{"id":"https://openalex.org/W2914956632","doi":"https://doi.org/10.1145/3302425.3302444","title":"Speech Emotion Recognition Based on LSTM and Mel Scale Wavelet Packet Decomposition","display_name":"Speech Emotion Recognition Based on LSTM and Mel Scale Wavelet Packet Decomposition","publication_year":2018,"publication_date":"2018-12-21","ids":{"openalex":"https://openalex.org/W2914956632","doi":"https://doi.org/10.1145/3302425.3302444","mag":"2914956632"},"language":"en","primary_location":{"id":"doi:10.1145/3302425.3302444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3302425.3302444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence","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/A5091654380","display_name":"Feng Tian","orcid":"https://orcid.org/0000-0002-5057-4657"},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian Feng","raw_affiliation_strings":["Key Laboratory of Computer Vision & System, Ministry of Education, Tianjin University of Technology, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Computer Vision & System, Ministry of Education, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100917265","display_name":"Shuying Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I136765683","display_name":"Tianjin University of Technology","ror":"https://ror.org/00zbe0w13","country_code":"CN","type":"education","lineage":["https://openalex.org/I136765683"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuying Yang","raw_affiliation_strings":["School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China","institution_ids":["https://openalex.org/I136765683"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I136765683"],"apc_list":null,"apc_paid":null,"fwci":0.4986,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.66675359,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"18","issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9991000294685364,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9975000023841858,"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":0.9959999918937683,"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/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.8345835208892822},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.8239901065826416},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7805765867233276},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7505248785018921},{"id":"https://openalex.org/keywords/wavelet-packet-decomposition","display_name":"Wavelet packet decomposition","score":0.6843334436416626},{"id":"https://openalex.org/keywords/autocorrelation","display_name":"Autocorrelation","score":0.6567434072494507},{"id":"https://openalex.org/keywords/wavelet","display_name":"Wavelet","score":0.6166213750839233},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5317921042442322},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.5262909531593323},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5153269171714783},{"id":"https://openalex.org/keywords/time\u2013frequency-analysis","display_name":"Time\u2013frequency analysis","score":0.5075808763504028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4827917814254761},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4804201126098633},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.4791373908519745},{"id":"https://openalex.org/keywords/wavelet-transform","display_name":"Wavelet transform","score":0.47098228335380554},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44506028294563293},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.3925178647041321},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19013050198554993},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08915296196937561}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.8345835208892822},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.8239901065826416},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7805765867233276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7505248785018921},{"id":"https://openalex.org/C155777637","wikidata":"https://www.wikidata.org/wiki/Q2736187","display_name":"Wavelet packet decomposition","level":4,"score":0.6843334436416626},{"id":"https://openalex.org/C5297727","wikidata":"https://www.wikidata.org/wiki/Q786970","display_name":"Autocorrelation","level":2,"score":0.6567434072494507},{"id":"https://openalex.org/C47432892","wikidata":"https://www.wikidata.org/wiki/Q831390","display_name":"Wavelet","level":2,"score":0.6166213750839233},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5317921042442322},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.5262909531593323},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5153269171714783},{"id":"https://openalex.org/C142433447","wikidata":"https://www.wikidata.org/wiki/Q7806653","display_name":"Time\u2013frequency analysis","level":3,"score":0.5075808763504028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4827917814254761},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4804201126098633},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.4791373908519745},{"id":"https://openalex.org/C196216189","wikidata":"https://www.wikidata.org/wiki/Q2867","display_name":"Wavelet transform","level":3,"score":0.47098228335380554},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44506028294563293},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3925178647041321},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19013050198554993},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08915296196937561},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3302425.3302444","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3302425.3302444","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Algorithms, Computing and Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320327240","display_name":"Liga Portuguesa Contra o Cancro","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W216271725","https://openalex.org/W1983334819","https://openalex.org/W2032254851","https://openalex.org/W2033310064","https://openalex.org/W2064675550","https://openalex.org/W2070604329","https://openalex.org/W2102697000","https://openalex.org/W2110052520","https://openalex.org/W2118911453","https://openalex.org/W2135013272","https://openalex.org/W2139671364","https://openalex.org/W2144354855","https://openalex.org/W2147768505","https://openalex.org/W2161281622","https://openalex.org/W2266946669","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2046217390","https://openalex.org/W4365503437","https://openalex.org/W2362995206","https://openalex.org/W2004825552","https://openalex.org/W1986672430","https://openalex.org/W37481168","https://openalex.org/W1990629684","https://openalex.org/W1971436356","https://openalex.org/W1975851543","https://openalex.org/W2070163607"],"abstract_inverted_index":{"The":[0,106],"traditional":[1],"Mel":[2,28],"Frequency":[3],"Cepstral":[4],"Coefficient":[5],"(MFCC)":[6],"feature":[7,45],"can":[8],"only":[9,123],"reflect":[10,122,137],"low":[11],"frequency":[12,16,29,50,89,99],"information,":[13],"ignoring":[14],"high":[15,49],"signals.":[17,70],"In":[18,71,131],"order":[19,132],"to":[20,31,135,143,158,161],"solve":[21],"this":[22,24,72],"problem,":[23],"paper":[25],"uses":[26],"the":[27,33,37,48,74,80,83,87,93,97,112,116,124,145],"decomposition":[30],"decompose":[32],"speech":[34,69,107,155],"signal":[35,108],"in":[36,47,68,111,127],"wavelet":[38],"packet,":[39],"and":[40,86,96],"then":[41],"obtains":[42],"many":[43],"valuable":[44],"information":[46,146],"signal,":[51],"such":[52],"as":[53],"short-time":[54,75],"energy,":[55],"fundamental":[56,88],"frequency,":[57],"formant,":[58],"MFCC,":[59],"sub-band":[60],"energy.":[61],"These":[62],"features":[63,117,126,134],"are":[64,90,101],"extremely":[65],"important":[66],"parameters":[67],"paper,":[73],"energy":[76,81],"is":[77,109,141,151],"obtained":[78,91],"by":[79,103],"formula,":[82],"pitch":[84],"period":[85],"from":[92,119],"autocorrelation":[94],"function,":[95],"formant":[98],"characteristics":[100],"characterized":[102],"Hilbert-Huang":[104],"transform.":[105],"continuous":[110],"time":[113,167],"domain,":[114],"so":[115],"extracted":[118],"each":[120],"frame":[121],"emotional":[125],"a":[128],"single":[129],"frame.":[130],"for":[133,154],"better":[136],"temporal":[138],"continuity,":[139],"LSTM":[140,150],"used":[142],"increase":[144],"between":[147],"adjacent":[148],"frames.":[149],"naturally":[152],"suitable":[153],"recognition":[156],"due":[157],"its":[159],"ability":[160],"take":[162],"advantage":[163],"of":[164],"dynamically":[165],"changing":[166],"information.":[168]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}