{"id":"https://openalex.org/W4410027603","doi":"https://doi.org/10.1109/jbhi.2025.3566767","title":"Vector Quantization-Based Counterfactual Augmentation for Speech-Based Depression Detection Under Data Scarcity","display_name":"Vector Quantization-Based Counterfactual Augmentation for Speech-Based Depression Detection Under Data Scarcity","publication_year":2025,"publication_date":"2025-05-02","ids":{"openalex":"https://openalex.org/W4410027603","doi":"https://doi.org/10.1109/jbhi.2025.3566767","pmid":"https://pubmed.ncbi.nlm.nih.gov/40315097"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2025.3566767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3566767","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"last","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":["Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronic Engineering, The Hong Kong Polytechnic University, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5040294396"],"corresponding_institution_ids":["https://openalex.org/I14243506"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04185291,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":"10","first_page":"7559","last_page":"7567"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.8389000296592712,"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":0.8389000296592712,"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":0.7797999978065491,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.7247911095619202},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6149541735649109},{"id":"https://openalex.org/keywords/vector-quantization","display_name":"Vector quantization","score":0.6121808290481567},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.5387670993804932},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.48009875416755676},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46628332138061523},{"id":"https://openalex.org/keywords/scarcity","display_name":"Scarcity","score":0.4497350752353668},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4472177028656006},{"id":"https://openalex.org/keywords/linde\u2013buzo\u2013gray-algorithm","display_name":"Linde\u2013Buzo\u2013Gray algorithm","score":0.4404389560222626},{"id":"https://openalex.org/keywords/learning-vector-quantization","display_name":"Learning vector quantization","score":0.4371386766433716},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.26803863048553467},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.2253418266773224},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.12408056855201721},{"id":"https://openalex.org/keywords/economics","display_name":"Economics","score":0.11517795920372009}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.7247911095619202},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6149541735649109},{"id":"https://openalex.org/C199833920","wikidata":"https://www.wikidata.org/wiki/Q612536","display_name":"Vector quantization","level":2,"score":0.6121808290481567},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.5387670993804932},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.48009875416755676},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46628332138061523},{"id":"https://openalex.org/C109747225","wikidata":"https://www.wikidata.org/wiki/Q815758","display_name":"Scarcity","level":2,"score":0.4497350752353668},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4472177028656006},{"id":"https://openalex.org/C93372532","wikidata":"https://www.wikidata.org/wiki/Q6552455","display_name":"Linde\u2013Buzo\u2013Gray algorithm","level":3,"score":0.4404389560222626},{"id":"https://openalex.org/C40567965","wikidata":"https://www.wikidata.org/wiki/Q1820283","display_name":"Learning vector quantization","level":3,"score":0.4371386766433716},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.26803863048553467},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2253418266773224},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.12408056855201721},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.11517795920372009},{"id":"https://openalex.org/C175444787","wikidata":"https://www.wikidata.org/wiki/Q39072","display_name":"Microeconomics","level":1,"score":0.0},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003863","descriptor_name":"Depression","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003863","descriptor_name":"Depression","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003863","descriptor_name":"Depression","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003863","descriptor_name":"Depression","qualifier_ui":"Q000175","qualifier_name":"diagnosis","is_major_topic":true},{"descriptor_ui":"D003936","descriptor_name":"Diagnosis, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D003936","descriptor_name":"Diagnosis, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D003936","descriptor_name":"Diagnosis, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D003936","descriptor_name":"Diagnosis, Computer-Assisted","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005260","descriptor_name":"Female","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012815","descriptor_name":"Signal Processing, Computer-Assisted","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1109/jbhi.2025.3566767","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2025.3566767","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:40315097","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40315097","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE journal of biomedical and health informatics","raw_type":null},{"id":"pmh:oai:ira.lib.polyu.edu.hk:10397/113413","is_oa":false,"landing_page_url":"http://hdl.handle.net/10397/113413","pdf_url":null,"source":{"id":"https://openalex.org/S4306400205","display_name":"PolyU Institutional Research Archive (Hong Kong Polytechnic University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I14243506","host_organization_name":"Hong Kong Polytechnic University","host_organization_lineage":["https://openalex.org/I14243506"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Journal/Magazine Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1981656674","https://openalex.org/W2003502731","https://openalex.org/W2048533792","https://openalex.org/W2057393928","https://openalex.org/W2080298947","https://openalex.org/W2530421149","https://openalex.org/W2593853439","https://openalex.org/W2807869636","https://openalex.org/W2889056793","https://openalex.org/W2909392392","https://openalex.org/W2958946409","https://openalex.org/W2962793481","https://openalex.org/W2963125461","https://openalex.org/W2970963824","https://openalex.org/W2972724712","https://openalex.org/W2973049979","https://openalex.org/W2981677410","https://openalex.org/W3004492706","https://openalex.org/W3020674209","https://openalex.org/W3092190487","https://openalex.org/W3094977969","https://openalex.org/W3111789454","https://openalex.org/W3134427999","https://openalex.org/W3155044607","https://openalex.org/W3161779466","https://openalex.org/W3183605589","https://openalex.org/W4206297453","https://openalex.org/W4221162874","https://openalex.org/W4224247713","https://openalex.org/W4224924082","https://openalex.org/W4225304582","https://openalex.org/W4251867726","https://openalex.org/W4297841836","https://openalex.org/W4317436377","https://openalex.org/W4385605894","https://openalex.org/W4386524186","https://openalex.org/W4388767362","https://openalex.org/W4390226844","https://openalex.org/W4392904026","https://openalex.org/W4393159919","https://openalex.org/W4396911963"],"related_works":["https://openalex.org/W2352648934","https://openalex.org/W2378212145","https://openalex.org/W2100968651","https://openalex.org/W2158420043","https://openalex.org/W2071781501","https://openalex.org/W4243803532","https://openalex.org/W1805748654","https://openalex.org/W3193872944","https://openalex.org/W116978123","https://openalex.org/W1530767163"],"abstract_inverted_index":{"Data":[0],"scarcity":[1],"is":[2,45],"a":[3,26,60,64,80],"common":[4],"and":[5,15,111,142],"serious":[6],"problem":[7],"in":[8,92,139],"depression":[9,22,37,130],"detection,":[10],"often":[11],"leading":[12],"to":[13,63,67,75,125],"overfitting":[14,110],"bias":[16,112],"that":[17,31,105],"degrade":[18],"the":[19,53,69,72,86,90,100,109,135],"performance":[20,123],"of":[21,71,137],"detectors.":[23],"We":[24,132],"propose":[25],"counterfactual":[27,61],"augmentation":[28],"(CF-aug)":[29],"framework":[30,120],"generates":[32],"latent":[33],"features":[34],"for":[35,144],"speech-based":[36],"detection":[38],"under":[39,147],"data-scarce":[40,148],"conditions.":[41],"The":[42],"generation":[43],"method":[44],"based":[46],"on":[47,128],"exploring":[48],"how":[49,89],"feature":[50],"changes":[51,91],"affect":[52,99],"outcomes.":[54],"To":[55],"this":[56],"end,":[57],"we":[58],"introduce":[59],"layer":[62],"deep":[65],"network":[66],"transform":[68],"representation":[70],"original":[73],"data":[74,116],"its":[76],"opposite":[77],"class,":[78],"while":[79],"group-wise":[81],"vector":[82],"quantization":[83],"module":[84],"helps":[85],"model":[87],"explore":[88],"vectors":[93],"(or":[94],"entries)":[95],"sampled":[96],"from":[97],"codebooks":[98],"outcome.":[101],"Experimental":[102],"results":[103],"demonstrate":[104,134],"CF-aug":[106,119,138],"can":[107],"alleviate":[108],"problems":[113],"caused":[114],"by":[115],"scarcity.":[117],"Our":[118],"achieves":[121],"competitive":[122],"compared":[124],"state-of-the-art":[126],"methods":[127],"two":[129],"datasets.":[131],"also":[133],"potential":[136],"other":[140],"domains":[141],"modalities":[143],"medical":[145],"diagnosis":[146],"settings.":[149]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
