{"id":"https://openalex.org/W4226462964","doi":"https://doi.org/10.21437/interspeech.2022-10498","title":"Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load","display_name":"Hybrid Handcrafted and Learnable Audio Representation for Analysis of Speech Under Cognitive and Physical Load","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4226462964","doi":"https://doi.org/10.21437/interspeech.2022-10498"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10498","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10498","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.16637","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008399208","display_name":"Gasser Elbanna","orcid":"https://orcid.org/0009-0002-2077-548X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Gasser Elbanna","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045332368","display_name":"Alice Biryukov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alice Biryukov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055084920","display_name":"Neil Scheidwasser","orcid":"https://orcid.org/0000-0001-9922-0289"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Neil Scheidwasser-Clow","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015086775","display_name":"Lara Orlandic","orcid":"https://orcid.org/0000-0002-4078-7528"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lara Orlandic","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008181078","display_name":"Pablo Mainar","orcid":"https://orcid.org/0009-0005-9662-492X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pablo Mainar","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029632932","display_name":"Mikolaj Kegler","orcid":"https://orcid.org/0000-0003-3408-2588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mikolaj Kegler","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012253790","display_name":"Pierre Beckmann","orcid":"https://orcid.org/0000-0001-9247-4841"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pierre Beckmann","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5003558571","display_name":"Milo\u0161 Cer\u0148ak","orcid":"https://orcid.org/0000-0002-5569-9491"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milos Cernak","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5008399208"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1393,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.28893242,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9609000086784363,"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":0.9609000086784363,"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/paralanguage","display_name":"Paralanguage","score":0.7467782497406006},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7159329652786255},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.559384286403656},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.5314722657203674},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5306215286254883},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5228039026260376},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.521953284740448},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.47691652178764343},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.4444468021392822},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.43993061780929565},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.42820024490356445},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3727879226207733},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.21138057112693787},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.10788300633430481}],"concepts":[{"id":"https://openalex.org/C133378560","wikidata":"https://www.wikidata.org/wiki/Q1753225","display_name":"Paralanguage","level":2,"score":0.7467782497406006},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7159329652786255},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.559384286403656},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.5314722657203674},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5306215286254883},{"id":"https://openalex.org/C21036866","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5228039026260376},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.521953284740448},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.47691652178764343},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.4444468021392822},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.43993061780929565},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.42820024490356445},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3727879226207733},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.21138057112693787},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.10788300633430481},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","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/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.21437/interspeech.2022-10498","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10498","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2022","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2203.16637","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.16637","pdf_url":"https://arxiv.org/pdf/2203.16637","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:infoscience.epfl.ch:301513","is_oa":true,"landing_page_url":"https://infoscience.epfl.ch/handle/20.500.14299/196514","pdf_url":null,"source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"WoS","raw_type":"conference proceedings"},{"id":"doi:10.48550/arxiv.2203.16637","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.16637","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.16637","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.16637","pdf_url":"https://arxiv.org/pdf/2203.16637","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.7900000214576721,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W587737","https://openalex.org/W7174772","https://openalex.org/W14326248","https://openalex.org/W15113896","https://openalex.org/W6060060","https://openalex.org/W13021510","https://openalex.org/W14486930","https://openalex.org/W9986601","https://openalex.org/W9733432","https://openalex.org/W7326553"],"abstract_inverted_index":{"As":[0],"a":[1,44,116,146,152,163],"neurophysiological":[2],"response":[3],"to":[4,52,97,159],"threat":[5],"or":[6,135],"adverse":[7],"conditions,":[8],"stress":[9,64,91,109,137],"can":[10],"affect":[11],"cognition,":[12],"emotion":[13],"and":[14,41,103,161,176,193],"behaviour":[15],"with":[16,145],"potentially":[17],"detrimental":[18],"effects":[19],"on":[20,84],"health":[21],"in":[22,92,106,125,140],"the":[23,29,53,78,98,107,141,157,170,177,184],"case":[24],"of":[25,32,47,55,58,80,101,118,143,149,172,179],"sustained":[26],"exposure.":[27],"Since":[28],"affective":[30],"content":[31],"speech":[33,93],"is":[34],"inherently":[35],"modulated":[36],"by":[37],"an":[38],"individual's":[39],"physical":[40,136],"mental":[42],"state,":[43],"substantial":[45],"body":[46],"research":[48],"has":[49,67],"been":[50,68],"devoted":[51],"study":[54],"paralinguistic":[56],"correlates":[57],"stress-inducing":[59],"task":[60,122],"load.":[61],"Historically,":[62],"voice":[63,128],"analysis":[65],"(VSA)":[66],"conducted":[69],"using":[70],"conventional":[71],"digital":[72],"signal":[73],"processing":[74],"(DSP)":[75],"techniques.":[76],"Despite":[77],"development":[79],"modern":[81],"methods":[82],"based":[83],"deep":[85],"neural":[86],"networks":[87],"(DNNs),":[88],"accurately":[89],"detecting":[90],"remains":[94],"difficult":[95],"due":[96],"wide":[99],"variety":[100],"stressors":[102],"considerable":[104],"variability":[105],"individual":[108],"perception.":[110],"To":[111],"that":[112,168],"end,":[113],"we":[114],"introduce":[115],"set":[117],"five":[119],"datasets":[120,158],"for":[121],"load":[123],"detection":[124],"speech.":[126],"The":[127],"recordings":[129],"were":[130],"collected":[131],"as":[132],"either":[133],"cognitive":[134],"was":[138],"induced":[139],"cohort":[142],"volunteers,":[144],"cumulative":[147],"number":[148],"more":[150],"than":[151],"hundred":[153],"speakers.":[154],"We":[155],"used":[156],"design":[160],"evaluate":[162],"novel":[164,194],"self-supervised":[165],"audio":[166,196],"representation":[167,197],"leverages":[169],"effectiveness":[171],"handcrafted":[173,190],"features":[174],"(DSP-based)":[175],"complexity":[178],"data-driven":[180],"DNN":[181],"representations.":[182],"Notably,":[183],"proposed":[185],"approach":[186],"outperformed":[187],"both":[188],"extensive":[189],"feature":[191],"sets":[192],"DNN-based":[195],"learning":[198],"approaches.":[199]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2022-05-05T00:00:00"}