{"id":"https://openalex.org/W4392904026","doi":"https://doi.org/10.1109/icassp48485.2024.10448231","title":"Promoting Independence of Depression and Speaker Features for Speaker Disentanglement in Speech-Based Depression Detection","display_name":"Promoting Independence of Depression and Speaker Features for Speaker Disentanglement in Speech-Based Depression Detection","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392904026","doi":"https://doi.org/10.1109/icassp48485.2024.10448231"},"language":"en","primary_location":{"id":"doi:10.1109/icassp48485.2024.10448231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448231","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/A5040294396","display_name":"Lishi Zuo","orcid":"https://orcid.org/0000-0002-7234-289X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Lishi Zuo","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068768998","display_name":"Man\u2010Wai Mak","orcid":"https://orcid.org/0000-0001-8854-3760"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Man-Wai Mak","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019467579","display_name":"Youzhi Tu","orcid":"https://orcid.org/0000-0002-9580-2414"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Youzhi Tu","raw_affiliation_strings":["The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University"],"affiliations":[{"raw_affiliation_string":"The Hong Kong Polytechnic University,Department of Electrical and Electronic Engineering","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5040294396"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":5.4038,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.9539949,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"10191","last_page":"10195"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12488","display_name":"Mental Health via Writing","score":0.9965999722480774,"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":0.9965999722480774,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9945999979972839,"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/T10667","display_name":"Emotion and Mood Recognition","score":0.992900013923645,"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/mutual-information","display_name":"Mutual information","score":0.6588547229766846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6392197608947754},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.6214233636856079},{"id":"https://openalex.org/keywords/speaker-diarisation","display_name":"Speaker diarisation","score":0.6143661737442017},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.57419353723526},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.47755345702171326},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.4575277268886566},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.42946675419807434},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4283989667892456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34415021538734436},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.18514645099639893},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17041859030723572},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09645101428031921}],"concepts":[{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.6588547229766846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6392197608947754},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.6214233636856079},{"id":"https://openalex.org/C149838564","wikidata":"https://www.wikidata.org/wiki/Q7574248","display_name":"Speaker diarisation","level":3,"score":0.6143661737442017},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.57419353723526},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.47755345702171326},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.4575277268886566},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.42946675419807434},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4283989667892456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34415021538734436},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.18514645099639893},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17041859030723572},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09645101428031921},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/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/icassp48485.2024.10448231","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448231","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":[{"id":"https://metadata.un.org/sdg/10","score":0.7200000286102295,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1981656674","https://openalex.org/W2003502731","https://openalex.org/W2530421149","https://openalex.org/W2973049979","https://openalex.org/W3024200162","https://openalex.org/W3191808899","https://openalex.org/W3198275944","https://openalex.org/W4206297453","https://openalex.org/W4221162874","https://openalex.org/W4224924082","https://openalex.org/W4251867726","https://openalex.org/W4296069164","https://openalex.org/W4297841418","https://openalex.org/W4297841836","https://openalex.org/W4385605894","https://openalex.org/W6684918901","https://openalex.org/W6691669583","https://openalex.org/W6734345245","https://openalex.org/W6762533536"],"related_works":["https://openalex.org/W2206035908","https://openalex.org/W2149220986","https://openalex.org/W1493012537","https://openalex.org/W4247736853","https://openalex.org/W2162158162","https://openalex.org/W1999004162","https://openalex.org/W2125642021","https://openalex.org/W1521049138","https://openalex.org/W2023466863","https://openalex.org/W2696990509"],"abstract_inverted_index":{"Recent":[0],"studies":[1],"have":[2],"demonstrated":[3],"the":[4,11,22,65,79,96,102,122],"effectiveness":[5,97],"of":[6,98,104],"speaker":[7,15,29,56,60,66,85,99,109],"disentanglement":[8,100],"in":[9,17],"mitigating":[10],"interference":[12],"caused":[13],"by":[14],"features":[16,27,30,57,67,86],"speech-based":[18],"depression":[19,26,34,45,54,83,107],"detection.":[20,35],"However,":[21],"inherent":[23],"entanglement":[24],"between":[25,53,82,106],"and":[28,55,77,84,101,108],"poses":[31],"challenges":[32],"to":[33,50,58,118],"In":[36],"this":[37],"study,":[38],"we":[39,63],"propose":[40],"a":[41,69,73,88],"mutual":[42,80,90],"information-based":[43],"speaker-invariant":[44],"detector":[46],"(MI-SIDD)":[47],"that":[48],"aims":[49],"promote":[51],"independence":[52,105],"facilitate":[59],"disentanglement.":[61],"Specifically,":[62],"disentangle":[64],"using":[68,87],"vanilla":[70],"autoencoder":[71],"with":[72],"well-tuned":[74],"bottleneck":[75],"layer":[76],"minimize":[78],"information":[81,91],"conditional":[89],"constraint.":[92],"Experimental":[93],"results":[94],"demonstrate":[95],"promotion":[103],"features.":[110],"Our":[111],"MI-SIDD":[112],"model":[113],"achieves":[114],"competitive":[115],"performance":[116],"compared":[117],"state-of-the-art":[119],"methods":[120],"on":[121],"DAIC-WOZ":[123],"dataset.":[124]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
