{"id":"https://openalex.org/W4408353719","doi":"https://doi.org/10.1109/icassp49660.2025.10889061","title":"Modulating State Space Model with SlowFast Framework for Compute-Efficient Ultra Low-Latency Speech Enhancement","display_name":"Modulating State Space Model with SlowFast Framework for Compute-Efficient Ultra Low-Latency Speech Enhancement","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408353719","doi":"https://doi.org/10.1109/icassp49660.2025.10889061"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889061","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/A5011611391","display_name":"Longbiao Cheng","orcid":"https://orcid.org/0000-0002-0635-1480"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Longbiao Cheng","raw_affiliation_strings":["Institute of Neuroinformatics, University of Zurich and ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neuroinformatics, University of Zurich and ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I202697423","https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050492887","display_name":"Ashutosh Pandey","orcid":"https://orcid.org/0000-0002-3352-7453"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ashutosh Pandey","raw_affiliation_strings":["Reality Labs Research, Meta,Redmond,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research, Meta,Redmond,United States","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040562171","display_name":"Buye Xu","orcid":"https://orcid.org/0000-0002-3027-7567"},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Buye Xu","raw_affiliation_strings":["Reality Labs Research, Meta,Redmond,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research, Meta,Redmond,United States","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051651857","display_name":"Tobi Delbr\u00fcck","orcid":"https://orcid.org/0000-0001-5479-1141"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Tobi Delbruck","raw_affiliation_strings":["Institute of Neuroinformatics, University of Zurich and ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neuroinformatics, University of Zurich and ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I202697423","https://openalex.org/I35440088"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108520440","display_name":"Vamsi Krishna Ithapu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210128585","display_name":"META Health","ror":"https://ror.org/035h67p10","country_code":"US","type":"other","lineage":["https://openalex.org/I4210128585"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vamsi Krishna Ithapu","raw_affiliation_strings":["Reality Labs Research, Meta,Redmond,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reality Labs Research, Meta,Redmond,United States","institution_ids":["https://openalex.org/I4210128585"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053821067","display_name":"Shih\u2010Chii Liu","orcid":"https://orcid.org/0000-0002-7557-045X"},"institutions":[{"id":"https://openalex.org/I12708293","display_name":"SIB Swiss Institute of Bioinformatics","ror":"https://ror.org/002n09z45","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I12708293"]},{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]},{"id":"https://openalex.org/I35440088","display_name":"ETH Zurich","ror":"https://ror.org/05a28rw58","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I35440088"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Shih-Chii Liu","raw_affiliation_strings":["Institute of Neuroinformatics, University of Zurich and ETH Zurich,Zurich,Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Neuroinformatics, University of Zurich and ETH Zurich,Zurich,Switzerland","institution_ids":["https://openalex.org/I12708293","https://openalex.org/I202697423","https://openalex.org/I35440088"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.3841,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.96508867,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"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/T10860","display_name":"Speech and Audio Processing","score":0.998199999332428,"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":0.998199999332428,"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":0.9945999979972839,"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/T13289","display_name":"Infant Health and Development","score":0.9509000182151794,"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":0.746936023235321},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6830326914787292},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6350778937339783},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5510361194610596},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4136110842227936},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.17523851990699768},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15871453285217285},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14983630180358887},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.09191939234733582}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.746936023235321},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6830326914787292},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6350778937339783},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5510361194610596},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4136110842227936},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.17523851990699768},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15871453285217285},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14983630180358887},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.09191939234733582}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889061","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889061","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":37,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W2038724679","https://openalex.org/W2092644348","https://openalex.org/W2094721231","https://openalex.org/W2141998673","https://openalex.org/W2516001803","https://openalex.org/W2760103357","https://openalex.org/W2892110446","https://openalex.org/W2892129657","https://openalex.org/W2929750792","https://openalex.org/W2962935966","https://openalex.org/W2963868408","https://openalex.org/W2990503944","https://openalex.org/W3015199127","https://openalex.org/W3015424358","https://openalex.org/W3134695619","https://openalex.org/W3174108421","https://openalex.org/W3187677606","https://openalex.org/W3196601925","https://openalex.org/W3198968036","https://openalex.org/W4213061196","https://openalex.org/W4229050860","https://openalex.org/W4232282348","https://openalex.org/W4292387427","https://openalex.org/W4308455602","https://openalex.org/W4311187069","https://openalex.org/W4385822774","https://openalex.org/W4392909774","https://openalex.org/W4402112230","https://openalex.org/W4402112446","https://openalex.org/W6629956514","https://openalex.org/W6732307519","https://openalex.org/W6744762798","https://openalex.org/W6803444062","https://openalex.org/W6851054131","https://openalex.org/W6892220874","https://openalex.org/W6929805505"],"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":{"Deep":[0],"learning-based":[1],"speech":[2],"enhancement":[3,42,144],"(SE)":[4],"methods":[5],"often":[6],"face":[7],"significant":[8],"computational":[9],"challenges":[10],"when":[11,40],"needing":[12],"to":[13,24,35,79,134],"meet":[14],"low-latency":[15,41],"requirements":[16],"because":[17],"of":[18,22,48,161,177,185,189],"the":[19,30,54,70,74,81,85,102,118,149],"increased":[20],"number":[21],"frames":[23],"be":[25],"processed.":[26],"This":[27],"paper":[28],"introduces":[29],"SlowFast":[31,150],"framework":[32,46],"which":[33],"aims":[34],"reduce":[36],"computation":[37,129,175],"costs":[38],"specifically":[39],"is":[43,98],"needed.":[44],"The":[45],"consists":[47],"a":[49,58,63,89,107,111,135,154,174,183],"slow":[50,103],"branch":[51,65,87],"that":[52,66,125,156],"analyzes":[53],"acoustic":[55],"environment":[56],"at":[57,73,168],"low":[59],"frame":[60,77],"rate,":[61],"and":[62,187],"fast":[64,86],"performs":[67],"SE":[68,108],"in":[69],"time":[71],"domain":[72],"needed":[75],"higher":[76],"rate":[78],"match":[80],"required":[82],"latency.":[83],"Specifically,":[84],"employs":[88],"state":[90,95],"space":[91],"model":[92],"where":[93],"its":[94],"transition":[96],"process":[97],"dynamically":[99],"modulated":[100],"by":[101,131,147],"branch.":[104],"Experiments":[105],"on":[106],"task":[109],"with":[110,139,173],"2":[112],"ms":[113],"algorithmic":[114,159],"latency":[115,160],"requirement":[116],"using":[117],"Voice":[119],"Bank":[120],"+":[121],"Demand":[122],"dataset":[123],"show":[124],"our":[126],"approach":[127],"reduces":[128],"cost":[130,176],"70%":[132],"compared":[133],"baseline":[136],"single-branch":[137],"network":[138,155],"equivalent":[140],"parameters,":[141],"without":[142],"compromising":[143],"performance.":[145],"Furthermore,":[146],"leveraging":[148],"framework,":[151],"we":[152],"implemented":[153],"achieves":[157],"an":[158],"just":[162],"62.5":[163],"\u03bcs":[164],"(one":[165],"sample":[166,171],"point":[167],"16":[169],"kHz":[170],"rate)":[172],"100":[178],"M":[179],"MACs/s,":[180],"while":[181],"scoring":[182],"PESQ-NB":[184],"3.12":[186],"SISNR":[188],"16.62.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}