{"id":"https://openalex.org/W2786863597","doi":"https://doi.org/10.1109/apsipa.2017.8282315","title":"Speech emotion recognition using convolutional long short-term memory neural network and support vector machines","display_name":"Speech emotion recognition using convolutional long short-term memory neural network and support vector machines","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2786863597","doi":"https://doi.org/10.1109/apsipa.2017.8282315","mag":"2786863597"},"language":"en","primary_location":{"id":"doi:10.1109/apsipa.2017.8282315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","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/A5025925774","display_name":"Nattapong Kurpukdee","orcid":null},"institutions":[{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]},{"id":"https://openalex.org/I198105771","display_name":"Kasetsart University","ror":"https://ror.org/05gzceg21","country_code":"TH","type":"education","lineage":["https://openalex.org/I198105771"]},{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}],"countries":["TH"],"is_corresponding":true,"raw_author_name":"Nattapong Kurpukdee","raw_affiliation_strings":["NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","TAIST Tokyo Tech, Kasetsart University, Thailand","NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand; TAIST Tokyo Tech, Kasetsart University, Thailand"],"affiliations":[{"raw_affiliation_string":"NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"TAIST Tokyo Tech, Kasetsart University, Thailand","institution_ids":["https://openalex.org/I198105771"]},{"raw_affiliation_string":"NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand; TAIST Tokyo Tech, Kasetsart University, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I198105771","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024181978","display_name":"Tomoki Koriyama","orcid":"https://orcid.org/0000-0002-8347-5604"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Koriyama","raw_affiliation_strings":["School of Engineering, Tokyo Institute of Technology, Yokohama, Japan","School of Engineering, Tokyo Institute of Technology, Yokohama 226-8502, Japan"],"affiliations":[{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology, Yokohama, Japan","institution_ids":["https://openalex.org/I114531698"]},{"raw_affiliation_string":"School of Engineering, Tokyo Institute of Technology, Yokohama 226-8502, Japan","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022405100","display_name":"Takao Kobayashi","orcid":"https://orcid.org/0000-0003-0387-8030"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takao Kobayashi","raw_affiliation_strings":["Tokyo Kogyo Daigaku, Meguro-ku, Tokyo, JP"],"affiliations":[{"raw_affiliation_string":"Tokyo Kogyo Daigaku, Meguro-ku, Tokyo, JP","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083154069","display_name":"Sawit Kasuriya","orcid":"https://orcid.org/0000-0003-3429-0440"},"institutions":[{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Sawit Kasuriya","raw_affiliation_strings":["NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","NECTEC, National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand"],"affiliations":[{"raw_affiliation_string":"NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"NECTEC, National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065708730","display_name":"Chai Wutiwiwatchai","orcid":null},"institutions":[{"id":"https://openalex.org/I14316845","display_name":"National Electronics and Computer Technology Center","ror":"https://ror.org/04z82ry91","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"id":"https://openalex.org/I1332092204","display_name":"National Science and Technology Development Agency","ror":"https://ror.org/04vy95b61","country_code":"TH","type":"government","lineage":["https://openalex.org/I1332092204"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Chai Wutiwiwatchai","raw_affiliation_strings":["NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","NECTEC, National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand"],"affiliations":[{"raw_affiliation_string":"NECTEC, National Science and Technology Development Agency (NSTDA), Pathumthani, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]},{"raw_affiliation_string":"NECTEC, National Science and Technology Development Agency (NSTDA), 112 Pahonyothin Road, Pathumthani, 12120, Thailand","institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042654966","display_name":"Poonlap Lamsrichan","orcid":null},"institutions":[{"id":"https://openalex.org/I198105771","display_name":"Kasetsart University","ror":"https://ror.org/05gzceg21","country_code":"TH","type":"education","lineage":["https://openalex.org/I198105771"]}],"countries":["TH"],"is_corresponding":false,"raw_author_name":"Poonlap Lamsrichan","raw_affiliation_strings":["TAIST Tokyo Tech, Kasetsart University, Thailand","TAIST Tokyo Tech, ICTES Program, Kasetsart University, Thailand"],"affiliations":[{"raw_affiliation_string":"TAIST Tokyo Tech, Kasetsart University, Thailand","institution_ids":["https://openalex.org/I198105771"]},{"raw_affiliation_string":"TAIST Tokyo Tech, ICTES Program, Kasetsart University, Thailand","institution_ids":["https://openalex.org/I198105771"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5025925774"],"corresponding_institution_ids":["https://openalex.org/I1332092204","https://openalex.org/I14316845","https://openalex.org/I198105771"],"apc_list":null,"apc_paid":null,"fwci":2.1083,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.87852916,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1744","last_page":"1749"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9998999834060669,"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":0.9998999834060669,"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/T10860","display_name":"Speech and Audio Processing","score":0.9944000244140625,"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/T10057","display_name":"Face and Expression Recognition","score":0.9930999875068665,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8026036024093628},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.686537504196167},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6559870839118958},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6453046202659607},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6254345178604126},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5715024471282959},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.5373296737670898},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.503792941570282},{"id":"https://openalex.org/keywords/linear-discriminant-analysis","display_name":"Linear discriminant analysis","score":0.4565330445766449},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.43299925327301025},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4319276809692383},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3903898298740387}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8026036024093628},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.686537504196167},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6559870839118958},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6453046202659607},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6254345178604126},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5715024471282959},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.5373296737670898},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.503792941570282},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.4565330445766449},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.43299925327301025},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4319276809692383},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3903898298740387},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/apsipa.2017.8282315","is_oa":false,"landing_page_url":"https://doi.org/10.1109/apsipa.2017.8282315","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC)","raw_type":"proceedings-article"},{"id":"pmh:oai:t2r2.star.titech.ac.jp:50402283","is_oa":false,"landing_page_url":"http://t2r2.star.titech.ac.jp/cgi-bin/publicationinfo.cgi?q_publication_content_number=CTT100758687","pdf_url":null,"source":{"id":"https://openalex.org/S4377196385","display_name":"Tokyo Tech Research Repository (Tokyo Institute of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I114531698","host_organization_name":"Tokyo Institute of Technology","host_organization_lineage":["https://openalex.org/I114531698"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1534131679","https://openalex.org/W1844030040","https://openalex.org/W1972280480","https://openalex.org/W2030316446","https://openalex.org/W2055911634","https://openalex.org/W2087618018","https://openalex.org/W2101234009","https://openalex.org/W2110052520","https://openalex.org/W2146334809","https://openalex.org/W2181741066","https://openalex.org/W2295001676","https://openalex.org/W2309898435","https://openalex.org/W2399733683","https://openalex.org/W2408520939","https://openalex.org/W2499760652","https://openalex.org/W2507824935","https://openalex.org/W2547704635","https://openalex.org/W2578895956","https://openalex.org/W6638569628","https://openalex.org/W6675354045","https://openalex.org/W6676494506","https://openalex.org/W6697498398","https://openalex.org/W6714031499"],"related_works":["https://openalex.org/W2529301793","https://openalex.org/W2384121599","https://openalex.org/W2038083449","https://openalex.org/W3177678247","https://openalex.org/W1999617572","https://openalex.org/W2944572343","https://openalex.org/W2333799855","https://openalex.org/W2351687372","https://openalex.org/W2004087835","https://openalex.org/W2951122819"],"abstract_inverted_index":{"In":[0,30],"this":[1],"paper,":[2],"we":[3,89],"propose":[4],"a":[5,21],"speech":[6,28],"emotion":[7,38],"recognition":[8],"technique":[9,112],"using":[10],"convolutional":[11],"long":[12],"short-term":[13],"memory":[14],"(LSTM)":[15],"recurrent":[16],"neural":[17],"network":[18],"(ConvLSTM-RNN)":[19],"as":[20],"phoneme-based":[22],"feature":[23],"extractor":[24],"from":[25],"raw":[26],"input":[27,45,57,63],"signal.":[29],"the":[31,56,62,78,83,86,93,110,121],"proposed":[32,87,111],"technique,":[33,88],"ConvLSTM-RNN":[34],"outputs":[35],"phoneme-":[36],"based":[37],"probabilities":[39,49],"to":[40,76],"every":[41],"frame":[42],"of":[43,55,65,85,95,115],"an":[44],"utterance.":[46],"Then":[47],"these":[48],"are":[50],"converted":[51],"into":[52],"statistical":[53],"features":[54,64],"utterance":[58],"and":[59,101],"used":[60],"for":[61],"support":[66],"vector":[67],"machines":[68],"(SVMs)":[69],"or":[70,117],"linear":[71],"discriminant":[72],"analysis":[73],"(LDA)":[74],"system":[75],"classify":[77],"utterance-level":[79],"emotions.":[80],"To":[81],"assess":[82],"effectiveness":[84],"conducted":[90],"experiments":[91],"in":[92],"classification":[94],"four":[96],"emotions":[97],"(anger,":[98],"happiness,":[99],"sadness,":[100],"neutral)":[102],"on":[103],"IEMOCAP":[104],"database.":[105],"The":[106],"result":[107],"showed":[108],"that":[109],"with":[113],"either":[114],"SVM":[116],"LDA":[118],"classifier":[119],"outperforms":[120],"conventional":[122],"ConvLSTM-based":[123],"one.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}