","raw_affiliation_strings":["Speech and Hearing Group University of Sheffield Sheffield , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group University of Sheffield Sheffield , United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024283093","display_name":"Anton Ragni","orcid":"https://orcid.org/0000-0003-0634-4456","observed_orcids":["https://orcid.org/0000-0003-0634-4456"]},"institutions":[{"id":"https://openalex.org/I91136226","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044","country_code":"GB","type":"education","lineage":["https://openalex.org/I91136226"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ragni, Anton","raw_affiliation_strings":["Speech and Hearing Group University of Sheffield Sheffield , United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Hearing Group University of Sheffield Sheffield , United Kingdom","institution_ids":["https://openalex.org/I91136226"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I91136226"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.00019999999494757503,"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/neural-controlled-differential-equations","display_name":"neural controlled differential equations","score":0.8859999775886536},{"id":"https://openalex.org/keywords/text-to-speech","display_name":"text-to-speech","score":0.8999999761581421},{"id":"https://openalex.org/keywords/emotional-expression","display_name":"emotional expression","score":0.6850000023841858},{"id":"https://openalex.org/keywords/temporal-resolution","display_name":"temporal resolution","score":0.5419999957084656}],"concepts":[{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6238999962806702},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5855000019073486},{"id":"https://openalex.org/C198082294","wikidata":"https://www.wikidata.org/wiki/Q3399648","display_name":"Position (finance)","level":2,"score":0.5616000294685364},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5471000075340271},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4287000000476837},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40290001034736633},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.39910000562667847},{"id":"https://openalex.org/C108250783","wikidata":"https://www.wikidata.org/wiki/Q4674710","display_name":"Acoustic space","level":3,"score":0.39730000495910645},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3882000148296356},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.38690000772476196},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.38089999556541443},{"id":"https://openalex.org/C78045399","wikidata":"https://www.wikidata.org/wiki/Q11214","display_name":"Differential equation","level":2,"score":0.35510000586509705},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3544999957084656},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33739998936653137},{"id":"https://openalex.org/C47446073","wikidata":"https://www.wikidata.org/wiki/Q5165890","display_name":"Control theory (sociology)","level":3,"score":0.329800009727478},{"id":"https://openalex.org/C93226319","wikidata":"https://www.wikidata.org/wiki/Q193137","display_name":"Differential (mechanical device)","level":2,"score":0.3181999921798706},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.296099990606308},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.2937999963760376},{"id":"https://openalex.org/C2779426996","wikidata":"https://www.wikidata.org/wiki/Q18389128","display_name":"Echo (communications protocol)","level":2,"score":0.28519999980926514},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2791999876499176},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2728999853134155},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.2567000091075897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.25609999895095825},{"id":"https://openalex.org/C52918065","wikidata":"https://www.wikidata.org/wiki/Q230945","display_name":"State-space representation","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.11725","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.11725","pdf_url":"https://arxiv.org/pdf/2609.11725","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.2609.11725","doi":"https://doi.org/10.48550/arxiv.2609.11725","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.11725","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.11725","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.11725","pdf_url":"https://arxiv.org/pdf/2609.11725","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":[{"id":"https://openalex.org/F4320320342","display_name":"University of Sheffield","ror":"https://ror.org/05krs5044"},{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7212282965.pdf","grobid_xml":"https://content.openalex.org/works/W7212282965.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2127141656","https://openalex.org/W4407801326","https://openalex.org/W4412945617"],"related_works":["https://openalex.org/W3197294703","https://openalex.org/W4296068767","https://openalex.org/W4411949025","https://openalex.org/W3163338468","https://openalex.org/W4297841537","https://openalex.org/W3206353686","https://openalex.org/W4372341178","https://openalex.org/W7156571141","https://openalex.org/W3091928890","https://openalex.org/W4402772729"],"abstract_inverted_index":{"Text-to-speech":[0],"(TTS)":[1],"models":[2,128],"commonly":[3],"address":[4],"text--speech":[5],"alignment":[6,24],"by":[7],"expanding":[8],"phone-level":[9],"encoder":[10],"states":[11,38,45],"to":[12,83,149],"frame-level":[13],"decoder":[14,113],"inputs":[15],"using":[16,59],"predicted":[17],"durations.":[18],"While":[19],"this":[20,26],"length-regulation":[21],"step":[22,133],"resolves":[23],"structurally,":[25],"use":[27,77],"of":[28,43],"duration":[29],"typically":[30],"changes":[31,162],"only":[32],"where":[33],"and":[34,76,95,107,119,140,168,182],"how":[35],"often":[36],"latent":[37],"appear,":[39],"not":[40],"the":[41,44,67,163],"values":[42,90],"themselves.":[46],"This":[47],"paper":[48],"proposes":[49],"a":[50,71,78,85,110,150,176],"continuous-time":[51,86,181],"mechanism":[52],"for":[53,180],"duration-aware":[54,183],"acoustic":[55,80,112],"modelling":[56],"in":[57],"TTS":[58],"neural":[60,79],"controlled":[61],"differential":[62],"equations":[63],"(CDEs).":[64],"We":[65],"formulate":[66],"phone":[68,131],"representation":[69],"as":[70,175],"temporally":[72],"parameterised":[73],"control":[74],"path":[75],"vector":[81],"field":[82],"produce":[84],"hidden":[87],"state":[88],"whose":[89],"evolve":[91],"with":[92,155],"phonetic":[93],"content":[94],"duration-derived":[96],"timing.":[97],"The":[98],"resulting":[99],"trajectory":[100],"can":[101,134],"be":[102],"sampled":[103],"at":[104],"discrete":[105],"points":[106],"integrated":[108],"into":[109],"standard":[111],"pipeline.":[114],"Objective":[115],"results":[116,124,172],"contrast":[117],"CDEs":[118,174],"typical":[120],"recurrent":[121],"models.":[122],"Subjective":[123],"suggest":[125,158],"that":[126,159],"CDE-based":[127],"evaluating":[129],"one":[130],"per":[132],"improve":[135],"rank-order":[136],"agreement":[137],"between":[138,165],"synthesised":[139],"reference":[141],"emotion":[142],"intensity":[143],"while":[144],"maintaining":[145],"comparable":[146],"emotion-expression":[147],"quality":[148],"strong":[151],"baseline.":[152],"Additional":[153],"experiments":[154],"half-phone":[156],"step-sizes":[157],"temporal":[160],"resolution":[161],"trade-off":[164],"style":[166],"tracking":[167],"absolute":[169],"calibration.":[170],"These":[171],"position":[173],"promising":[177],"design":[178],"space":[179],"style-sensitive":[184],"TTS.":[185]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-12T00:00:00"}
