{"id":"https://openalex.org/W4387968088","doi":"https://doi.org/10.1145/3581783.3612851","title":"Multi-Layer Acoustic & Linguistic Feature Fusion for ComParE-23 Emotion and Requests Challenge","display_name":"Multi-Layer Acoustic & Linguistic Feature Fusion for ComParE-23 Emotion and Requests Challenge","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387968088","doi":"https://doi.org/10.1145/3581783.3612851"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5093130606","display_name":"Siddhant R. Viksit","orcid":"https://orcid.org/0009-0004-5538-9735"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Siddhant R. Viksit","raw_affiliation_strings":["Indraprastha Institute of Technology Delhi, Delhi, India"],"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075520691","display_name":"Vinayak Abrol","orcid":"https://orcid.org/0000-0001-8149-8151"},"institutions":[{"id":"https://openalex.org/I119939252","display_name":"Indraprastha Institute of Information Technology Delhi","ror":"https://ror.org/03vfp4g33","country_code":"IN","type":"education","lineage":["https://openalex.org/I119939252"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vinayak Abrol","raw_affiliation_strings":["Indraprastha Institute of Technology Delhi, Delhi, India"],"affiliations":[{"raw_affiliation_string":"Indraprastha Institute of Technology Delhi, Delhi, India","institution_ids":["https://openalex.org/I119939252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5093130606"],"corresponding_institution_ids":["https://openalex.org/I119939252"],"apc_list":null,"apc_paid":null,"fwci":0.3491,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6625136,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"9492","last_page":"9495"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9990000128746033,"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":0.7738400101661682},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.6952137351036072},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.6598379015922546},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5919268727302551},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5859887003898621},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5459647178649902},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5337138175964355},{"id":"https://openalex.org/keywords/standard-deviation","display_name":"Standard deviation","score":0.4280153214931488},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4158029556274414},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.41319432854652405},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38349294662475586},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3757355511188507},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08275607228279114},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.07558172941207886},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06993234157562256}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7738400101661682},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6952137351036072},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.6598379015922546},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5919268727302551},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5859887003898621},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5459647178649902},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5337138175964355},{"id":"https://openalex.org/C22679943","wikidata":"https://www.wikidata.org/wiki/Q159375","display_name":"Standard deviation","level":2,"score":0.4280153214931488},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4158029556274414},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41319432854652405},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38349294662475586},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3757355511188507},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08275607228279114},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.07558172941207886},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06993234157562256},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3612851","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612851","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G313305162","display_name":null,"funder_award_id":"FAP-50","funder_id":"https://openalex.org/F4320307774","funder_display_name":"JPMorgan Chase and Company"}],"funders":[{"id":"https://openalex.org/F4320307774","display_name":"JPMorgan Chase and Company","ror":"https://ror.org/01x3kkr08"},{"id":"https://openalex.org/F4320322753","display_name":"Infosys Foundation","ror":"https://ror.org/03bs18y54"},{"id":"https://openalex.org/F4320330597","display_name":"Indraprastha Institute of Information Technology, Delhi","ror":"https://ror.org/03vfp4g33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2085662862","https://openalex.org/W2794506738","https://openalex.org/W2972717745","https://openalex.org/W3209984917","https://openalex.org/W4225328536","https://openalex.org/W4387968410","https://openalex.org/W6931421704"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"The":[0,17],"ACM":[1],"Multimedia":[2],"2023":[3],"ComParE":[4],"challenge":[5,18],"focuses":[6],"on":[7,129],"classification/regression":[8],"tasks":[9],"for":[10,101,119],"spoken":[11],"customer-agent":[12],"and":[13,83,93,111,132],"emotionally":[14],"rated":[15],"conversations.":[16,105],"baseline":[19,128],"systems":[20,117],"build":[21],"upon":[22],"the":[23,43,47,60,64,77,127,130],"recent":[24],"advancement":[25],"in":[26],"large-scale":[27],"supervised/unsupervised":[28],"foundational":[29],"acoustic":[30,68,98],"models":[31,69],"that":[32],"demonstrate":[33],"consistently":[34],"good":[35],"performance":[36,48,124],"across":[37],"tasks.":[38],"In":[39,58],"this":[40],"work,":[41],"with":[42,90,97],"aim":[44],"of":[45,80,109],"improving":[46],"further,":[49],"we":[50,75,113],"present":[51,114],"a":[52],"novel":[53],"multi-layer":[54,71],"feature":[55],"fusion":[56,96],"method.":[57],"particular,":[59],"proposed":[61],"approach":[62],"leverages":[63],"hierarchical":[65],"information":[66],"from":[67],"using":[70],"statistics":[72],"pooling,":[73],"where":[74],"compute":[76],"weighted":[78],"sum":[79],"layer-wise":[81],"(mean":[82],"standard":[84],"deviation)":[85],"features.":[86],"We":[87],"further":[88],"experimented":[89],"linguistic":[91],"features":[92],"their":[94],"late":[95],"features,":[99,112],"especially":[100],"subtasks":[102],"involving":[103],"complex":[104],"Exploring":[106],"various":[107],"combinations":[108],"methods":[110],"four":[115],"different":[116],"tailored":[118],"each":[120],"subchallenge,":[121],"demonstrating":[122],"significant":[123],"gains":[125],"over":[126],"development":[131],"test":[133],"set.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}