{"id":"https://openalex.org/W4408355405","doi":"https://doi.org/10.1109/icassp49660.2025.10889188","title":"A Frequency-aware Augmentation Network for Mental Disorders Assessment from Audio","display_name":"A Frequency-aware Augmentation Network for Mental Disorders Assessment from Audio","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355405","doi":"https://doi.org/10.1109/icassp49660.2025.10889188"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 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/A5103026192","display_name":"Shuanglin Li","orcid":"https://orcid.org/0009-0004-5421-3156"},"institutions":[{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuanglin Li","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University,U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University,U.K","institution_ids":["https://openalex.org/I4210105785"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115792133","display_name":"Siyang Song","orcid":null},"institutions":[{"id":"https://openalex.org/I153648349","display_name":"University of Leicester","ror":"https://ror.org/04h699437","country_code":"GB","type":"education","lineage":["https://openalex.org/I153648349"]},{"id":"https://openalex.org/I4210124601","display_name":"Department of Mathematical Sciences","ror":"https://ror.org/02xkdev90","country_code":"RU","type":"government","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210124601"]}],"countries":["GB","RU"],"is_corresponding":false,"raw_author_name":"Siyang Song","raw_affiliation_strings":["School of Computing and Mathematical Sciences, University of Leicester,U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computing and Mathematical Sciences, University of Leicester,U.K","institution_ids":["https://openalex.org/I153648349","https://openalex.org/I4210124601"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863342","display_name":"Rajesh Nair","orcid":"https://orcid.org/0000-0002-7223-4629"},"institutions":[{"id":"https://openalex.org/I240202130","display_name":"Cumbria Northumberland Tyne and Wear NHS Foundation Trust","ror":"https://ror.org/01ajv0n48","country_code":"GB","type":"healthcare","lineage":["https://openalex.org/I240202130"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rajesh Nair","raw_affiliation_strings":["Cumbria, Northumberland, Tyne and Wear, CNTW-NHS Foundation Trust,U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cumbria, Northumberland, Tyne and Wear, CNTW-NHS Foundation Trust,U.K","institution_ids":["https://openalex.org/I240202130"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053121936","display_name":"Syed Mohsen Naqvi","orcid":"https://orcid.org/0000-0002-1547-0908"},"institutions":[{"id":"https://openalex.org/I4210105785","display_name":"Intelligent Systems Research (United States)","ror":"https://ror.org/01reevc91","country_code":"US","type":"company","lineage":["https://openalex.org/I4210105785"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Syed Mohsen Naqvi","raw_affiliation_strings":["Intelligent Sensing and Communications Research Group, Newcastle University,U.K"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Intelligent Sensing and Communications Research Group, Newcastle University,U.K","institution_ids":["https://openalex.org/I4210105785"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.067,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.73764138,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10429","display_name":"EEG and Brain-Computer Interfaces","score":0.9682999849319458,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10667","display_name":"Emotion and Mood Recognition","score":0.9671000242233276,"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/T11021","display_name":"ECG Monitoring and Analysis","score":0.9596999883651733,"subfield":{"id":"https://openalex.org/subfields/2705","display_name":"Cardiology and Cardiovascular Medicine"},"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":0.6608028411865234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6608028411865234}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889188","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889188","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W1998512907","https://openalex.org/W2003502731","https://openalex.org/W2056403322","https://openalex.org/W2060779380","https://openalex.org/W2099917845","https://openalex.org/W2593898237","https://openalex.org/W2736814566","https://openalex.org/W2805409402","https://openalex.org/W2897623369","https://openalex.org/W2918745114","https://openalex.org/W2973178409","https://openalex.org/W3004047823","https://openalex.org/W3094259155","https://openalex.org/W3095858789","https://openalex.org/W3101080567","https://openalex.org/W3116242343","https://openalex.org/W3154272446","https://openalex.org/W3160076723","https://openalex.org/W3208158979","https://openalex.org/W3214493799","https://openalex.org/W3216528674","https://openalex.org/W4200634403","https://openalex.org/W4210893564","https://openalex.org/W4211094461","https://openalex.org/W4312627712","https://openalex.org/W4313312917","https://openalex.org/W4365420402","https://openalex.org/W4385731885","https://openalex.org/W4387730160","https://openalex.org/W4388699643","https://openalex.org/W4389101750","https://openalex.org/W4392157583","https://openalex.org/W4401942840","https://openalex.org/W4405754389","https://openalex.org/W6729858928"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Depression":[0],"and":[1,55,70,85,139,152],"Attention":[2],"Deficit":[3],"Hyperactivity":[4],"Disorder":[5],"(ADHD)":[6],"stand":[7],"out":[8],"as":[9,22,81],"the":[10,48,74,77,82,92,135,144,157],"common":[11],"mental":[12,26,101],"health":[13],"challenges":[14],"today.":[15],"In":[16,73],"affective":[17],"computing,":[18],"speech":[19],"signals":[20],"serve":[21],"effective":[23],"biomarkers":[24],"for":[25,47,68,168],"disorder":[27],"assessment.":[28,72],"Current":[29],"research,":[30],"relying":[31],"on":[32,95,149],"labor-intensive":[33],"hand-crafted":[34],"features":[35],"or":[36],"simplistic":[37],"time-frequency":[38],"representations,":[39],"often":[40],"overlooks":[41],"critical":[42],"details":[43],"by":[44],"not":[45],"accounting":[46],"differential":[49],"impacts":[50],"of":[51,143,159,164,176],"various":[52],"frequency":[53,97],"bands":[54,98],"temporal":[56],"fluctuations.":[57],"Therefore,":[58],"we":[59],"propose":[60],"a":[61,87,127],"frequency-aware":[62],"augmentation":[63,129],"network":[64,93],"with":[65,173],"dynamic":[66,104,124],"convolution":[67,89,105,112],"depression":[69,170],"ADHD":[71,154],"proposed":[75,132],"method,":[76,161],"spectrogram":[78],"is":[79,106,131],"used":[80],"input":[83],"feature":[84,128,136],"adopts":[86],"multi-scale":[88],"to":[90,100,109,122,133],"help":[91],"focus":[94],"discriminative":[96],"related":[99],"disorders.":[102],"A":[103],"also":[107],"designed":[108],"aggregate":[110],"multiple":[111],"kernels":[113],"dynamically":[114],"based":[115],"upon":[116],"their":[117],"attentions":[118],"which":[119],"are":[120],"input-independent":[121],"capture":[123],"information.":[125,146],"Finally,":[126],"block":[130],"enhance":[134],"representation":[137],"ability":[138],"make":[140],"full":[141],"use":[142],"captured":[145],"Experimental":[147],"results":[148],"AVEC":[150],"2014":[151],"self-recorded":[153],"dataset":[155],"prove":[156],"robustness":[158],"our":[160],"an":[162,174],"RMSE":[163],"9.23":[165],"was":[166],"attained":[167],"estimating":[169],"severity,":[171],"along":[172],"accuracy":[175],"89.8%":[177],"in":[178],"detecting":[179],"ADHD.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}