{"id":"https://openalex.org/W4410297023","doi":"https://doi.org/10.1109/hri61500.2025.10974020","title":"SpeechCAT: Cross-Attentive Transformer for Audio to Motion Generation","display_name":"SpeechCAT: Cross-Attentive Transformer for Audio to Motion Generation","publication_year":2025,"publication_date":"2025-03-04","ids":{"openalex":"https://openalex.org/W4410297023","doi":"https://doi.org/10.1109/hri61500.2025.10974020"},"language":"en","primary_location":{"id":"doi:10.1109/hri61500.2025.10974020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10974020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5117518585","display_name":"Sebastian Deaconu","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Sebastian Deaconu","raw_affiliation_strings":["Delft University of Technology,Delft,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Delft,Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088314307","display_name":"Xiangwei Shi","orcid":"https://orcid.org/0000-0003-0711-2147"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xiangwei Shi","raw_affiliation_strings":["Delft University of Technology,Delft,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Delft,Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117518586","display_name":"Thomas Markhorst","orcid":null},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Thomas Markhorst","raw_affiliation_strings":["Delft University of Technology,Delft,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Delft,Netherlands","institution_ids":["https://openalex.org/I98358874"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055570308","display_name":"Jouh Yeong Chew","orcid":"https://orcid.org/0000-0001-7906-2113"},"institutions":[{"id":"https://openalex.org/I1283473643","display_name":"Honda (Japan)","ror":"https://ror.org/03jzay846","country_code":"JP","type":"company","lineage":["https://openalex.org/I1283473643"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jouh Yeong Chew","raw_affiliation_strings":["Honda Research Institute Japan,Saitama,Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Honda Research Institute Japan,Saitama,Japan","institution_ids":["https://openalex.org/I1283473643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010012679","display_name":"Xucong Zhang","orcid":"https://orcid.org/0000-0002-8368-3542"},"institutions":[{"id":"https://openalex.org/I98358874","display_name":"Delft University of Technology","ror":"https://ror.org/02e2c7k09","country_code":"NL","type":"education","lineage":["https://openalex.org/I98358874"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Xucong Zhang","raw_affiliation_strings":["Delft University of Technology,Delft,Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Delft University of Technology,Delft,Netherlands","institution_ids":["https://openalex.org/I98358874"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09432843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1284","last_page":"1288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9643999934196472,"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"}},"topics":[{"id":"https://openalex.org/T12290","display_name":"Human Motion and Animation","score":0.9643999934196472,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.949999988079071,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6578875184059143},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6576438546180725},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.40166032314300537},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.2636112570762634},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1332990527153015},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.09016764163970947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6578875184059143},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6576438546180725},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.40166032314300537},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.2636112570762634},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1332990527153015},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.09016764163970947}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hri61500.2025.10974020","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hri61500.2025.10974020","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 20th ACM/IEEE International Conference on Human-Robot Interaction (HRI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Audio-to-motion":[0],"generation":[1,27],"is":[2],"an":[3],"important":[4],"task":[5],"with":[6,141],"applications":[7],"in":[8,19,134],"virtual":[9],"avatar":[10],"creation":[11],"for":[12],"XR":[13],"systems":[14],"and":[15,49,79,85,138,144],"intelligent":[16],"robot":[17],"control":[18],"daily":[20],"life":[21],"scenarios.":[22],"However,":[23],"most":[24],"existing":[25],"motion":[26],"methods":[28],"rely":[29],"on":[30],"a":[31,60,93],"single":[32],"encoder-decoder":[33,68],"architecture":[34],"to":[35,45,70,96,105],"model":[36,72,106],"all":[37],"body":[38,89,112],"parts":[39],"simultaneously,":[40],"which":[41],"limits":[42],"their":[43,99],"ability":[44],"capture":[46,82],"the":[47,73,76,83,107,116,124],"diverse":[48],"complex":[50],"motions":[51,74,140],"exhibited":[52],"by":[53],"humans.":[54],"In":[55],"this":[56],"paper,":[57],"we":[58,91],"propose":[59],"novel":[61],"method,":[62],"SpeechCAT,":[63],"that":[64],"employs":[65],"three":[66],"separate":[67],"modules":[69],"individually":[71],"of":[75,110,126],"face,":[77,142],"body,":[78,143],"hands.":[80],"To":[81],"relationships":[84],"synchronization":[86],"among":[87],"these":[88],"parts,":[90],"introduce":[92],"cross-attention":[94],"mechanism":[95],"effectively":[97],"learn":[98],"correlations.":[100],"SpeechCAT":[101,127],"ensures":[102],"sufficient":[103],"capacity":[104],"unique":[108],"characteristics":[109],"each":[111],"part":[113],"while":[114],"preserving":[115],"coherence":[117],"between":[118],"them.":[119],"Our":[120],"experimental":[121],"results":[122],"demonstrate":[123],"superiority":[125],"over":[128],"baseline":[129],"methods,":[130],"highlighting":[131],"its":[132],"effectiveness":[133],"generating":[135],"diverse,":[136],"realistic,":[137],"synchronized":[139],"hand":[145],"parts.":[146]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}