{"id":"https://openalex.org/W7204913616","doi":"https://doi.org/10.1201/9788743815211-5","title":"Multichannel Speech Enhancement under Low-Latency Constraints: Balancing Quality and Computational Cost","display_name":"Multichannel Speech Enhancement under Low-Latency Constraints: Balancing Quality and Computational Cost","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7204913616","doi":"https://doi.org/10.1201/9788743815211-5"},"language":"en","primary_location":{"id":"doi:10.1201/9788743815211-5","doi":"https://doi.org/10.1201/9788743815211-5","is_oa":false,"landing_page_url":"https://doi.org/10.1201/9788743815211-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306463845","display_name":"River Publishers eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pervasive Intelligence \u2013 From Architectures to Sustainable Edge AI Systems-of-Systems","raw_type":"book-chapter"},"volume":{"id":"https://openalex.org/W7204912895","display_name":"Pervasive Intelligence \u2013 From Architectures to Sustainable Edge AI Systems-of-Systems"},"type":"book-chapter","is_traditional":true,"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/A5140448311","display_name":"Zahra Benslimane","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zahra Benslimane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5140413624","display_name":"Fabrice Auzanneau","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabrice Auzanneau","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060479495","display_name":"Martyna Por\u00eaba","orcid":"https://orcid.org/0000-0002-5102-7735","observed_orcids":["https://orcid.org/0000-0002-5102-7735"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Martyna Poreba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124040813","display_name":"Michal Szczepanski","orcid":"https://orcid.org/0009-0000-9061-4396","observed_orcids":["https://orcid.org/0009-0000-9061-4396"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michal Szczepanski","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014233098","display_name":"Fabian Chersi","orcid":"https://orcid.org/0000-0003-1257-2607","observed_orcids":["https://orcid.org/0000-0003-1257-2607"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fabian Chersi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5064988262","display_name":"Romain Serizel","orcid":"https://orcid.org/0000-0002-6848-0114","observed_orcids":["https://orcid.org/0000-0002-6848-0114"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Romain Serizel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.74120083,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"81","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"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":1.0,"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":0.0,"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/T11309","display_name":"Music and Audio Processing","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multichannel-speech-enhancement","display_name":"multichannel speech enhancement","score":0.9990000128746033},{"id":"https://openalex.org/keywords/real-time-speech-enhancement","display_name":"real-time speech enhancement","score":0.7960000038146973},{"id":"https://openalex.org/keywords/embedded-systems","display_name":"embedded systems","score":0.5450000166893005},{"id":"https://openalex.org/keywords/tango","display_name":"tango","score":0.8610000014305115},{"id":"https://openalex.org/keywords/computational-complexity","display_name":"computational complexity","score":0.722000002861023},{"id":"https://openalex.org/keywords/noise-robustness","display_name":"noise robustness","score":0.5580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6661999821662903},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6011000275611877},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5406000018119812},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4388999938964844},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.311599999666214},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.30219998955726624},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.26820001006126404},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2549000084400177},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1201/9788743815211-5","doi":"https://doi.org/10.1201/9788743815211-5","is_oa":false,"landing_page_url":"https://doi.org/10.1201/9788743815211-5","pdf_url":null,"source":{"id":"https://openalex.org/S4306463845","display_name":"River Publishers eBooks","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"ebook platform"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Pervasive Intelligence \u2013 From Architectures to Sustainable Edge AI Systems-of-Systems","raw_type":"book-chapter"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4392903047","https://openalex.org/W4408354537","https://openalex.org/W4318200307","https://openalex.org/W4417073314","https://openalex.org/W4392902607","https://openalex.org/W7155078129","https://openalex.org/W4408353719","https://openalex.org/W3015278429","https://openalex.org/W2899693363","https://openalex.org/W7165953790"],"abstract_inverted_index":{"Multichannel":[0],"speech":[1,7],"enhancement":[2,89],"is":[3,112,137],"essential":[4],"for":[5,69,170],"robust":[6,129],"intelligibility":[8],"in":[9,20],"noisy":[10],"environments.":[11],"Although":[12],"many":[13],"algorithms":[14],"address":[15],"this":[16],"challenge,":[17],"their":[18,95],"deployment":[19],"real-time":[21,172],"or":[22],"embedded":[23],"settings":[24],"imposes":[25],"strict":[26],"computational":[27,96,155],"and":[28,49,82,94,143],"latency":[29,102,133,168],"constraints.":[30],"This":[31],"work":[32],"compares":[33],"three":[34],"representative":[35],"methods:":[36],"FaSNet-TAC,":[37],"an":[38],"end-to-end":[39],"neural":[40,43],"network-based":[41],"approach;":[42],"MVDR,":[44],"a":[45,51,60,77,108],"hybrid":[46],"time-frequency":[47],"method;":[48],"Tango,":[50],"fully":[52],"distributed":[53],"framework.":[54],"For":[55],"our":[56],"evaluation,":[57],"we":[58,86],"employ":[59],"methodology":[61],"that":[62,107,149],"explicitly":[63],"separates":[64],"the":[65,73,88,127,138,153,158,166],"input":[66],"context":[67,111,142],"needed":[68],"optimal":[70],"performance":[71],"from":[72],"output":[74],"latency.":[75],"Using":[76],"common":[78],"noisy-speech":[79],"test":[80],"set":[81],"identical":[83],"evaluation":[84],"protocols,":[85],"assess":[87],"quality":[90],"of":[91,160],"these":[92],"methods":[93],"complexity":[97],"under":[98,131],"various":[99],"target":[100],"algorithmic":[101],"requirements.":[103],"Our":[104],"analysis":[105],"shows":[106],"one":[109],"second":[110],"sufficient":[113],"to":[114,141],"approach":[115],"full-utterance":[116],"performance.":[117],"It":[118],"also":[119,147],"highlights":[120],"distinct":[121],"trade-offs":[122],"across":[123],"architectures:":[124],"Tango":[125],"exhibits":[126],"most":[128,139],"behaviour":[130],"stringent":[132],"constraints,":[134],"whereas":[135],"FaSNet-TAC":[136],"sensitive":[140],"hop-size":[144],"reduction.":[145],"We":[146],"find":[148],"mask-estimation":[150],"stages":[151],"constitute":[152],"dominant":[154],"bottleneck,":[156],"underscoring":[157],"importance":[159],"82":[161],"aligning":[162],"model":[163],"design":[164],"with":[165],"intended":[167],"regime":[169],"practical":[171],"deployment.":[173]},"counts_by_year":[],"updated_date":"2026-10-12T09:40:04.860316","created_date":"2026-09-02T00:00:00"}