{"id":"https://openalex.org/W3193038511","doi":"https://doi.org/10.1109/iwcmc51323.2021.9498598","title":"Speech Emotion Recognition Model with Time-Scale-Invariance MFCCs as Input","display_name":"Speech Emotion Recognition Model with Time-Scale-Invariance MFCCs as Input","publication_year":2021,"publication_date":"2021-06-28","ids":{"openalex":"https://openalex.org/W3193038511","doi":"https://doi.org/10.1109/iwcmc51323.2021.9498598","mag":"3193038511"},"language":"en","primary_location":{"id":"doi:10.1109/iwcmc51323.2021.9498598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc51323.2021.9498598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Wireless Communications and Mobile Computing (IWCMC)","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/A5037982800","display_name":"Xiaohan Xie","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137235","display_name":"Tengzhou Central People's Hospital","ror":"https://ror.org/03b867n98","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210137235"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaohan Xie","raw_affiliation_strings":["Shandong Province Tengzhou No.1 High School, Tengzhou, China"],"affiliations":[{"raw_affiliation_string":"Shandong Province Tengzhou No.1 High School, Tengzhou, China","institution_ids":["https://openalex.org/I4210137235"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008091363","display_name":"Jiaqi Lou","orcid":null},"institutions":[{"id":"https://openalex.org/I82284825","display_name":"Cranfield University","ror":"https://ror.org/05cncd958","country_code":"GB","type":"education","lineage":["https://openalex.org/I82284825"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jiaqi Lou","raw_affiliation_strings":["School of Aerospace, Transport and Manufacturing Cranfield University, Bedford, UK"],"affiliations":[{"raw_affiliation_string":"School of Aerospace, Transport and Manufacturing Cranfield University, Bedford, UK","institution_ids":["https://openalex.org/I82284825"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100683340","display_name":"Lingzhi Zhang","orcid":"https://orcid.org/0000-0002-8348-5618"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Lingzhi Zhang","raw_affiliation_strings":["School of Environment, Education and Development The University of Manchester, Manchestery, UK"],"affiliations":[{"raw_affiliation_string":"School of Environment, Education and Development The University of Manchester, Manchestery, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5037982800"],"corresponding_institution_ids":["https://openalex.org/I4210137235"],"apc_list":null,"apc_paid":null,"fwci":0.3047,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.53718729,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"542"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9976000189781189,"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":0.9976000189781189,"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/T13905","display_name":"Telecommunications and Broadcasting Technologies","score":0.9950000047683716,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13731","display_name":"Advanced Computing and Algorithms","score":0.9918000102043152,"subfield":{"id":"https://openalex.org/subfields/3322","display_name":"Urban Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.9166356325149536},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7830719947814941},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7226283550262451},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6570354700088501},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5185214281082153},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.4968288242816925},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.43831580877304077},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4257551431655884},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4173002541065216},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.40698742866516113},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40515315532684326},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06363734602928162}],"concepts":[{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.9166356325149536},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7830719947814941},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7226283550262451},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6570354700088501},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5185214281082153},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.4968288242816925},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.43831580877304077},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4257551431655884},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4173002541065216},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.40698742866516113},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40515315532684326},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06363734602928162},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iwcmc51323.2021.9498598","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwcmc51323.2021.9498598","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Wireless Communications and Mobile Computing (IWCMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.7699999809265137,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W565267543","https://openalex.org/W1963552095","https://openalex.org/W2056890665","https://openalex.org/W2131049857","https://openalex.org/W2142246654","https://openalex.org/W2163168488","https://openalex.org/W2191779130","https://openalex.org/W2295001676","https://openalex.org/W2342475039","https://openalex.org/W2399733683","https://openalex.org/W2520774990","https://openalex.org/W2592549785","https://openalex.org/W2599615286","https://openalex.org/W2648194195","https://openalex.org/W2804529354","https://openalex.org/W2885005742","https://openalex.org/W2896457183","https://openalex.org/W2936372954","https://openalex.org/W2937977583","https://openalex.org/W2981096252","https://openalex.org/W3011830499","https://openalex.org/W3013686035","https://openalex.org/W3015240477","https://openalex.org/W3015850999","https://openalex.org/W3045823312","https://openalex.org/W3095379519","https://openalex.org/W3096149610","https://openalex.org/W4385245566","https://openalex.org/W6697498398","https://openalex.org/W6739901393","https://openalex.org/W6775162343"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W2787035864","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W3119288895","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W2074132948"],"abstract_inverted_index":{"Speech":[0],"Emotion":[1],"Recognition":[2],"(SER)":[3],"is":[4],"a":[5,37,95],"significant":[6],"task":[7,43],"for":[8],"human":[9],"communication.":[10],"In":[11,32],"the":[12,25,53,67],"recent":[13],"years,":[14],"Mel-frequency":[15],"Cepstrum":[16],"Coefficient":[17],"(MFCC)":[18],"feature":[19],"can":[20,84,100],"be":[21],"usually":[22],"utilized":[23],"in":[24,80],"related":[26],"tasks":[27],"of":[28,44,55,62,69,90],"speech":[29,91],"emotion":[30,92],"recognition.":[31],"this":[33],"study,":[34],"we":[35,51],"developed":[36],"multi-head-attention":[38],"CNN":[39],"model":[40,86,102],"with":[41,94],"auxiliary":[42],"gender":[45],"task.":[46],"Base":[47],"on":[48,66],"proposed":[49,70],"model,":[50],"explore":[52],"effect":[54],"different":[56,60,108],"time-scale":[57,81,109],"MFCCs":[58,110],"and":[59],"combination":[61],"them":[63],"as":[64,82],"input":[65,83],"performance":[68,89,105],"model.":[71],"Experimental":[72],"results":[73],"show":[74],"that":[75],"MFCC":[76],"having":[77],"higher":[78],"resolution":[79],"help":[85,101],"achieving":[87,103],"better":[88,104],"recognition":[93],"moderate":[96],"range.":[97],"Also,":[98],"it":[99],"to":[106],"combine":[107],"appropriately.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}