{"id":"https://openalex.org/W4386272861","doi":"https://doi.org/10.1145/3581783.3612855","title":"Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks","display_name":"Effect of Attention and Self-Supervised Speech Embeddings on Non-Semantic Speech Tasks","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4386272861","doi":"https://doi.org/10.1145/3581783.3612855"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612855","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":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.14359","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075681305","display_name":"Payal Mohapatra","orcid":"https://orcid.org/0000-0002-3534-9136"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Payal Mohapatra","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-3534-9136","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101484748","display_name":"Akash Pandey","orcid":"https://orcid.org/0009-0003-5324-8667"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Akash Pandey","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0009-0003-5324-8667","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101443153","display_name":"Yueyuan Sui","orcid":"https://orcid.org/0009-0007-1602-5359"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yueyuan Sui","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0009-0007-1602-5359","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020896290","display_name":"Qi Zhu","orcid":"https://orcid.org/0000-0002-7700-4099"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qi Zhu","raw_affiliation_strings":["Northwestern University, Evanston, IL, USA"],"raw_orcid":"https://orcid.org/0000-0002-7700-4099","affiliations":[{"raw_affiliation_string":"Northwestern University, Evanston, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9511","last_page":"9515"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12032","display_name":"Multisensory perception and integration","score":0.9804999828338623,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9745000004768372,"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":0.7762521505355835},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6302329897880554},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5896561145782471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5116808414459229},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4240691065788269}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7762521505355835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6302329897880554},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5896561145782471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5116808414459229},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4240691065788269}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612855","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612855","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"},{"id":"pmh:oai:arXiv.org:2308.14359","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14359","pdf_url":"https://arxiv.org/pdf/2308.14359","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.14359","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.14359","pdf_url":"https://arxiv.org/pdf/2308.14359","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"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":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G6305127867","display_name":null,"funder_award_id":"1834701, 2038853","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4386272861.pdf"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2078483536","https://openalex.org/W2146334809","https://openalex.org/W2180587936","https://openalex.org/W2612690371","https://openalex.org/W2757184610","https://openalex.org/W2793383796","https://openalex.org/W2905841571","https://openalex.org/W2950518992","https://openalex.org/W3036601975","https://openalex.org/W3089365109","https://openalex.org/W3112736871","https://openalex.org/W3119048198","https://openalex.org/W3169320628","https://openalex.org/W3198528147","https://openalex.org/W3209059054","https://openalex.org/W4225635674","https://openalex.org/W4226217762","https://openalex.org/W4292402161","https://openalex.org/W4323896824","https://openalex.org/W4324382619","https://openalex.org/W4327928277","https://openalex.org/W4361994820","https://openalex.org/W4367692173","https://openalex.org/W4372259942","https://openalex.org/W4372337800","https://openalex.org/W4385245566","https://openalex.org/W4387968410","https://openalex.org/W6801377430"],"related_works":["https://openalex.org/W3204019825","https://openalex.org/W2981428355","https://openalex.org/W1834994814","https://openalex.org/W2041273198","https://openalex.org/W1599055764","https://openalex.org/W2131711534","https://openalex.org/W2149163000","https://openalex.org/W2962858469","https://openalex.org/W2289873871","https://openalex.org/W2559040841"],"abstract_inverted_index":{"Human":[0],"emotion":[1,13,104],"understanding":[2,14],"is":[3,20,107],"pivotal":[4],"in":[5,55,117,124],"making":[6],"conversational":[7],"technology":[8],"mainstream.":[9],"We":[10,80],"view":[11],"speech":[12,38,96,101],"as":[15,40],"a":[16,21,41,108,134],"perception":[17,76],"task":[18,111],"which":[19],"more":[22],"realistic":[23],"setting.":[24],"With":[25],"varying":[26],"contexts":[27],"(languages,":[28],"demographics":[29],"etc.)":[30],"different":[31,87],"share":[32],"of":[33,46,65,72,77,86],"people":[34],"perceive":[35],"the":[36,47,56,83,118,125,143],"same":[37],"segment":[39],"non-unanimous":[42],"emotion.":[43,79],"As":[44],"part":[45],"ACM":[48],"Multimedia":[49],"2023":[50],"Computational":[51],"Paralinguistics":[52],"ChallengE":[53],"(ComParE)":[54],"EMotion":[57],"Share":[58],"track,":[59],"we":[60],"leverage":[61],"their":[62,91],"rich":[63],"dataset":[64],"multilingual":[66,114],"speakers":[67],"and":[68,121],"multi-label":[69],"regression":[70,126],"target":[71,119],"'emotion":[73],"share'":[74],"or":[75],"that":[78,82,131],"demonstrate":[81],"training":[84],"scheme":[85],"foundation":[88],"models":[89],"dictates":[90],"effectiveness":[92],"for":[93,99],"tasks":[94,102],"beyond":[95],"recognition,":[97],"especially":[98],"non-semantic":[100],"like":[103],"understanding.":[105],"This":[106],"very":[109],"complex":[110],"due":[112],"to":[113],"speakers,":[115],"variability":[116],"labels,":[120],"inherent":[122],"imbalance":[123],"dataset.":[127],"Our":[128],"results":[129],"show":[130],"HuBERT-Large":[132],"with":[133],"self-attention-based":[135],"light-weight":[136],"sequence":[137],"model":[138],"provides":[139],"4.6%":[140],"improvement":[141],"over":[142],"reported":[144],"baseline.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2023-08-31T00:00:00"}