{"id":"https://openalex.org/W7225830707","doi":"https://doi.org/10.20944/preprints202607.2237.v2","title":"Embodied Audio Intelligence: Foundations, Capabilities, and Opportunities","display_name":"Embodied Audio Intelligence: Foundations, Capabilities, and Opportunities","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225830707","doi":"https://doi.org/10.20944/preprints202607.2237.v2"},"language":"en","primary_location":{"id":"doi:10.20944/preprints202607.2237.v2","doi":"https://doi.org/10.20944/preprints202607.2237.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202607.2237.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.20944/preprints202607.2237.v2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045616176","display_name":"Wentao Lei","orcid":"https://orcid.org/0009-0008-4577-396X","observed_orcids":["https://orcid.org/0009-0008-4577-396X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wentao Lei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144440086","display_name":"Tianxin Xie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tianxin Xie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126262825","display_name":"Kai Jiang","orcid":"https://orcid.org/0009-0008-3936-1221","observed_orcids":["https://orcid.org/0009-0008-3936-1221","https://orcid.org/0009-0006-1707-1034"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kai Jiang","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0006-1707-1034","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5158791006","display_name":"Hui Xiong","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hui Xiong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5161460327","display_name":"Li Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Li Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5161460327"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T10860","display_name":"Speech and Audio Processing","score":0.21770000457763672,"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":0.21770000457763672,"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/T11309","display_name":"Music and Audio Processing","score":0.10360000282526016,"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":0.09969999641180038,"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":[],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.9085000157356262},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.6636000275611877},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5110999941825867},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4490000009536743},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.31779998540878296},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.2985999882221222},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.290800005197525},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2799000144004822},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.25529998540878296}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.20944/preprints202607.2237.v2","doi":"https://doi.org/10.20944/preprints202607.2237.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202607.2237.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.20944/preprints202607.2237.v2","doi":"https://doi.org/10.20944/preprints202607.2237.v2","is_oa":true,"landing_page_url":"https://doi.org/10.20944/preprints202607.2237.v2","pdf_url":null,"source":{"id":"https://openalex.org/S6309402219","display_name":"Preprints.org","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Embodied":[0],"intelligence":[1],"requires":[2],"perception,":[3,64],"reasoning,":[4,65],"action,":[5],"and":[6,16,24,56,66,78,85,95],"interaction,":[7],"yet":[8],"existing":[9],"systems":[10],"predominantly":[11],"rely":[12],"on":[13],"vision,":[14],"text,":[15],"proprioception.":[17],"Audio":[18],"offers":[19],"complementary":[20],"evidence":[21],"about":[22],"environments":[23],"human":[25],"intentions,":[26],"but":[27],"research":[28,89],"remains":[29],"fragmented.":[30],"From":[31],"a":[32,60,87],"novel":[33],"perspective":[34],"linking":[35],"auditory":[36,70],"roles":[37],"to":[38],"behavioral":[39],"functions,":[40],"this":[41],"survey":[42,82],"establishes":[43,86],"the":[44,81],"first":[45],"unified":[46],"framework":[47],"for":[48,91],"embodied":[49,97],"audio":[50,98],"intelligence.":[51,99],"It":[52],"brings":[53],"physical,":[54],"semantic,":[55],"socio-affective":[57],"capabilities":[58],"into":[59],"common":[61],"account":[62],"of":[63],"interaction":[67],"through":[68],"continuous":[69],"feedback":[71],"loops.":[72],"By":[73],"synthesizing":[74],"foundations,":[75],"methods,":[76],"applications,":[77],"evaluation":[79],"resources,":[80],"identifies":[83],"challenges":[84],"systematic":[88],"agenda":[90],"advancing":[92],"robust,":[93],"adaptive,":[94],"interactive":[96]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
