{"id":"https://openalex.org/W7214920274","doi":"https://doi.org/10.48550/arxiv.2609.36624","title":"DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors","display_name":"DualTrack: Synchronized speech-gesture generation via symmetric coupling of pretrained priors","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214920274","doi":"https://doi.org/10.48550/arxiv.2609.36624"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.36624","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36624","pdf_url":"https://arxiv.org/pdf/2609.36624","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/2609.36624","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134655182","display_name":"Hu Yuanzhuo","orcid":"https://orcid.org/0009-0005-4573-124X","observed_orcids":["https://orcid.org/0009-0005-4573-124X"]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Yuanzhuo","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen , China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147735110","display_name":"Zehan Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zehan","raw_affiliation_strings":["X Square Robot"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X Square Robot","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153625802","display_name":"Xiaoyi Qin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qin, Xiaoyi","raw_affiliation_strings":["X Square Robot"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"X Square Robot","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153637225","display_name":"Ming Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Ming","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen , China","institution_ids":["https://openalex.org/I4210116924"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.5776000022888184,"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":0.5776000022888184,"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":0.16500000655651093,"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/T12290","display_name":"Human Motion and Animation","score":0.1615000069141388,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/multimodal-synthesis","display_name":"multimodal synthesis","score":0.5580000281333923},{"id":"https://openalex.org/keywords/symmetric-coupling","display_name":"symmetric coupling","score":0.6579999923706055},{"id":"https://openalex.org/keywords/unseen-speakers","display_name":"unseen speakers","score":0.5289999842643738}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6710000038146973},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635000109672546},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.6482999920845032},{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.5501000285148621},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.45829999446868896},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4262000024318695},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.415800005197525},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3856000006198883},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.37040001153945923},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.36410000920295715},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.3587999939918518},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C18653775","wikidata":"https://www.wikidata.org/wiki/Q1333358","display_name":"Joint probability distribution","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2948000133037567},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C189809214","wikidata":"https://www.wikidata.org/wiki/Q829522","display_name":"Beat (acoustics)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27970001101493835},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C173064807","wikidata":"https://www.wikidata.org/wiki/Q7233190","display_name":"Position error","level":3,"score":0.2685999870300293},{"id":"https://openalex.org/C158525013","wikidata":"https://www.wikidata.org/wiki/Q2593739","display_name":"Fusion","level":2,"score":0.2639999985694885},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2556000053882599}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.36624","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36624","pdf_url":"https://arxiv.org/pdf/2609.36624","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.2609.36624","doi":"https://doi.org/10.48550/arxiv.2609.36624","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.36624","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:2609.36624","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.36624","pdf_url":"https://arxiv.org/pdf/2609.36624","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214920274.pdf","grobid_xml":"https://content.openalex.org/works/W7214920274.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415273624","https://openalex.org/W7162543732","https://openalex.org/W4386755513","https://openalex.org/W4402916657","https://openalex.org/W808171498","https://openalex.org/W4386655536","https://openalex.org/W3002310794","https://openalex.org/W4387421716","https://openalex.org/W7160132741","https://openalex.org/W7112154665"],"abstract_inverted_index":{"Joint":[0],"speech-gesture":[1],"synthesis":[2],"must":[3],"coordinate":[4],"two":[5],"modalities":[6],"despite":[7],"limited":[8,18],"paired":[9],"data.":[10],"Existing":[11],"approaches":[12],"often":[13],"lack":[14],"bidirectional":[15],"interaction,":[16],"have":[17],"language":[19],"coverage,":[20],"or":[21,84],"simplify":[22],"body":[23],"and":[24,34,75,93,101],"finger":[25],"representations.":[26],"We":[27,60],"present":[28],"DualTrack,":[29],"which":[30],"couples":[31],"pretrained":[32],"speech":[33,83,102],"motion":[35,85],"priors":[36],"on":[37],"a":[38],"shared":[39,79],"12.5":[40],"Hz":[41],"timeline.":[42],"Causal":[43],"adapters":[44],"exchange":[45],"previous-packet":[46],"information,":[47],"while":[48],"current-state":[49],"fusion":[50],"coordinates":[51],"the":[52,78,105],"streams":[53],"before":[54],"they":[55],"separately":[56],"complete":[57],"sixteen-codebook":[58],"packets.":[59],"evaluate":[61],"43":[62],"BEAT2":[63],"recordings":[64],"in":[65],"four":[66],"languages,":[67],"with":[68],"speakers":[69],"held":[70],"out":[71],"from":[72],"joint":[73],"training":[74],"validation.":[76],"On":[77],"English/Spanish":[80],"inputs,":[81],"without":[82],"prefixes,":[86],"DualTrack":[87],"achieves":[88],"lower":[89],"word":[90],"error":[91],"rate":[92],"full-motion":[94],"Fr\u00e9chet":[95],"Gesture":[96],"Distance,":[97],"higher":[98],"beat":[99],"consistency":[100],"naturalness":[103],"than":[104],"evaluated":[106],"GELINA":[107],"baseline.":[108]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-01T00:00:00"}