{"id":"https://openalex.org/W1589734697","doi":"https://doi.org/10.1109/icassp.2015.7178874","title":"Emotion recognition using synthetic speech as neutral reference","display_name":"Emotion recognition using synthetic speech as neutral reference","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W1589734697","doi":"https://doi.org/10.1109/icassp.2015.7178874","mag":"1589734697"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041789037","display_name":"Reza Lotfian","orcid":"https://orcid.org/0000-0003-1891-0267"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reza Lotfian","raw_affiliation_strings":["Department of Electrical Engineering The University of Texas at Dallas, Multimodal Signal Processing (MSP) Laboratory, Richardson, TX, USA","Multimodal Signal Processing (MSP) Laboratory, Department of Electrical Engineering, The University of Texas at Dallas, Richardson 75080, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering The University of Texas at Dallas, Multimodal Signal Processing (MSP) Laboratory, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Multimodal Signal Processing (MSP) Laboratory, Department of Electrical Engineering, The University of Texas at Dallas, Richardson 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040793194","display_name":"Carlos Busso","orcid":"https://orcid.org/0000-0002-4075-4072"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Busso","raw_affiliation_strings":["Department of Electrical Engineering The University of Texas at Dallas, Multimodal Signal Processing (MSP) Laboratory, Richardson, TX, USA","Multimodal Signal Processing (MSP) Laboratory, Department of Electrical Engineering, The University of Texas at Dallas, Richardson 75080, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering The University of Texas at Dallas, Multimodal Signal Processing (MSP) Laboratory, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]},{"raw_affiliation_string":"Multimodal Signal Processing (MSP) Laboratory, Department of Electrical Engineering, The University of Texas at Dallas, Richardson 75080, USA","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4759","last_page":"4763"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":1.0,"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":1.0,"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":0.9950000047683716,"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/T13289","display_name":"Infant Health and Development","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7779024839401245},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7007004022598267},{"id":"https://openalex.org/keywords/valence","display_name":"Valence (chemistry)","score":0.5603362917900085},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.5085188150405884},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5078368782997131},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4780448079109192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.45571187138557434},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4537225067615509},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4412901997566223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7779024839401245},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7007004022598267},{"id":"https://openalex.org/C168900304","wikidata":"https://www.wikidata.org/wiki/Q171407","display_name":"Valence (chemistry)","level":2,"score":0.5603362917900085},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.5085188150405884},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5078368782997131},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4780448079109192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45571187138557434},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4537225067615509},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4412901997566223},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2015.7178874","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178874","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W99485238","https://openalex.org/W1261896931","https://openalex.org/W1599623585","https://openalex.org/W1668904664","https://openalex.org/W1785074626","https://openalex.org/W1976090878","https://openalex.org/W1976725440","https://openalex.org/W1981950962","https://openalex.org/W2004804300","https://openalex.org/W2016178520","https://openalex.org/W2032254851","https://openalex.org/W2055910046","https://openalex.org/W2072054026","https://openalex.org/W2072712810","https://openalex.org/W2085662862","https://openalex.org/W2092495673","https://openalex.org/W2102298245","https://openalex.org/W2131406347","https://openalex.org/W2132555391","https://openalex.org/W2133990480","https://openalex.org/W2167820006","https://openalex.org/W2169485456","https://openalex.org/W2183790675","https://openalex.org/W2296199791","https://openalex.org/W2401623121","https://openalex.org/W2403326047","https://openalex.org/W2404863510","https://openalex.org/W2550557083","https://openalex.org/W6635953567","https://openalex.org/W6637112759","https://openalex.org/W6638212026","https://openalex.org/W6697151493","https://openalex.org/W6713265837"],"related_works":["https://openalex.org/W231741463","https://openalex.org/W4200068392","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623","https://openalex.org/W2757826346","https://openalex.org/W2184371793"],"abstract_inverted_index":{"A":[0],"common":[1],"approach":[2],"to":[3,9,109,129,148],"recognize":[4],"emotion":[5,37,153],"from":[6,163],"speech":[7,79,88,93,101,135,144,166,171],"is":[8,72,89,102],"estimate":[10],"multiple":[11],"acoustic":[12,112],"features":[13,20,161],"at":[14],"sentence":[15,69],"or":[16,53],"turn":[17],"level.":[18],"These":[19],"are":[21],"derived":[22,162],"independent":[23],"of":[24,85,142,187],"the":[25,76,83,86,95,131,140,168,174],"underlying":[26],"lexical":[27,33,48,66,97,150],"content.":[28],"Studies":[29],"have":[30],"demonstrated":[31],"that":[32,63,82,159],"dependent":[34],"models":[35,67],"improve":[36],"recognition":[38],"accuracy.":[39],"However,":[40],"current":[41],"practical":[42],"approaches":[43],"can":[44],"only":[45],"model":[46,108],"small":[47],"units":[49],"like":[50],"phonemes,":[51],"syllables":[52],"few":[54],"key":[55],"words,":[56],"which":[57],"limits":[58],"these":[59],"systems.":[60],"We":[61],"believe":[62],"building":[64],"longer":[65],"(i.e.,":[68],"level":[70],"model)":[71],"feasible":[73],"by":[74],"leveraging":[75],"advances":[77],"in":[78,152,176,181],"synthesis.":[80],"Assuming":[81],"transcript":[84],"target":[87,132],"available,":[90],"we":[91],"synthesize":[92],"conveying":[94],"same":[96],"information.":[98],"The":[99,155],"synthetic":[100,134,143,170],"used":[103],"as":[104,145],"a":[105],"neutral":[106,146],"reference":[107,147,172],"contrast":[110],"different":[111],"features,":[113],"unveiling":[114],"local":[115],"emotional":[116],"changes.":[117],"This":[118],"paper":[119],"introduces":[120],"this":[121],"novel":[122],"framework":[123],"and":[124,133,178,189],"provides":[125],"insights":[126],"on":[127],"how":[128],"compare":[130],"signals.":[136],"Our":[137],"evaluations":[138],"demonstrate":[139],"benefits":[141],"incorporate":[149],"dependencies":[151],"recognition.":[154],"experimental":[156],"results":[157],"show":[158],"adding":[160],"contrasting":[164],"expressive":[165],"with":[167],"proposed":[169],"increases":[173],"accuracy":[175],"2.1%":[177],"2.8%":[179],"(absolute)":[180],"classifying":[182],"low":[183],"versus":[184],"high":[185],"levels":[186],"arousal":[188],"valence,":[190],"respectively.":[191]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}