{"id":"https://openalex.org/W3174253394","doi":"https://doi.org/10.1145/3456126.3456129","title":"SeeSpeech: See Emotions in The Speech","display_name":"SeeSpeech: See Emotions in The Speech","publication_year":2021,"publication_date":"2021-02-24","ids":{"openalex":"https://openalex.org/W3174253394","doi":"https://doi.org/10.1145/3456126.3456129","mag":"3174253394"},"language":"en","primary_location":{"id":"doi:10.1145/3456126.3456129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3456126.3456129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 2nd Asia Service Sciences and Software Engineering Conference","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/A5102407450","display_name":"Jianing Geng","orcid":null},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jianing Geng","raw_affiliation_strings":["School of Data Science, University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"School of Data Science, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101589497","display_name":"Hao Zhu","orcid":"https://orcid.org/0000-0003-2155-1488"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Zhu","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100341802","display_name":"Xiang\u2010Yang Li","orcid":"https://orcid.org/0000-0002-6070-6625"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang-Yang Li","raw_affiliation_strings":["University of Science and Technology of China, China"],"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5102407450"],"corresponding_institution_ids":["https://openalex.org/I126520041"],"apc_list":null,"apc_paid":null,"fwci":0.1753,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.53479125,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9998000264167786,"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":0.9998000264167786,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9891999959945679,"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/T10860","display_name":"Speech and Audio Processing","score":0.9790999889373779,"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/softmax-function","display_name":"Softmax function","score":0.7640412449836731},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7362328171730042},{"id":"https://openalex.org/keywords/normalization","display_name":"Normalization (sociology)","score":0.7169803380966187},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6620126962661743},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.560799777507782},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4581017792224884},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3947994112968445},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.13373425602912903},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.10296511650085449},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09101530909538269}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.7640412449836731},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7362328171730042},{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7169803380966187},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6620126962661743},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.560799777507782},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4581017792224884},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3947994112968445},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.13373425602912903},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.10296511650085449},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09101530909538269},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3456126.3456129","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3456126.3456129","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 2nd Asia Service Sciences and Software Engineering Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4699999988079071}],"awards":[{"id":"https://openalex.org/G2874098862","display_name":null,"funder_award_id":"No. 61625205","funder_id":"https://openalex.org/F4320334953","funder_display_name":"China National Funds for Distinguished Young Scientists"}],"funders":[{"id":"https://openalex.org/F4320334953","display_name":"China National Funds for Distinguished Young Scientists","ror":"https://ror.org/01pab2602"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W257874415","https://openalex.org/W1536822605","https://openalex.org/W1538482441","https://openalex.org/W1595401537","https://openalex.org/W1888913026","https://openalex.org/W1963552095","https://openalex.org/W1973270182","https://openalex.org/W1988111866","https://openalex.org/W2058819080","https://openalex.org/W2061068689","https://openalex.org/W2111926505","https://openalex.org/W2118911453","https://openalex.org/W2140801466","https://openalex.org/W2330379721","https://openalex.org/W2397083728","https://openalex.org/W2399733683","https://openalex.org/W2578895956","https://openalex.org/W2803193013","https://openalex.org/W2899156568","https://openalex.org/W2939551310","https://openalex.org/W3035120387","https://openalex.org/W3037933265","https://openalex.org/W4239447739"],"related_works":["https://openalex.org/W2891743287","https://openalex.org/W2888789309","https://openalex.org/W2922692936","https://openalex.org/W3107474891","https://openalex.org/W4287268156","https://openalex.org/W3137649401","https://openalex.org/W2913039608","https://openalex.org/W2166688768","https://openalex.org/W3185514949","https://openalex.org/W3211213731"],"abstract_inverted_index":{"At":[0],"present,":[1],"the":[2,11,22,42,53,83,90,100,108,115,122,132],"understanding":[3,12],"of":[4,13,85,92,105,119,148],"speech":[5,16,54,140],"by":[6],"machines":[7],"mostly":[8],"focuses":[9],"on":[10,107,121],"semantics,":[14,29],"but":[15,30],"should":[17],"also":[18,113],"include":[19],"emotions":[20],"in":[21,139,151],"speech.":[23],"Emotion":[24],"can":[25,31,128],"not":[26],"only":[27],"strengthen":[28],"even":[32],"change":[33],"semantic":[34],"information.":[35],"The":[36],"paper":[37],"discusses":[38],"how":[39],"to":[40,67],"realize":[41],"emotion":[43,55,93,141],"classification,":[44],"which":[45],"is":[46,94],"called":[47],"SeeSpeech.":[48],"SeeSpeech":[49,98,135],"chooses":[50],"MCEP":[51],"as":[52],"feature,":[56],"and":[57,62,80,87,112,143],"inputs":[58],"it":[59],"into":[60],"CNN":[61,71,86],"Transformer":[63,76],"respectively.":[64],"In":[65],"order":[66],"obtain":[68],"richer":[69],"features,":[70],"uses":[72,77],"batch":[73],"normalization,":[74,79],"while":[75],"layer":[78],"then":[81],"combines":[82],"output":[84],"Transformer.":[88],"Finally,":[89],"type":[91],"obtained":[95,99,114],"through":[96],"SoftMax.":[97],"highest":[101],"classification":[102,116,142],"accuracy":[103,117],"rate":[104,118],"97%":[106],"RAVDESS":[109],"data":[110],"set,":[111],"85%":[120],"actual":[123],"edge":[124],"gateway":[125],"test.":[126],"It":[127],"be":[129],"seen":[130],"from":[131],"results":[133],"that":[134],"has":[136,144],"encouraging":[137],"performance":[138],"a":[145],"wide":[146],"range":[147],"application":[149],"prospects":[150],"human-computer":[152],"interaction.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}