{"id":"https://openalex.org/W4408355164","doi":"https://doi.org/10.1109/icassp49660.2025.10889823","title":"Ultra-Low Latency Speech Enhancement -A Comprehensive Study","display_name":"Ultra-Low Latency Speech Enhancement -A Comprehensive Study","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408355164","doi":"https://doi.org/10.1109/icassp49660.2025.10889823"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889823","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/A5101474128","display_name":"Haibin Wu","orcid":"https://orcid.org/0000-0001-7166-5534"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Haibin Wu","raw_affiliation_strings":["National Taiwan University,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Taiwan University,WA,USA","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055277441","display_name":"Sebastian Braun","orcid":"https://orcid.org/0000-0001-9060-223X"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sebastian Braun","raw_affiliation_strings":["Microsoft,Redmond,WA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft,Redmond,WA,USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9896000027656555,"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/T13289","display_name":"Infant Health and Development","score":0.9623000025749207,"subfield":{"id":"https://openalex.org/subfields/3611","display_name":"Pharmacy"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6581469774246216},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6465122699737549},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.558285117149353},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4703790247440338},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46832185983657837},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18654891848564148},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.16464927792549133},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.15168103575706482},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10341987013816833}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6581469774246216},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6465122699737549},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.558285117149353},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4703790247440338},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46832185983657837},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18654891848564148},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.16464927792549133},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.15168103575706482},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10341987013816833}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889823","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":[{"id":"https://openalex.org/F4320307764","display_name":"Microsoft","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2044893557","https://openalex.org/W2062461584","https://openalex.org/W2139208951","https://openalex.org/W2149374737","https://openalex.org/W2952218014","https://openalex.org/W2962780374","https://openalex.org/W2974407961","https://openalex.org/W2991361823","https://openalex.org/W3015191643","https://openalex.org/W3016213974","https://openalex.org/W3160129476","https://openalex.org/W3163464523","https://openalex.org/W3174108421","https://openalex.org/W3197832224","https://openalex.org/W4224933825","https://openalex.org/W4226372244","https://openalex.org/W4311187069","https://openalex.org/W4313178358","https://openalex.org/W4391828783","https://openalex.org/W4392908343","https://openalex.org/W4394862910","https://openalex.org/W6629956514"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479","https://openalex.org/W3029351463","https://openalex.org/W4308600690"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1],"models":[2],"should":[3],"meet":[4],"very":[5],"low":[6],"latency":[7],"requirements":[8],"typically":[9],"smaller":[10],"than":[11],"5":[12],"ms":[13],"for":[14,135],"hearing":[15],"assistive":[16],"devices.":[17],"While":[18],"various":[19,88],"low-latency":[20,89],"techniques":[21,90],"have":[22,38],"been":[23],"proposed,":[24],"comparing":[25],"these":[26,83],"methods":[27,55],"in":[28,40,70],"a":[29],"controlled":[30],"setup":[31],"using":[32,91],"DNNs":[33],"remains":[34],"blank.":[35],"Previous":[36],"papers":[37],"variations":[39],"task,":[41],"training":[42,93],"data,":[43],"scripts,":[44],"and":[45,97,120],"evaluation":[46],"settings,":[47],"which":[48,73],"make":[49],"fair":[50],"comparison":[51],"impossible.":[52],"Moreover,":[53],"all":[54],"are":[56],"tested":[57],"on":[58,94,103],"small,":[59],"simulated":[60],"datasets,":[61],"making":[62],"it":[63],"difficult":[64],"to":[65],"fairly":[66],"assess":[67],"their":[68],"performance":[69],"real-world":[71,104],"conditions,":[72],"could":[74],"impact":[75],"the":[76,109,121,130,136],"reliability":[77],"of":[78,111],"scientific":[79],"findings.":[80],"To":[81],"address":[82],"issues,":[84],"we":[85,107,126],"comprehensively":[86],"investigate":[87],"consistent":[92],"large-scale":[95],"data":[96],"evaluate":[98],"with":[99],"more":[100],"relevant":[101],"metrics":[102],"data.":[105],"Specifically,":[106],"explore":[108],"effectiveness":[110],"asymmetric":[112],"windows,":[113,115],"learnable":[114],"adaptive":[116],"time":[117],"domain":[118],"filterbanks,":[119],"future-frame":[122],"prediction":[123],"technique.":[124],"Additionally,":[125],"examine":[127],"whether":[128],"increasing":[129],"model":[131],"size":[132],"can":[133],"compensate":[134],"reduced":[137],"window":[138],"size.":[139]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}