{"id":"https://openalex.org/W4408345731","doi":"https://doi.org/10.1109/icassp49660.2025.10889290","title":"Efficient Long Speech Sequence Modelling for Time-Domain Depression Level Estimation","display_name":"Efficient Long Speech Sequence Modelling for Time-Domain Depression Level Estimation","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408345731","doi":"https://doi.org/10.1109/icassp49660.2025.10889290"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889290","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":"conference-paper","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/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Shuanglin Li","raw_affiliation_strings":["Newcastle University,Intelligent Sensing and Communications Research Group,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University,Intelligent Sensing and Communications Research Group,UK","institution_ids":["https://openalex.org/I84884186"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017666991","display_name":"Zhijie Xie","orcid":"https://orcid.org/0000-0002-1104-2375"},"institutions":[{"id":"https://openalex.org/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zhijie Xie","raw_affiliation_strings":["Newcastle University,Intelligent Sensing and Communications Research Group,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University,Intelligent Sensing and Communications Research Group,UK","institution_ids":["https://openalex.org/I84884186"]}]},{"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/I84884186","display_name":"Newcastle University","ror":"https://ror.org/01kj2bm70","country_code":"GB","type":"education","lineage":["https://openalex.org/I84884186"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Syed Mohsen Naqvi","raw_affiliation_strings":["Newcastle University,Intelligent Sensing and Communications Research Group,UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Newcastle University,Intelligent Sensing and Communications Research Group,UK","institution_ids":["https://openalex.org/I84884186"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I84884186"],"apc_list":null,"apc_paid":null,"fwci":10.3502,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.98213446,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.8998000025749207,"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":0.8998000025749207,"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/estimation","display_name":"Estimation","score":0.6645455956459045},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6408911347389221},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5823351740837097},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5117301940917969},{"id":"https://openalex.org/keywords/depression","display_name":"Depression (economics)","score":0.45554155111312866},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4434857964515686},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32093021273612976},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16489630937576294},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.09379908442497253}],"concepts":[{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.6645455956459045},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6408911347389221},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5823351740837097},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5117301940917969},{"id":"https://openalex.org/C2776867660","wikidata":"https://www.wikidata.org/wiki/Q1814941","display_name":"Depression (economics)","level":2,"score":0.45554155111312866},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4434857964515686},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32093021273612976},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16489630937576294},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09379908442497253},{"id":"https://openalex.org/C139719470","wikidata":"https://www.wikidata.org/wiki/Q39680","display_name":"Macroeconomics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889290","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889290","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":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1976066595","https://openalex.org/W1998512907","https://openalex.org/W2056403322","https://openalex.org/W2148822124","https://openalex.org/W2519531315","https://openalex.org/W2973178409","https://openalex.org/W3015199127","https://openalex.org/W3094259155","https://openalex.org/W3096893582","https://openalex.org/W3134427999","https://openalex.org/W3163652268","https://openalex.org/W3197466182","https://openalex.org/W3214493799","https://openalex.org/W4225308041","https://openalex.org/W4293363567","https://openalex.org/W4302275239","https://openalex.org/W4313887688","https://openalex.org/W4368232813","https://openalex.org/W4385731885","https://openalex.org/W4392157583","https://openalex.org/W4401609625","https://openalex.org/W4401942840","https://openalex.org/W4405754389","https://openalex.org/W4410087476","https://openalex.org/W6739901393","https://openalex.org/W6802912272","https://openalex.org/W6803444062","https://openalex.org/W6859298233"],"related_works":["https://openalex.org/W2576994247","https://openalex.org/W2608353378","https://openalex.org/W4249206767","https://openalex.org/W2086259589","https://openalex.org/W2563559453","https://openalex.org/W2382330008","https://openalex.org/W1519970947","https://openalex.org/W4243860260","https://openalex.org/W2012885586","https://openalex.org/W4383503847"],"abstract_inverted_index":{"Depression":[0],"significantly":[1],"affects":[2],"emotions,":[3],"thoughts,":[4],"and":[5,59,91,97,137,144,162,174],"daily":[6],"activities.":[7],"Recent":[8],"research":[9],"indicates":[10],"that":[11],"speech":[12,37,65,114],"signals":[13,115],"contain":[14],"vital":[15],"cues":[16,150,173],"about":[17],"depression,":[18],"sparking":[19],"interest":[20],"in":[21,94,116,152,168],"audiobased":[22],"deep-learning":[23],"methods":[24,31],"for":[25,43,108],"estimating":[26],"its":[27],"severity.":[28],"However,":[29],"most":[30],"rely":[32],"on":[33,100,159],"time-frequency":[34,54],"representations":[35],"of":[36,50,148],"which":[38],"have":[39],"recently":[40],"been":[41],"criticized":[42],"their":[44,95],"limitations":[45],"due":[46],"to":[47,142],"the":[48,117,130,146,153,160,179],"loss":[49],"information":[51],"when":[52],"performing":[53],"projections,":[55],"e.g.":[56],"Fourier":[57],"transform,":[58],"Mel-scale":[60],"transformation.":[61],"Furthermore,":[62],"segmenting":[63],"real-world":[64,83],"into":[66],"brief":[67],"intervals":[68],"risks":[69],"losing":[70],"critical":[71],"interconnections":[72],"between":[73],"recordings.":[74],"Additionally,":[75],"such":[76],"an":[77,105],"approach":[78],"may":[79],"not":[80],"adequately":[81],"reflect":[82],"scenarios,":[84],"as":[85],"individuals":[86],"with":[87,129],"depression":[88,109,172],"often":[89],"pause":[90],"slow":[92],"down":[93],"conversations":[96],"interactions.":[98],"Building":[99],"these":[101],"observations,":[102],"we":[103],"present":[104],"efficient":[106],"method":[107,122],"level":[110],"estimation":[111],"using":[112],"long":[113,133],"time":[118],"domain.":[119],"The":[120],"proposed":[121],"leverages":[123],"a":[124],"state":[125],"space":[126],"model":[127],"coupled":[128],"dual-path":[131],"structure-based":[132],"sequence":[134],"modelling":[135],"module":[136,141],"temporal":[138],"external":[139],"attention":[140],"reconstruct":[143],"enhance":[145],"detection":[147],"depression-related":[149],"hidden":[151],"raw":[154],"audio":[155],"waveforms.":[156],"Experimental":[157],"results":[158,167],"AVEC2013":[161],"AVEC2014":[163],"datasets":[164],"show":[165],"promising":[166],"capturing":[169],"consequential":[170],"long-sequence":[171],"demonstrate":[175],"outstanding":[176],"performance":[177],"over":[178],"state-of-the-art.":[180]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6}],"updated_date":"2026-08-12T21:12:35.861297","created_date":"2025-10-10T00:00:00"}