{"id":"https://openalex.org/W2611029437","doi":"https://doi.org/10.1109/ita.2017.8023477","title":"Speech emotion recognition based on Gaussian Mixture Models and Deep Neural Networks","display_name":"Speech emotion recognition based on Gaussian Mixture Models and Deep Neural Networks","publication_year":2017,"publication_date":"2017-02-01","ids":{"openalex":"https://openalex.org/W2611029437","doi":"https://doi.org/10.1109/ita.2017.8023477","mag":"2611029437"},"language":"en","primary_location":{"id":"doi:10.1109/ita.2017.8023477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2017.8023477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Information Theory and Applications Workshop (ITA)","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/A5007425970","display_name":"Ivan Tashev","orcid":"https://orcid.org/0000-0002-2263-2047"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ivan J. Tashev","raw_affiliation_strings":["Microsoft Research Labs, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research Labs, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109000140","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0003-2812-2299"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Dept. of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068934511","display_name":"Keith W. Godin","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Keith Godin","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8915,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.92814339,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9990000128746033,"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":0.9990000128746033,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7815366983413696},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6340351700782776},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.633638322353363},{"id":"https://openalex.org/keywords/utterance","display_name":"Utterance","score":0.6239780783653259},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6208566427230835},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.5882436633110046},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5123032331466675},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5093594789505005},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4947659373283386},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.4790695607662201},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.4512898921966553},{"id":"https://openalex.org/keywords/emotion-recognition","display_name":"Emotion recognition","score":0.44380852580070496},{"id":"https://openalex.org/keywords/dialog-system","display_name":"Dialog system","score":0.4393395185470581},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4303666353225708},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3586103320121765},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3488169014453888}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7815366983413696},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6340351700782776},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.633638322353363},{"id":"https://openalex.org/C2775852435","wikidata":"https://www.wikidata.org/wiki/Q258403","display_name":"Utterance","level":2,"score":0.6239780783653259},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6208566427230835},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.5882436633110046},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5123032331466675},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5093594789505005},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4947659373283386},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.4790695607662201},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4512898921966553},{"id":"https://openalex.org/C2777438025","wikidata":"https://www.wikidata.org/wiki/Q1339090","display_name":"Emotion recognition","level":2,"score":0.44380852580070496},{"id":"https://openalex.org/C190954187","wikidata":"https://www.wikidata.org/wiki/Q5270587","display_name":"Dialog system","level":3,"score":0.4393395185470581},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4303666353225708},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3586103320121765},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3488169014453888},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ita.2017.8023477","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ita.2017.8023477","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 Information Theory and Applications Workshop (ITA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1936725236","https://openalex.org/W1972280480","https://openalex.org/W1980713635","https://openalex.org/W2026131661","https://openalex.org/W2038750313","https://openalex.org/W2041823554","https://openalex.org/W2110052520","https://openalex.org/W2129120544","https://openalex.org/W2154024118","https://openalex.org/W2167854178","https://openalex.org/W2295001676","https://openalex.org/W2408520939","https://openalex.org/W2599621350","https://openalex.org/W2963467407","https://openalex.org/W2963626623","https://openalex.org/W6676494506","https://openalex.org/W6714031499"],"related_works":["https://openalex.org/W2500779211","https://openalex.org/W48079147","https://openalex.org/W326836678","https://openalex.org/W1963944933","https://openalex.org/W2563921006","https://openalex.org/W1600043506","https://openalex.org/W2111550420","https://openalex.org/W2549666521","https://openalex.org/W3133893348","https://openalex.org/W2920931047"],"abstract_inverted_index":{"Recognition":[0],"of":[1,25,52,71],"speaker":[2],"emotion":[3,41,92],"during":[4],"interaction":[5,26],"in":[6],"spoken":[7],"dialog":[8],"systems":[9],"can":[10],"enhance":[11],"the":[12,39,79,86,104],"user":[13],"experience,":[14],"and":[15,29,36],"provide":[16],"system":[17,27,73],"operators":[18],"with":[19,58,85],"information":[20],"valuable":[21],"to":[22,91],"ongoing":[23],"assessment":[24],"performance":[28],"utility.":[30],"Interaction":[31],"utterances":[32],"are":[33],"very":[34],"short,":[35],"we":[37],"assume":[38],"speaker's":[40],"is":[42,75],"constant":[43],"throughout":[44],"a":[45,53,59,64,96],"given":[46],"utterance.":[47],"This":[48],"paper":[49],"investigates":[50],"combinations":[51],"GMM-based":[54],"low-level":[55],"feature":[56,67],"extractor":[57],"neural":[60,82],"network":[61],"serving":[62],"as":[63],"high":[65],"level":[66],"extractor.":[68],"The":[69],"advantage":[70],"this":[72],"architecture":[74],"that":[76],"it":[77],"combines":[78],"fast":[80],"developing":[81],"network-based":[83],"solutions":[84,102],"classic":[87],"statistical":[88],"approaches":[89],"applied":[90],"recognition.":[93],"Experiments":[94],"on":[95],"Mandarin":[97],"data":[98],"set":[99],"compare":[100],"different":[101],"under":[103],"same":[105],"or":[106],"close":[107],"conditions.":[108]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":7}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}