{"id":"https://openalex.org/W4408354789","doi":"https://doi.org/10.1109/icassp49660.2025.10889429","title":"Active Listener: Continuous Generation of Listener\u2019s Head Motion Response in Dyadic Interactions","display_name":"Active Listener: Continuous Generation of Listener\u2019s Head Motion Response in Dyadic Interactions","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408354789","doi":"https://doi.org/10.1109/icassp49660.2025.10889429"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/345947/1/345947.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049298856","display_name":"Bishal Ghosh","orcid":"https://orcid.org/0000-0002-0502-7267"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bishal Ghosh","raw_affiliation_strings":["University of Glasgow,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100748983","display_name":"Liying Li","orcid":"https://orcid.org/0000-0003-4200-0669"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Emma Li","raw_affiliation_strings":["University of Glasgow,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021354054","display_name":"Tanaya Guha","orcid":"https://orcid.org/0000-0003-2167-4891"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tanaya Guha","raw_affiliation_strings":["University of Glasgow,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,UK","institution_ids":["https://openalex.org/I7882870"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I7882870"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.46000000834465027,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.46000000834465027,"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/T12031","display_name":"Speech and dialogue systems","score":0.42800000309944153,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.3837999999523163,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/computer-science","display_name":"Computer science","score":0.6020234227180481},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.5417791604995728},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.515017032623291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37457573413848877},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34804850816726685},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.07929810881614685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6020234227180481},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.5417791604995728},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.515017032623291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37457573413848877},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34804850816726685},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.07929810881614685},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889429","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889429","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:345947","is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/view/author/70763.html>,","pdf_url":"https://eprints.gla.ac.uk/345947/1/345947.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:345947","is_oa":true,"landing_page_url":"http://eprints.gla.ac.uk/view/author/70763.html>,","pdf_url":"https://eprints.gla.ac.uk/345947/1/345947.pdf","source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G213999160","display_name":"DTP 2224 University of Glasgow","funder_award_id":"EP/W524359/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4408354789.pdf"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W1780788718","https://openalex.org/W1991123335","https://openalex.org/W2146334809","https://openalex.org/W2239141610","https://openalex.org/W2889445100","https://openalex.org/W2967714332","https://openalex.org/W3120931376","https://openalex.org/W3162387328","https://openalex.org/W3199141871","https://openalex.org/W4205725129","https://openalex.org/W4225760288","https://openalex.org/W4285414370","https://openalex.org/W4385877119","https://openalex.org/W4391021755","https://openalex.org/W4404893046","https://openalex.org/W6738964360","https://openalex.org/W6780218876"],"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":{"A":[0],"key":[1],"component":[2],"of":[3,35,50,56,94],"dyadic":[4,127],"spoken":[5],"interactions":[6],"is":[7,106,161],"the":[8,23,33,48,62,95,126,131],"contextually":[9],"relevant":[10],"non-verbal":[11],"gestures,":[12,38],"such":[13],"as":[14,83],"head":[15,53,88,116],"movements":[16],"that":[17,78,135],"reflect":[18],"a":[19,44,57,73,139,146],"listener\u2019s":[20,40],"response":[21,41,55,60],"to":[22,61,118],"interlocutor\u2019s":[24,80],"speech.":[25],"Although":[26],"significant":[27],"progress":[28],"has":[29,42],"been":[30],"made":[31],"in":[32,59,65,97,154],"context":[34],"generating":[36,39,51],"co-speech":[37],"remained":[43],"challenge.":[45],"We":[46],"introduce":[47],"task":[49],"continuous":[52],"motion":[54,117],"listener":[58,96],"speaker\u2019s":[63],"speech":[64,81],"real":[66,98],"time.":[67,99],"To":[68],"this":[69],"end,":[70],"we":[71],"propose":[72],"graph-based":[74],"end-to-end":[75],"crossmodal":[76],"model":[77,137],"takes":[79],"audio":[82],"input":[84],"and":[85,121,145],"directly":[86],"generates":[87],"pose":[89],"angles":[90],"(roll,":[91],"pitch,":[92],"yaw)":[93],"Different":[100],"from":[101],"previous":[102],"work,":[103],"our":[104,136],"approach":[105],"completely":[107],"data-driven,":[108],"does":[109],"not":[110],"require":[111],"manual":[112],"annotations":[113],"or":[114],"oversimplify":[115],"merely":[119],"nods":[120],"shakes.":[122],"Extensive":[123],"evaluation":[124],"on":[125,130],"interaction":[128,157],"sessions":[129],"IEMOCAP":[132],"dataset":[133],"shows":[134],"produces":[138],"low":[140],"overall":[141],"error":[142],"(4.5":[143],"degrees)":[144],"high":[147],"frame":[148],"rate,":[149],"thereby":[150],"indicating":[151],"its":[152],"deployability":[153],"real-world":[155],"human-robot":[156],"systems.":[158],"Our":[159],"code":[160],"available":[162],"at":[163],"-":[164],"https://github.":[165],"com/bigzen/Active-Listener":[166]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
