{"id":"https://openalex.org/W4372260525","doi":"https://doi.org/10.1109/icassp49357.2023.10096097","title":"Continuous Interaction with A Smart Speaker via Low-Dimensional Embeddings of Dynamic Hand Pose","display_name":"Continuous Interaction with A Smart Speaker via Low-Dimensional Embeddings of Dynamic Hand Pose","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372260525","doi":"https://doi.org/10.1109/icassp49357.2023.10096097"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.gla.ac.uk/view/author/61957.html>,","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029582812","display_name":"Songpei Xu","orcid":"https://orcid.org/0009-0001-5735-8674"},"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":"Songpei Xu","raw_affiliation_strings":["University of Glasgow,School of Computing Science,UK","School of Computing Science, University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science,UK","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076295200","display_name":"Chaitanya Kaul","orcid":"https://orcid.org/0000-0003-4893-6222"},"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":"Chaitanya Kaul","raw_affiliation_strings":["University of Glasgow,School of Computing Science,UK","School of Computing Science, University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science,UK","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026473068","display_name":"Xuri Ge","orcid":"https://orcid.org/0000-0002-3925-4951"},"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":"Xuri Ge","raw_affiliation_strings":["University of Glasgow,School of Computing Science,UK","School of Computing Science, University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science,UK","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, University of Glasgow, UK","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070918132","display_name":"Roderick Murray\u2010Smith","orcid":"https://orcid.org/0000-0003-4228-7962"},"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":"Roderick Murray-Smith","raw_affiliation_strings":["University of Glasgow,School of Computing Science,UK","School of Computing Science, University of Glasgow, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Glasgow,School of Computing Science,UK","institution_ids":["https://openalex.org/I7882870"]},{"raw_affiliation_string":"School of Computing Science, 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":0.5709,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66407612,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T11398","display_name":"Hand Gesture Recognition Systems","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1709","display_name":"Human-Computer Interaction"},"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.9970999956130981,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/gesture","display_name":"Gesture","score":0.8676306009292603},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.8584722280502319},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.805883526802063},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.737041175365448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5698582530021667},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5478111505508423},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5336561799049377},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5162403583526611},{"id":"https://openalex.org/keywords/gesture-recognition","display_name":"Gesture recognition","score":0.4548628032207489},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34902164340019226},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.2509855628013611}],"concepts":[{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.8676306009292603},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8584722280502319},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.805883526802063},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.737041175365448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698582530021667},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5478111505508423},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5336561799049377},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5162403583526611},{"id":"https://openalex.org/C159437735","wikidata":"https://www.wikidata.org/wiki/Q1519524","display_name":"Gesture recognition","level":3,"score":0.4548628032207489},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34902164340019226},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2509855628013611}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096097","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10096097","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.gla.ac.uk:298426","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/61957.html>,","pdf_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"}],"best_oa_location":{"id":"pmh:oai:eprints.gla.ac.uk:298426","is_oa":true,"landing_page_url":"https://eprints.gla.ac.uk/view/author/61957.html>,","pdf_url":null,"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":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference Proceedings"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.75,"display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1989121949","display_name":null,"funder_award_id":"EP/R018634/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G8703912931","display_name":null,"funder_award_id":"EP/M01326X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W119121488","https://openalex.org/W1522301498","https://openalex.org/W1921523184","https://openalex.org/W1969411960","https://openalex.org/W1989571016","https://openalex.org/W2020984122","https://openalex.org/W2105806403","https://openalex.org/W2119344328","https://openalex.org/W2133739410","https://openalex.org/W2165093411","https://openalex.org/W2560609797","https://openalex.org/W2760367275","https://openalex.org/W2786672974","https://openalex.org/W2796897898","https://openalex.org/W2803187616","https://openalex.org/W2919234133","https://openalex.org/W2963218601","https://openalex.org/W3024333932","https://openalex.org/W3036954260","https://openalex.org/W3080070928","https://openalex.org/W3183325202","https://openalex.org/W3206003474","https://openalex.org/W3208089751","https://openalex.org/W3210279979","https://openalex.org/W3214813988","https://openalex.org/W4210792305","https://openalex.org/W4226236225","https://openalex.org/W4285259512","https://openalex.org/W4288327876","https://openalex.org/W6631190155","https://openalex.org/W6640185926","https://openalex.org/W6748816842","https://openalex.org/W6750267149","https://openalex.org/W6751420435","https://openalex.org/W6763422710","https://openalex.org/W6764045775","https://openalex.org/W6779442434","https://openalex.org/W6808079559","https://openalex.org/W6810874864"],"related_works":["https://openalex.org/W2902873204","https://openalex.org/W2185750513","https://openalex.org/W2010878661","https://openalex.org/W3147379364","https://openalex.org/W2026258298","https://openalex.org/W3204639664","https://openalex.org/W2970836791","https://openalex.org/W2805039731","https://openalex.org/W2989699735","https://openalex.org/W4321789545"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,21,47,73,110],"new":[4],"continuous":[5],"interaction":[6,59,93],"strategy":[7],"with":[8,60,103,125],"visual":[9],"feedback":[10],"of":[11,122],"hand":[12,35,135],"pose":[13,36,50],"and":[14,18],"mid-air":[15],"gesture":[16],"recognition":[17],"control":[19,90],"for":[20,58,115],"smart":[22],"music":[23,62,69,96],"speaker,":[24],"which":[25,86],"utilizes":[26],"only":[27],"2":[28,48],"video":[29],"frames":[30],"to":[31,72,83,89,108],"recognize":[32],"gestures.":[33,117],"Frame-based":[34],"features":[37],"from":[38],"MediaPipe":[39],"Hands,":[40],"containing":[41],"21":[42],"landmarks,":[43],"are":[44,87],"embedded":[45],"into":[46],"dimensional":[49],"space":[51,57,114],"by":[52,66,132],"an":[53],"autoencoder.":[54],"The":[55],"corresponding":[56],"the":[61,91,101,104,120,123],"content":[63],"is":[64,80],"created":[65],"embedding":[67,113],"high-dimensional":[68],"track":[70],"profiles":[71],"compatible":[74],"two-dimensional":[75],"embedding.":[76],"A":[77],"PointNet-based":[78],"model":[79],"then":[81],"applied":[82],"classify":[84],"gestures":[85],"used":[88],"device":[92],"or":[94],"explore":[95],"spaces.":[97],"By":[98],"jointly":[99],"optimising":[100],"autoencoder":[102],"classifier,":[105],"we":[106],"manage":[107],"learn":[109],"more":[111],"useful":[112],"discriminating":[116],"We":[118],"demonstrate":[119],"functionality":[121],"system":[124],"experienced":[126],"users":[127],"selecting":[128],"different":[129],"musical":[130],"moods":[131],"varying":[133],"their":[134],"pose.":[136]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-02T09:51:11.867554","created_date":"2025-10-10T00:00:00"}