{"id":"https://openalex.org/W2936879941","doi":"https://doi.org/10.1109/icassp.2019.8683498","title":"Learning Voice Source Related Information for Depression Detection","display_name":"Learning Voice Source Related Information for Depression Detection","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2936879941","doi":"https://doi.org/10.1109/icassp.2019.8683498","mag":"2936879941"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683498","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":true,"oa_status":"green","oa_url":"http://infoscience.epfl.ch/record/264110","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008235303","display_name":"S. Pavankumar Dubagunta","orcid":"https://orcid.org/0000-0002-4307-8604"},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"S. Pavankumar Dubagunta","raw_affiliation_strings":["\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"\u00c9cole polytechnique f\u00e9d\u00e9rale de Lausanne (EPFL), Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087200921","display_name":"Bogdan Vlasenko","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bogdan Vlasenko","raw_affiliation_strings":["VIMA, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VIMA, Martigny, Switzerland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043551083","display_name":"Mathew Magimai.-Doss","orcid":"https://orcid.org/0000-0002-8714-1409"},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Mathew Magimai.-Doss","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.4053,"has_fulltext":false,"cited_by_count":40,"citation_normalized_percentile":{"value":0.9204464,"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":"6525","last_page":"6529"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9988999962806702,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7080570459365845},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.6669284105300903},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6216912269592285},{"id":"https://openalex.org/keywords/neurophysiology","display_name":"Neurophysiology","score":0.5586002469062805},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5549383163452148},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47561079263687134},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4316604733467102},{"id":"https://openalex.org/keywords/information-source","display_name":"Information source (mathematics)","score":0.4302177131175995},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4176393151283264},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35271066427230835},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.3307057023048401},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14796903729438782},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1455363631248474},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.10170552134513855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7080570459365845},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.6669284105300903},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6216912269592285},{"id":"https://openalex.org/C152478114","wikidata":"https://www.wikidata.org/wiki/Q660910","display_name":"Neurophysiology","level":2,"score":0.5586002469062805},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5549383163452148},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47561079263687134},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4316604733467102},{"id":"https://openalex.org/C2778095710","wikidata":"https://www.wikidata.org/wiki/Q6031225","display_name":"Information source (mathematics)","level":2,"score":0.4302177131175995},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4176393151283264},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35271066427230835},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.3307057023048401},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14796903729438782},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1455363631248474},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.10170552134513855},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/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":2,"locations":[{"id":"doi:10.1109/icassp.2019.8683498","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683498","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"},{"id":"pmh:oai:infoscience.epfl.ch:264110","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/264110","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":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"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":"http://infoscience.epfl.ch/record/264110","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:infoscience.epfl.ch:264110","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/264110","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":"https://openalex.org/I5124864","host_organization_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","host_organization_lineage":["https://openalex.org/I5124864"],"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":"http://infoscience.epfl.ch/record/264110","raw_type":"Text"},"sustainable_development_goals":[{"score":0.7099999785423279,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W158097101","https://openalex.org/W204854131","https://openalex.org/W407558922","https://openalex.org/W1966264494","https://openalex.org/W1967625181","https://openalex.org/W1990043338","https://openalex.org/W2003502731","https://openalex.org/W2048533792","https://openalex.org/W2095176743","https://openalex.org/W2099076569","https://openalex.org/W2100971813","https://openalex.org/W2112844139","https://openalex.org/W2118225053","https://openalex.org/W2157225271","https://openalex.org/W2172110927","https://openalex.org/W2251335235","https://openalex.org/W2252180568","https://openalex.org/W2270987589","https://openalex.org/W2346454595","https://openalex.org/W2402715013","https://openalex.org/W2403913915","https://openalex.org/W2509484810","https://openalex.org/W2515456817","https://openalex.org/W2530421149","https://openalex.org/W2566781703","https://openalex.org/W2593853439","https://openalex.org/W2748488613","https://openalex.org/W2748516598","https://openalex.org/W2770454110","https://openalex.org/W2805409402","https://openalex.org/W2885329609","https://openalex.org/W2887376701","https://openalex.org/W2887949187","https://openalex.org/W2888918744","https://openalex.org/W2889056793","https://openalex.org/W2889150482","https://openalex.org/W2889378348","https://openalex.org/W2963175699","https://openalex.org/W6678409544","https://openalex.org/W6691669583","https://openalex.org/W6693639690","https://openalex.org/W6713212581","https://openalex.org/W6753678270","https://openalex.org/W7028400246"],"related_works":["https://openalex.org/W2400533375","https://openalex.org/W2097143083","https://openalex.org/W642007152","https://openalex.org/W2401827384","https://openalex.org/W4304187160","https://openalex.org/W2052688117","https://openalex.org/W2552102772","https://openalex.org/W4294771049","https://openalex.org/W1523214805","https://openalex.org/W2168417340"],"abstract_inverted_index":{"During":[0],"depression":[1,74,107],"neurophysiological":[2],"changes":[3,19],"can":[4],"occur,":[5],"which":[6],"may":[7],"affect":[8],"laryngeal":[9],"control":[10],"i.e.":[11],"behaviour":[12],"of":[13,38,52,80,116],"the":[14,39,50,59,131,144],"vocal":[15,145],"folds.":[16],"Characterising":[17],"these":[18],"in":[20],"a":[21,28],"precise":[22],"manner":[23],"from":[24,43,58],"speech":[25,84],"signals":[26,94,99,120,125],"is":[27],"non":[29],"trivial":[30],"task,":[31],"as":[32],"this":[33,46],"typically":[34],"involves":[35],"reliable":[36],"separation":[37],"voice":[40,69,92,102],"source":[41,70,93,103],"information":[42,57,72,105],"them.":[44],"In":[45],"paper,":[47],"by":[48],"exploiting":[49],"abilities":[51],"CNNs":[53],"to":[54,67,100,127],"learn":[55,101],"task-relevant":[56],"input":[60],"raw":[61],"signals,":[62,85,89],"we":[63,77],"investigate":[64,78],"several":[65],"methods":[66],"model":[68],"related":[71,104],"for":[73,106],"detection.":[75,108],"Specifically,":[76],"modelling":[79,115,143],"low":[81,133],"pass":[82],"filtered":[83,91,98,124],"linear":[86,117],"prediction":[87,118],"residual":[88,119],"homomorphically":[90],"and":[95,138],"zero":[96,122],"frequency":[97,123],"Our":[109],"investigations":[110],"show":[111],"that":[112],"subsegmental":[113],"level":[114,134],"or":[121],"leads":[126],"systems":[128,137,142],"better":[129],"than":[130],"state-of-the-art":[132],"descriptor":[135],"based":[136,141],"deep":[139],"learning":[140],"tract":[146],"system":[147],"information.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2}],"updated_date":"2026-08-13T07:04:57.449891","created_date":"2025-10-10T00:00:00"}