{"id":"https://openalex.org/W4402402557","doi":"https://doi.org/10.1109/ialp63756.2024.10661182","title":"MDG:Multilingual Co-speech Gesture Generation with Low-level Audio Representation and Diffusion Models","display_name":"MDG:Multilingual Co-speech Gesture Generation with Low-level Audio Representation and Diffusion Models","publication_year":2024,"publication_date":"2024-08-04","ids":{"openalex":"https://openalex.org/W4402402557","doi":"https://doi.org/10.1109/ialp63756.2024.10661182"},"language":"en","primary_location":{"id":"doi:10.1109/ialp63756.2024.10661182","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ialp63756.2024.10661182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","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/A5107854645","display_name":"Jie Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jie Yang","raw_affiliation_strings":["Inner Mongolia University,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University,Hohhot,China"],"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,Hohhot,China","institution_ids":["https://openalex.org/I2722730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5107854645"],"corresponding_institution_ids":["https://openalex.org/I2722730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16564943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"210","last_page":"215"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9988999962806702,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9972000122070312,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7147579193115234},{"id":"https://openalex.org/keywords/gesture","display_name":"Gesture","score":0.6882057189941406},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6011402010917664},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5991677045822144},{"id":"https://openalex.org/keywords/diffusion","display_name":"Diffusion","score":0.44521671533584595},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.25149112939834595}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7147579193115234},{"id":"https://openalex.org/C207347870","wikidata":"https://www.wikidata.org/wiki/Q371174","display_name":"Gesture","level":2,"score":0.6882057189941406},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6011402010917664},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5991677045822144},{"id":"https://openalex.org/C69357855","wikidata":"https://www.wikidata.org/wiki/Q163214","display_name":"Diffusion","level":2,"score":0.44521671533584595},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25149112939834595},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ialp63756.2024.10661182","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ialp63756.2024.10661182","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Asian Language Processing (IALP)","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":33,"referenced_works":["https://openalex.org/W2140304104","https://openalex.org/W2191779130","https://openalex.org/W2559085405","https://openalex.org/W2884225676","https://openalex.org/W2901285216","https://openalex.org/W2922298118","https://openalex.org/W2962795401","https://openalex.org/W3009385801","https://openalex.org/W3036167779","https://openalex.org/W3083173864","https://openalex.org/W3099073275","https://openalex.org/W3125775899","https://openalex.org/W3162926177","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W4221142137","https://openalex.org/W4249736682","https://openalex.org/W4292945985","https://openalex.org/W4293352083","https://openalex.org/W4308222758","https://openalex.org/W4310695675","https://openalex.org/W4312674262","https://openalex.org/W4364377334","https://openalex.org/W4385245566","https://openalex.org/W4385764101","https://openalex.org/W4386076103","https://openalex.org/W4386270206","https://openalex.org/W4391305822","https://openalex.org/W4402703119","https://openalex.org/W6779823529","https://openalex.org/W6795288823","https://openalex.org/W6810007534","https://openalex.org/W6810793953"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2066003895","https://openalex.org/W2537963312","https://openalex.org/W2537762514","https://openalex.org/W2349788282","https://openalex.org/W577271088","https://openalex.org/W2120801881","https://openalex.org/W1982853263","https://openalex.org/W1974473538"],"abstract_inverted_index":{"Co-speech":[0],"gesture":[1,54,90],"generation":[2,55],"is":[3],"crucial":[4],"for":[5,37,52],"enhancing":[6],"human-computer":[7],"interaction.":[8],"Most":[9],"existing":[10],"research":[11],"focuses":[12],"on":[13,30],"English,":[14],"overlooking":[15],"multilingual":[16,58,76,88],"speech":[17],"and":[18,69],"the":[19],"ability":[20],"to":[21,65,74],"generalize":[22],"across":[23],"languages.":[24,39],"Additionally,":[25],"these":[26,42],"studies":[27],"often":[28],"rely":[29],"pre-trained":[31],"audio":[32,72],"feature":[33],"extraction":[34],"models,":[35],"insufficient":[36],"non-English":[38],"To":[40],"address":[41],"issues,":[43],"we":[44],"introduce":[45],"MDG,":[46],"a":[47,57],"novel":[48],"diffusion":[49],"model-based":[50],"method":[51],"speech-driven":[53],"using":[56],"dataset.":[59],"Our":[60],"approach":[61],"incorporates":[62],"Language":[63],"ID":[64],"distinguish":[66],"between":[67],"languages":[68],"utilizes":[70],"low-level":[71],"features":[73],"improve":[75],"generalization.":[77],"Extensive":[78],"experiments":[79],"demonstrate":[80],"that":[81],"MDG":[82],"significantly":[83],"outperforms":[84],"baseline":[85],"models":[86],"in":[87],"co-speech":[89],"generation.":[91],"For":[92],"more":[93],"details,":[94],"please":[95],"visit":[96],"our":[97],"demo":[98],"page<sup":[99],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[100],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[101]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
