{"id":"https://openalex.org/W2121552713","doi":"https://doi.org/10.1109/icassp.2009.4960678","title":"Speaker dependency of spectral features and speech production cues for automatic emotion classification","display_name":"Speaker dependency of spectral features and speech production cues for automatic emotion classification","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2121552713","doi":"https://doi.org/10.1109/icassp.2009.4960678","mag":"2121552713"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5032689109","display_name":"Vidhyasaharan Sethu","orcid":"https://orcid.org/0000-0001-8492-1787"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Vidhyasaharan Sethu","raw_affiliation_strings":["NICTA, Eveleigh, Australia","The School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"NICTA, Eveleigh, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"The School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028116210","display_name":"Eliathamby Ambikairajah","orcid":"https://orcid.org/0000-0003-4673-6534"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]},{"id":"https://openalex.org/I42894916","display_name":"Data61","ror":"https://ror.org/03q397159","country_code":"AU","type":"other","lineage":["https://openalex.org/I1292875679","https://openalex.org/I2801453606","https://openalex.org/I42894916","https://openalex.org/I4387156119"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Eliathamby Ambikairajah","raw_affiliation_strings":["NICTA, Eveleigh, Australia","The School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"NICTA, Eveleigh, Australia","institution_ids":["https://openalex.org/I42894916"]},{"raw_affiliation_string":"The School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030922449","display_name":"Julien Epps","orcid":"https://orcid.org/0000-0001-6624-5551"},"institutions":[{"id":"https://openalex.org/I31746571","display_name":"UNSW Sydney","ror":"https://ror.org/03r8z3t63","country_code":"AU","type":"education","lineage":["https://openalex.org/I31746571"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Julien Epps","raw_affiliation_strings":["The School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia"],"affiliations":[{"raw_affiliation_string":"The School of Electrical Engineering and Telecommunications, University of New South Wales, Sydney, NSW, Australia","institution_ids":["https://openalex.org/I31746571"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5032689109"],"corresponding_institution_ids":["https://openalex.org/I31746571","https://openalex.org/I42894916"],"apc_list":null,"apc_paid":null,"fwci":1.7805,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.85750379,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4693","last_page":"4696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.992900013923645,"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":0.992900013923645,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9736999869346619,"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":0.9706000089645386,"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/speech-recognition","display_name":"Speech recognition","score":0.7724655866622925},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7581411600112915},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7380107641220093},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.6091116666793823},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.5990408062934875},{"id":"https://openalex.org/keywords/speech-production","display_name":"Speech production","score":0.5905762910842896},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.5567923784255981},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.5071477890014648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4680483043193817},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.45846307277679443},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.44549301266670227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36551573872566223},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09709897637367249}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7724655866622925},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7581411600112915},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7380107641220093},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.6091116666793823},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.5990408062934875},{"id":"https://openalex.org/C43617652","wikidata":"https://www.wikidata.org/wiki/Q7575399","display_name":"Speech production","level":2,"score":0.5905762910842896},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.5567923784255981},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.5071477890014648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4680483043193817},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.45846307277679443},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.44549301266670227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36551573872566223},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09709897637367249},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960678","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960678","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W98179523","https://openalex.org/W1206231705","https://openalex.org/W1527277685","https://openalex.org/W1535925594","https://openalex.org/W1940245494","https://openalex.org/W2095590291","https://openalex.org/W2103257373","https://openalex.org/W2110052520","https://openalex.org/W2125365056","https://openalex.org/W2126672039","https://openalex.org/W2167797544","https://openalex.org/W2169786211","https://openalex.org/W6603953809","https://openalex.org/W6627945324","https://openalex.org/W6674250557","https://openalex.org/W6676494506"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2968813438","https://openalex.org/W2162158162","https://openalex.org/W4247736853","https://openalex.org/W1493012537","https://openalex.org/W2175373321","https://openalex.org/W2125642021","https://openalex.org/W4310979479","https://openalex.org/W2696990509","https://openalex.org/W1999004162"],"abstract_inverted_index":{"Spectral":[0],"and":[1,30,34,47,118],"excitation":[2],"features,":[3],"commonly":[4],"used":[5],"in":[6,40,43,69],"automatic":[7],"emotion":[8],"classification":[9,72],"systems,":[10],"parameterise":[11],"different":[12,64],"aspects":[13],"of":[14,53,63,71,115],"the":[15,78,103],"speech":[16,24,81],"signal.":[17],"This":[18],"paper":[19],"groups":[20],"these":[21,57],"features":[22,58,65],"as":[23],"production":[25],"cues,":[26],"broad":[27],"spectral":[28,32],"measures":[29,33],"detailed":[31],"looks":[35],"at":[36],"how":[37],"they":[38],"differ":[39],"their":[41],"performance":[42],"both":[44],"speaker":[45,48,54,97,109],"dependent":[46],"independent":[49,110],"systems.":[50],"The":[51],"extent":[52],"normalisation":[55],"on":[56,77],"is":[59,112],"also":[60],"considered.":[61],"Combinations":[62],"are":[66,91],"then":[67],"compared":[68],"terms":[70],"accuracies.":[73],"Evaluations":[74],"were":[75],"conducted":[76],"LDC":[79],"emotional":[80],"corpus":[82],"for":[83,107],"a":[84,108,113],"five-class":[85],"problem.":[86],"Results":[87],"indicate":[88],"that":[89,102],"MFCCs":[90],"very":[92],"discriminative":[93],"but":[94],"suffer":[95],"from":[96],"variability.":[98],"Further,":[99],"results":[100],"suggest":[101],"best":[104],"front":[105],"end":[106],"system":[111],"combination":[114],"pitch,":[116],"energy":[117],"formant":[119],"information.":[120]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}
