{"id":"https://openalex.org/W4297841808","doi":"https://doi.org/10.21437/interspeech.2022-10051","title":"ECAPA-TDNN Based Depression Detection from Clinical Speech","display_name":"ECAPA-TDNN Based Depression Detection from Clinical Speech","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4297841808","doi":"https://doi.org/10.21437/interspeech.2022-10051"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-10051","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10051","pdf_url":"https://www.isca-archive.org/interspeech_2022/wang22q_interspeech.pdf","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":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://www.isca-archive.org/interspeech_2022/wang22q_interspeech.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112505045","display_name":"Yanhui Ding","orcid":"https://orcid.org/0000-0002-4321-3036"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanhui Ding","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365847","display_name":"Qing Zhao","orcid":"https://orcid.org/0000-0002-9816-3611"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qing Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101282101","display_name":"Peilin Yang","orcid":"https://orcid.org/0000-0003-1944-9572"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peilin Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100787399","display_name":"Shuping Tan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuping Tan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100343662","display_name":"Ya Li","orcid":"https://orcid.org/0000-0002-6284-5039"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ya Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3333","last_page":"3337"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9186999797821045,"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":0.9186999797821045,"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/T12488","display_name":"Mental Health via Writing","score":0.9120000004768372,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social 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/computer-science","display_name":"Computer science","score":0.6913890838623047},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6058675646781921},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44634175300598145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36201539635658264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6913890838623047},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6058675646781921},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44634175300598145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36201539635658264}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-10051","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10051","pdf_url":"https://www.isca-archive.org/interspeech_2022/wang22q_interspeech.pdf","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"}],"best_oa_location":{"id":"doi:10.21437/interspeech.2022-10051","is_oa":true,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-10051","pdf_url":"https://www.isca-archive.org/interspeech_2022/wang22q_interspeech.pdf","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"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.41999998688697815}],"awards":[{"id":"https://openalex.org/G6685334198","display_name":null,"funder_award_id":"202200042","funder_id":"https://openalex.org/F4320326873","funder_display_name":"National Laboratory of Pattern Recognition"},{"id":"https://openalex.org/G7257301138","display_name":null,"funder_award_id":"2021RC37","funder_id":"https://openalex.org/F4320321470","funder_display_name":"Beijing University of Posts and Telecommunications"},{"id":"https://openalex.org/G7429218808","display_name":null,"funder_award_id":"ZR2020MF051","funder_id":"https://openalex.org/F4320324174","funder_display_name":"Natural Science Foundation of Shandong Province"}],"funders":[{"id":"https://openalex.org/F4320321470","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59"},{"id":"https://openalex.org/F4320324174","display_name":"Natural Science Foundation of Shandong Province","ror":null},{"id":"https://openalex.org/F4320326873","display_name":"National Laboratory of Pattern Recognition","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4297841808.pdf","grobid_xml":"https://content.openalex.org/works/W4297841808.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W4402327032","https://openalex.org/W2382290278"],"abstract_inverted_index":{"Depression":[0,81],"is":[1,39],"a":[2,28,41,63,91,98,111,133],"serious":[3],"mood":[4],"disorder":[5],"that":[6,14,127],"has":[7,26,132],"become":[8,27],"one":[9],"of":[10,21,35,57,68,115,120,140],"the":[11,32,50,58,76,128,138],"major":[12],"diseases":[13],"endanger":[15],"human":[16],"mental":[17],"health.The":[18],"automatic":[19],"detection":[20,94],"depression":[22,36,66,92,106],"using":[23],"speech":[24,74,93],"signals":[25],"promising":[29],"approach":[30,109],"for":[31,80],"early":[33],"diagnosis":[34,139],"currently.However,":[37],"there":[38],"still":[40],"performance":[42],"gap":[43],"between":[44],"clinical":[45,65,135],"practice":[46],"and":[47,117],"research,":[48],"considering":[49],"labrecorded":[51],"corpus":[52],"was":[53],"used":[54],"in":[55,86,137],"most":[56],"current":[59],"studies.Therefore,":[60],"we":[61,89],"collected":[62],"Chinese":[64],"corpus,":[67],"which":[69],"131":[70],"participants":[71],"with":[72],"their":[73],"during":[75],"Hamilton":[77],"Rating":[78],"Scale":[79],"(HAMD)":[82],"interview":[83],"were":[84],"included":[85],"this":[87],"study.Furthermore,":[88],"developed":[90,129],"system":[95],"based":[96],"on":[97],"Time-Delay":[99],"Neural":[100],"Network":[101],"(TDNN)":[102],"model":[103,131],"to":[104],"distinguish":[105],"i":[107],".Our":[108],"achieves":[110],"mean":[112],"F1":[113],"score":[114],"90.8%":[116],"an":[118],"accuracy":[119],"90.4%":[121],"by":[122],"five-fold":[123],"cross-validation.The":[124],"result":[125],"suggests":[126],"TDNN-based":[130],"potential":[134],"meaning":[136],"depression.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":7}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}