{"id":"https://openalex.org/W4392909502","doi":"https://doi.org/10.1109/icassp48485.2024.10446253","title":"Fusing Multi-Level Features from Audio and Contextual Sentence Embedding from Text for Interview-Based Depression Detection","display_name":"Fusing Multi-Level Features from Audio and Contextual Sentence Embedding from Text for Interview-Based Depression Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392909502","doi":"https://doi.org/10.1109/icassp48485.2024.10446253"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10446253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","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/A5101319289","display_name":"Junqi Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junqi Xue","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101348525","display_name":"Ruihan Qin","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruihan Qin","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104260163","display_name":"Xinxu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinxu Zhou","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085867312","display_name":"Honghai Liu","orcid":"https://orcid.org/0000-0002-2880-4698"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Honghai Liu","raw_affiliation_strings":["School of Mechanical Engineering and Automation Harbin Institute of Technology,Shenzhen,China","School of Mechanical Engineering and Automation Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Mechanical Engineering and Automation Harbin Institute of Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Mechanical Engineering and Automation Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402911","display_name":"Min Zhang","orcid":"https://orcid.org/0000-0002-3895-5510"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min Zhang","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100363345","display_name":"Zhiguo Zhang","orcid":"https://orcid.org/0000-0001-7992-7965"},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiguo Zhang","raw_affiliation_strings":["Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,School of Computer Science and Technology,Shenzhen,China","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China","institution_ids":["https://openalex.org/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.48,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.95503501,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6790","last_page":"6794"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9890999794006348,"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"}},"topics":[{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9890999794006348,"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"}},{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.9718000292778015,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7043593525886536},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6051616072654724},{"id":"https://openalex.org/keywords/sentence","display_name":"Sentence","score":0.6013432145118713},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.46047085523605347},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.4107184410095215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39704012870788574},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3905888795852661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7043593525886536},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6051616072654724},{"id":"https://openalex.org/C2777530160","wikidata":"https://www.wikidata.org/wiki/Q41796","display_name":"Sentence","level":2,"score":0.6013432145118713},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.46047085523605347},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.4107184410095215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39704012870788574},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3905888795852661},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp48485.2024.10446253","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10446253","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1972723949","https://openalex.org/W1988653510","https://openalex.org/W2239141610","https://openalex.org/W2252180568","https://openalex.org/W2587078977","https://openalex.org/W2889056793","https://openalex.org/W2896457183","https://openalex.org/W2951019013","https://openalex.org/W2963150162","https://openalex.org/W2981501230","https://openalex.org/W3036601975","https://openalex.org/W3093051361","https://openalex.org/W3204491229","https://openalex.org/W3206529771","https://openalex.org/W4221162872","https://openalex.org/W4224917917","https://openalex.org/W4224924082","https://openalex.org/W4294975644","https://openalex.org/W4307820296","https://openalex.org/W4308065851","https://openalex.org/W4310333988","https://openalex.org/W4385805174","https://openalex.org/W6691669583","https://openalex.org/W6755207826","https://openalex.org/W6780218876"],"related_works":["https://openalex.org/W2081900870","https://openalex.org/W2375873920","https://openalex.org/W2345479200","https://openalex.org/W2183306018","https://openalex.org/W2146114872","https://openalex.org/W2392060890","https://openalex.org/W2849310602","https://openalex.org/W3006008237","https://openalex.org/W2392760275","https://openalex.org/W2597655663"],"abstract_inverted_index":{"Automatic":[0],"depression":[1,32,77,195],"detection":[2,78,196],"based":[3,80],"on":[4,81,175],"audio":[5,40,61,86,127,144],"and":[6,41,62,88,101,145,163,179],"text":[7,42,63,89,146],"representations":[8,64],"from":[9,43,104],"participants\u2019":[10],"interviews":[11,44],"has":[12,45,186],"attracted":[13],"widespread":[14],"attention.":[15],"However,":[16],"most":[17],"of":[18,25,27,39,84,122],"previous":[19],"researches":[20],"only":[21],"used":[22],"one":[23,28],"type":[24],"feature":[26],"single":[29],"modality":[30],"for":[31,124,193],"detection,":[33],"so":[34,184],"that":[35],"the":[36,58,82,105,161],"rich":[37],"information":[38],"not":[46],"been":[47],"fully":[48],"utilized.":[49],"Moreover,":[50],"an":[51],"effective":[52],"multi-modal":[53,75],"fusion":[54,76],"approach":[55],"to":[56,117,136,141,190],"leverage":[57],"independence":[59,162],"among":[60],"is":[65],"still":[66],"lacking.":[67],"To":[68],"address":[69],"these":[70,119],"problems,":[71],"we":[72,93,108,132,148],"propose":[73],"a":[74,110,125,150,187],"model":[79,171],"interaction":[83],"multilevel":[85],"features":[87,103,123],"sentence":[90],"embedding.":[91,139],"Specifically,":[92],"first":[94],"extract":[95,137],"Low-Level":[96],"Descriptors":[97],"(LLDs),":[98],"mel-spectrogram":[99],"features,":[100],"wav2vec":[102],"audio.":[106],"Then":[107],"design":[109,149],"Multi-level":[111],"Audio":[112],"Features":[113],"Interaction":[114],"Module":[115,155],"(MAFIM)":[116],"fuse":[118,143],"three":[120],"levels":[121],"comprehensive":[126],"representation.":[128],"For":[129],"interview":[130],"text,":[131],"use":[133],"pre-trained":[134],"BERT":[135],"sentence-level":[138],"Further,":[140],"effectively":[142],"representations,":[147],"Channel":[151],"Attention-based":[152],"Multi-modal":[153],"Fusion":[154],"(CAMFM)":[156],"by":[157],"taking":[158],"into":[159],"account":[160],"correlation":[164],"between":[165],"two":[166,176],"different":[167],"modalities.":[168],"Our":[169],"proposed":[170],"shows":[172],"better":[173],"performance":[174],"datasets,":[177],"DAIC-WOZ":[178],"EATD-Corpus,":[180],"than":[181],"existing":[182],"methods,":[183],"it":[185],"high":[188],"potential":[189],"be":[191],"applied":[192],"interview-based":[194],"in":[197],"practice.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}