{"id":"https://openalex.org/W2936669509","doi":"https://doi.org/10.1109/icassp.2019.8683273","title":"Retrieving Speech Samples with Similar Emotional Content Using a Triplet Loss Function","display_name":"Retrieving Speech Samples with Similar Emotional Content Using a Triplet Loss Function","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936669509","doi":"https://doi.org/10.1109/icassp.2019.8683273","mag":"2936669509"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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/A5078256928","display_name":"John Harvill","orcid":"https://orcid.org/0000-0003-3633-6756"},"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":"John Harvill","raw_affiliation_strings":["Multimodal Signal Processing (MSP) Laboratory, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimodal Signal Processing (MSP) Laboratory, The University of Texas at Dallas, Richardson, TX, USA","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112428597","display_name":"Mohammed Abdel Wahab","orcid":null},"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":"Mohammed Abdel Wahab","raw_affiliation_strings":["University of Texas at Dallas, Richardson, TX, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Texas at Dallas, Richardson, TX, US","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","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":["Multimodal Signal Processing (MSP) Laboratory, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimodal Signal Processing (MSP) Laboratory, The University of Texas at Dallas, Richardson, TX, 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":["Multimodal Signal Processing (MSP) Laboratory, The University of Texas at Dallas, Richardson, TX, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Multimodal Signal Processing (MSP) Laboratory, The University of Texas at Dallas, Richardson, TX, 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":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"7400","last_page":"7404"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9998000264167786,"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":0.9998000264167786,"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/T11309","display_name":"Music and Audio Processing","score":0.9998000264167786,"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":0.9997000098228455,"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/discriminative-model","display_name":"Discriminative model","score":0.7735202312469482},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7620272040367126},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6363319158554077},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6201571226119995},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.548029899597168},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5286446213722229},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45353221893310547},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4119633436203003},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.4104440212249756},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3535391688346863},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08531180024147034}],"concepts":[{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7735202312469482},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7620272040367126},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6363319158554077},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6201571226119995},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.548029899597168},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286446213722229},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45353221893310547},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4119633436203003},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.4104440212249756},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3535391688346863},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08531180024147034},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683273","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683273","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"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":40,"referenced_works":["https://openalex.org/W200033050","https://openalex.org/W1951445929","https://openalex.org/W1955614066","https://openalex.org/W2026984028","https://openalex.org/W2064149108","https://openalex.org/W2085662862","https://openalex.org/W2096733369","https://openalex.org/W2102953093","https://openalex.org/W2144005487","https://openalex.org/W2144264893","https://openalex.org/W2144723972","https://openalex.org/W2161459043","https://openalex.org/W2396294578","https://openalex.org/W2404190044","https://openalex.org/W2404446881","https://openalex.org/W2404863510","https://openalex.org/W2491770404","https://openalex.org/W2508783453","https://openalex.org/W2518511005","https://openalex.org/W2525412388","https://openalex.org/W2673304402","https://openalex.org/W2742542661","https://openalex.org/W2747172199","https://openalex.org/W2787552263","https://openalex.org/W2804664105","https://openalex.org/W2889065492","https://openalex.org/W2889100420","https://openalex.org/W2889113107","https://openalex.org/W2899500748","https://openalex.org/W2900358852","https://openalex.org/W2962839749","https://openalex.org/W3099206234","https://openalex.org/W6608182480","https://openalex.org/W6681409903","https://openalex.org/W6713388680","https://openalex.org/W6713499852","https://openalex.org/W6742965559","https://openalex.org/W6755756314","https://openalex.org/W6756023270","https://openalex.org/W7073743773"],"related_works":["https://openalex.org/W3135230428","https://openalex.org/W2904739811","https://openalex.org/W2152158029","https://openalex.org/W2012540220","https://openalex.org/W2559837139","https://openalex.org/W1151175420","https://openalex.org/W2166690696","https://openalex.org/W2131711534","https://openalex.org/W2559040841","https://openalex.org/W114661351"],"abstract_inverted_index":{"The":[0,132],"ability":[1],"to":[2,11,54,62,94,148,161,190],"identify":[3],"speech":[4,15,20,26,56,65,137,142,154],"with":[5,175,196],"similar":[6,61,197],"emotional":[7,19,159,198],"content":[8,160],"is":[9,127,147],"valuable":[10],"many":[12],"applications,":[13],"including":[14],"retrieval,":[16],"surveillance,":[17],"and":[18,139,144],"synthesis.":[21],"While":[22],"current":[23],"formulations":[24],"in":[25,193],"emotion":[27,163],"recognition":[28],"based":[29,41],"on":[30,42],"classification":[31],"or":[32],"regression":[33],"are":[34,59],"not":[35],"appropriate":[36],"for":[37,48,129],"this":[38,49,84,101,130,179],"task,":[39],"solutions":[40],"preference":[43],"learning":[44,112],"offer":[45],"appealing":[46],"approaches":[47],"task.":[50,131],"This":[51,71,103],"paper":[52],"aims":[53],"find":[55],"samples":[57,195],"that":[58,126,182],"emotionally":[60],"an":[63,124,135],"anchor":[64,136],"sample":[66,138,155],"provided":[67],"as":[68],"a":[69,81,98,110,115],"query.":[70],"novel":[72],"formulation":[73],"opens":[74],"interesting":[75],"research":[76],"questions.":[77],"How":[78,86],"well":[79],"can":[80],"machine":[82],"complete":[83],"task?":[85,102],"does":[87],"the":[88,95,120,145,152,157,162,166,170,183],"accuracy":[89],"of":[90,97,151],"automatic":[91],"algorithms":[92],"compare":[93],"performance":[96,187,192],"human":[99,176,191],"performing":[100],"study":[104,180],"addresses":[105],"these":[106],"questions":[107],"by":[108,165],"training":[109],"deep":[111],"model":[113,174],"using":[114],"triplet":[116],"loss":[117],"function,":[118],"mapping":[119],"acoustic":[121],"features":[122],"into":[123],"embedding":[125],"discriminative":[128],"network":[133],"receives":[134],"two":[140],"competing":[141],"samples,":[143],"task":[146],"determine":[149],"which":[150],"candidate":[153],"conveys":[156],"closest":[158],"conveyed":[164],"anchor.":[167],"By":[168],"comparing":[169],"results":[171],"from":[172],"our":[173],"perceptual":[177],"evaluations,":[178],"demonstrates":[181],"proposed":[184],"approach":[185],"has":[186],"very":[188],"close":[189],"retrieving":[194],"content.":[199]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}