{"id":"https://openalex.org/W7155402974","doi":"https://doi.org/10.1016/j.specom.2026.103409","title":"Joint acoustic\u2013semantic alignment network for advanced speech emotion recognition","display_name":"Joint acoustic\u2013semantic alignment network for advanced speech emotion recognition","publication_year":2026,"publication_date":"2026-04-23","ids":{"openalex":"https://openalex.org/W7155402974","doi":"https://doi.org/10.1016/j.specom.2026.103409"},"language":"en","primary_location":{"id":"doi:10.1016/j.specom.2026.103409","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103409","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-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/A5102583702","display_name":"Yihong Meng","orcid":"https://orcid.org/0009-0000-3581-7537"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Meng","raw_affiliation_strings":["Shandong Normal University, China"],"raw_orcid":"https://orcid.org/0009-0000-3581-7537","affiliations":[{"raw_affiliation_string":"Shandong Normal University, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370862","display_name":"Hong Wang","orcid":"https://orcid.org/0000-0001-5727-7834"},"institutions":[{"id":"https://openalex.org/I28006308","display_name":"Shandong Normal University","ror":"https://ror.org/01wy3h363","country_code":"CN","type":"education","lineage":["https://openalex.org/I28006308"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hong Wang","raw_affiliation_strings":["Shandong Normal University, China"],"raw_orcid":"https://orcid.org/0000-0001-5727-7834","affiliations":[{"raw_affiliation_string":"Shandong Normal University, China","institution_ids":["https://openalex.org/I28006308"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134381223","display_name":"Yanshen Sun","orcid":null},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanshen Sun","raw_affiliation_strings":["Virginia Tech, United States of America"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Virginia Tech, United States of America","institution_ids":["https://openalex.org/I859038795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5134422072","display_name":"Aijun Li","orcid":null},"institutions":[{"id":"https://openalex.org/I114218197","display_name":"Chinese Academy of Social Sciences","ror":"https://ror.org/05bxbmy32","country_code":"CN","type":"facility","lineage":["https://openalex.org/I114218197"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Aijun Li","raw_affiliation_strings":["Chinese Academy of Social Sciences, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Social Sciences, China","institution_ids":["https://openalex.org/I114218197"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100370862"],"corresponding_institution_ids":["https://openalex.org/I28006308"],"apc_list":{"value":2610,"currency":"USD","value_usd":2610},"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.43199864,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"181","issue":null,"first_page":"103409","last_page":"103409"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9599999785423279,"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":0.9599999785423279,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.004999999888241291,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.00430000014603138,"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/joint","display_name":"Joint (building)","score":0.6753000020980835},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5181000232696533},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5087000131607056},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.4657000005245209},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.45879998803138733},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4440999925136566},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4207000136375427},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.366100013256073}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363000154495239},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.6753000020980835},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6216999888420105},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5181000232696533},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.4657000005245209},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.45879998803138733},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4440999925136566},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43059998750686646},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.366100013256073},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3537999987602234},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.3418000042438507},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34040001034736633},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31220000982284546},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.30329999327659607},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C48007421","wikidata":"https://www.wikidata.org/wiki/Q676252","display_name":"Motion capture","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C131584629","wikidata":"https://www.wikidata.org/wiki/Q4308705","display_name":"Coupling (piping)","level":2,"score":0.2524000108242035},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1016/j.specom.2026.103409","is_oa":false,"landing_page_url":"https://doi.org/10.1016/j.specom.2026.103409","pdf_url":null,"source":{"id":"https://openalex.org/S128025751","display_name":"Speech Communication","issn_l":"0167-6393","issn":["0167-6393","1872-7182"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Speech Communication","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6832069158554077}],"awards":[{"id":"https://openalex.org/G3599276463","display_name":null,"funder_award_id":"62573277","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6851897821","display_name":"\u9762\u5411\u7535\u5b50\u75c5\u5386\u52a8\u6001\u5efa\u6a21\u7684\u53ef\u89e3\u91ca\u6df1\u5ea6\u5b66\u4e60\u65b9\u6cd5\u7814\u7a76","funder_award_id":"62072290","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1983424905","https://openalex.org/W1995562189","https://openalex.org/W2001619934","https://openalex.org/W2087618018","https://openalex.org/W2102625004","https://openalex.org/W2112796928","https://openalex.org/W2119417805","https://openalex.org/W2119821739","https://openalex.org/W2125838338","https://openalex.org/W2128728535","https://openalex.org/W2146334809","https://openalex.org/W2295598076","https://openalex.org/W2625297138","https://openalex.org/W2787584921","https://openalex.org/W2892071465","https://openalex.org/W2963341956","https://openalex.org/W2963686995","https://openalex.org/W2963785564","https://openalex.org/W2963800675","https://openalex.org/W2981731882","https://openalex.org/W2999908512","https://openalex.org/W3013363049","https://openalex.org/W3126963415","https://openalex.org/W3160016036","https://openalex.org/W3160183718","https://openalex.org/W3160222702","https://openalex.org/W3186192207","https://openalex.org/W4221162872","https://openalex.org/W4224917001","https://openalex.org/W4224920209","https://openalex.org/W4372267501","https://openalex.org/W4372341189","https://openalex.org/W4379193822","https://openalex.org/W4389752793","https://openalex.org/W4390905568","https://openalex.org/W4417176242"],"related_works":[],"abstract_inverted_index":null,"counts_by_year":[],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2026-04-24T00:00:00"}