{"id":"https://openalex.org/W4372189495","doi":"https://doi.org/10.1109/icassp49357.2023.10095700","title":"FNeural Speech Enhancement with Very Low Algorithmic Latency and Complexity via Integrated full- and sub-band Modeling","display_name":"FNeural Speech Enhancement with Very Low Algorithmic Latency and Complexity via Integrated full- and sub-band Modeling","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372189495","doi":"https://doi.org/10.1109/icassp49357.2023.10095700"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 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/A5101607498","display_name":"Zhong-Qiu Wang","orcid":"https://orcid.org/0000-0002-4204-9430"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047682990","display_name":"Samuele Cornell","orcid":"https://orcid.org/0000-0002-5358-1844"},"institutions":[{"id":"https://openalex.org/I122534668","display_name":"Marche Polytechnic University","ror":"https://ror.org/00x69rs40","country_code":"IT","type":"education","lineage":["https://openalex.org/I122534668"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Samuele Cornell","raw_affiliation_strings":["Università Politecnica Delle Marche,Italy"],"affiliations":[{"raw_affiliation_string":"Università Politecnica Delle Marche,Italy","institution_ids":["https://openalex.org/I122534668"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079440375","display_name":"Shukjae Choi","orcid":null},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Shukjae Choi","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc.,Seoul,Korea","Hyundai Motor Group and 42dot Inc., Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I197312522"]},{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017337548","display_name":"Younglo Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Younglo Lee","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc.,Seoul,Korea","Hyundai Motor Group and 42dot Inc., Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I197312522"]},{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053784244","display_name":"Byeong-Yeol Kim","orcid":"https://orcid.org/0000-0001-6019-5047"},"institutions":[{"id":"https://openalex.org/I197312522","display_name":"Hyundai Motor Group (South Korea)","ror":"https://ror.org/05kxbz959","country_code":"KR","type":"company","lineage":["https://openalex.org/I197312522"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Byeong-Yeol Kim","raw_affiliation_strings":["Hyundai Motor Group and 42dot Inc.,Seoul,Korea","Hyundai Motor Group and 42dot Inc., Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc.,Seoul,Korea","institution_ids":["https://openalex.org/I197312522"]},{"raw_affiliation_string":"Hyundai Motor Group and 42dot Inc., Seoul, Korea","institution_ids":["https://openalex.org/I197312522"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,USA","institution_ids":["https://openalex.org/I74973139"]},{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101607498"],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":2.0377,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.87323944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"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/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":0.9976999759674072,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7982780337333679},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6221237778663635},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.5867714285850525},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5809430480003357},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5621063113212585},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5160786509513855},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5151904821395874},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5023527145385742},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4271166920661926},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3699697256088257},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.35698437690734863},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3334415555000305},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11354497075080872}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7982780337333679},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6221237778663635},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.5867714285850525},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5809430480003357},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5621063113212585},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5160786509513855},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5151904821395874},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5023527145385742},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4271166920661926},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3699697256088257},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.35698437690734863},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3334415555000305},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11354497075080872},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095700","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49357.2023.10095700","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7599999904632568,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2221409856","https://openalex.org/W2734774145","https://openalex.org/W2889442120","https://openalex.org/W2892163332","https://openalex.org/W2952218014","https://openalex.org/W2962843322","https://openalex.org/W2962866211","https://openalex.org/W2972460025","https://openalex.org/W2991361823","https://openalex.org/W3007256793","https://openalex.org/W3015199127","https://openalex.org/W3015679215","https://openalex.org/W3016094953","https://openalex.org/W3016120385","https://openalex.org/W3016912202","https://openalex.org/W3032514799","https://openalex.org/W3041647828","https://openalex.org/W3042857426","https://openalex.org/W3094607766","https://openalex.org/W3095248373","https://openalex.org/W3096408984","https://openalex.org/W3097034112","https://openalex.org/W3097906045","https://openalex.org/W3099330747","https://openalex.org/W3134695619","https://openalex.org/W3160129476","https://openalex.org/W3163652268","https://openalex.org/W3165776651","https://openalex.org/W3171278394","https://openalex.org/W3203119473","https://openalex.org/W3206706278","https://openalex.org/W3215005424","https://openalex.org/W4205689591","https://openalex.org/W4210402803","https://openalex.org/W4224917453","https://openalex.org/W4224931234","https://openalex.org/W4224936432","https://openalex.org/W4226185896","https://openalex.org/W4283329643","https://openalex.org/W4311187069","https://openalex.org/W4372271367","https://openalex.org/W4385756463","https://openalex.org/W6748894610","https://openalex.org/W6802205285","https://openalex.org/W6803190657","https://openalex.org/W6839002775"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","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":{"We":[0],"propose":[1],"FSB-LSTM,":[2],"a":[3,52,63,79,98,107,111,116,126,131],"novel":[4],"long":[5],"short-term":[6],"memory":[7],"(LSTM)":[8],"based":[9],"architecture":[10],"that":[11],"integrates":[12],"full-":[13],"and":[14,20,62,84,115],"sub-band":[15,64],"(FSB)":[16],"modeling,":[17],"for":[18],"single-":[19],"multi-channel":[21],"speech":[22,133],"enhancement":[23,128,134],"in":[24],"the":[25,75,94,122,138],"short-time":[26],"Fourier":[27],"transform":[28],"(STFT)":[29],"domain.":[30],"The":[31,101],"model":[32,56,67,102],"maintains":[33],"an":[34,39,86],"information":[35],"highway":[36],"to":[37,55,66,90,93,105],"flow":[38],"over-complete":[40],"input":[41,83,96],"representation":[42,81,89],"through":[43],"multiple":[44],"FSB-LSTM":[45,48],"modules.":[46],"Each":[47],"module":[49],"consists":[50],"of":[51,74],"full-band":[53],"block":[54,65,95],"spectro-temporal":[57],"patterns":[58,68],"at":[59,121],"all":[60],"frequencies":[61],"within":[69],"each":[70,73],"sub-band,":[71],"where":[72],"two":[76],"blocks":[77],"takes":[78],"down-sampled":[80],"as":[82,142,144],"returns":[85],"up-sampled":[87],"discriminative":[88],"be":[91],"added":[92],"via":[97],"residual":[99],"connection.":[100],"is":[103,141],"designed":[104],"have":[106],"low":[108,118,143],"algorithmic":[109,119],"complexity,":[110],"small":[112],"run-time":[113],"buffer":[114],"very":[117],"latency,":[120],"same":[123],"time":[124],"producing":[125],"strong":[127],"performance":[129],"on":[130],"noisy-reverberant":[132],"task":[135],"even":[136],"if":[137],"hop":[139],"size":[140],"2":[145],"ms.":[146]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}