{"id":"https://openalex.org/W4311187069","doi":"https://doi.org/10.1109/taslp.2022.3224285","title":"STFT-Domain Neural Speech Enhancement With Very Low Algorithmic Latency","display_name":"STFT-Domain Neural Speech Enhancement With Very Low Algorithmic Latency","publication_year":2022,"publication_date":"2022-11-24","ids":{"openalex":"https://openalex.org/W4311187069","doi":"https://doi.org/10.1109/taslp.2022.3224285"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3224285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3224285","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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":false,"raw_author_name":"Zhong-Qiu Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4204-9430","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086940921","display_name":"Gordon Wichern","orcid":"https://orcid.org/0000-0002-8597-6795"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gordon Wichern","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8597-6795","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","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":["Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076453358","display_name":"Jonathan Le Roux","orcid":"https://orcid.org/0000-0002-3451-171X"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jonathan Le Roux","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-3451-171X","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.5307,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.95966135,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"31","issue":null,"first_page":"397","last_page":"410"},"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9957000017166138,"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"}},{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/short-time-fourier-transform","display_name":"Short-time Fourier transform","score":0.859747588634491},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7999274730682373},{"id":"https://openalex.org/keywords/window-function","display_name":"Window function","score":0.5602449178695679},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5413017868995667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.521994948387146},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5219559073448181},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.5122813582420349},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.49417832493782043},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.4427456855773926},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.43916428089141846},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.41849035024642944},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38711386919021606},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3363340497016907},{"id":"https://openalex.org/keywords/spectral-density","display_name":"Spectral density","score":0.14956700801849365},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.12671750783920288},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.12444528937339783},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09913480281829834},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08335617184638977},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.07855147123336792}],"concepts":[{"id":"https://openalex.org/C166386157","wikidata":"https://www.wikidata.org/wiki/Q1477735","display_name":"Short-time Fourier transform","level":4,"score":0.859747588634491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999274730682373},{"id":"https://openalex.org/C140101238","wikidata":"https://www.wikidata.org/wiki/Q1404885","display_name":"Window function","level":3,"score":0.5602449178695679},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5413017868995667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.521994948387146},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5219559073448181},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.5122813582420349},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.49417832493782043},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.4427456855773926},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.43916428089141846},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.41849035024642944},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38711386919021606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3363340497016907},{"id":"https://openalex.org/C168110828","wikidata":"https://www.wikidata.org/wiki/Q1331626","display_name":"Spectral density","level":2,"score":0.14956700801849365},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.12671750783920288},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.12444528937339783},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09913480281829834},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08335617184638977},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.07855147123336792},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3224285","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3224285","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":63,"referenced_works":["https://openalex.org/W25870538","https://openalex.org/W1502398685","https://openalex.org/W1901129140","https://openalex.org/W1973669708","https://openalex.org/W2037951967","https://openalex.org/W2044893557","https://openalex.org/W2111460811","https://openalex.org/W2120847449","https://openalex.org/W2141998673","https://openalex.org/W2168379380","https://openalex.org/W2291877678","https://openalex.org/W2478884216","https://openalex.org/W2519091744","https://openalex.org/W2568308529","https://openalex.org/W2593116425","https://openalex.org/W2763188033","https://openalex.org/W2889885720","https://openalex.org/W2890553422","https://openalex.org/W2894785362","https://openalex.org/W2929750792","https://openalex.org/W2952218014","https://openalex.org/W2962866211","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963902628","https://openalex.org/W2964058413","https://openalex.org/W2981976899","https://openalex.org/W2991361823","https://openalex.org/W3002439978","https://openalex.org/W3007256793","https://openalex.org/W3015197852","https://openalex.org/W3015199127","https://openalex.org/W3015279216","https://openalex.org/W3015679215","https://openalex.org/W3015788098","https://openalex.org/W3015843733","https://openalex.org/W3016094953","https://openalex.org/W3032514799","https://openalex.org/W3086154751","https://openalex.org/W3096408984","https://openalex.org/W3099330747","https://openalex.org/W3110852964","https://openalex.org/W3151596526","https://openalex.org/W3161140524","https://openalex.org/W3161934504","https://openalex.org/W3162539493","https://openalex.org/W3163652268","https://openalex.org/W3163816345","https://openalex.org/W3165227983","https://openalex.org/W3171278394","https://openalex.org/W3174108421","https://openalex.org/W3201698955","https://openalex.org/W3203119473","https://openalex.org/W3209490467","https://openalex.org/W3215005424","https://openalex.org/W4205689591","https://openalex.org/W4224933825","https://openalex.org/W4297841846","https://openalex.org/W4307199125","https://openalex.org/W6629956514","https://openalex.org/W6639824700","https://openalex.org/W6772622344","https://openalex.org/W6802205285"],"related_works":["https://openalex.org/W4205152111","https://openalex.org/W2393357744","https://openalex.org/W4221076379","https://openalex.org/W2900815132","https://openalex.org/W2100209102","https://openalex.org/W1965222729","https://openalex.org/W2139920761","https://openalex.org/W4327650142","https://openalex.org/W2358528705","https://openalex.org/W3112721282"],"abstract_inverted_index":{"Deep":[0],"learning":[1,99],"based":[2,100],"speech":[3,102,135,205],"enhancement":[4,206,223],"in":[5,44,53],"the":[6,49,54,62,127,137,145,153,199,208,211],"short-time":[7],"Fourier":[8],"transform":[9],"(STFT)":[10],"domain":[11],"typically":[12],"uses":[13],"a":[14,73,78,88,118,163,192,226],"large":[15],"window":[16,24,64,81,91],"length":[17],"such":[18],"as":[19,159,244,246],"32":[20,42],"ms.":[21,248],"A":[22],"larger":[23],"can":[25,173,220],"lead":[26],"to":[27,125,149,166,183,196],"higher":[28],"frequency":[29],"resolution":[30],"and":[31,129,180],"potentially":[32],"better":[33,222],"enhancement.":[34,103],"This":[35],"however":[36],"incurs":[37],"an":[38,45,241],"algorithmic":[39,187,200,242],"latency":[40,243],"of":[41,133,155,210,229],"ms":[43],"online":[46],"setup,":[47],"because":[48],"overlap-add":[50],"algorithm":[51],"used":[52,84,93,158],"inverse":[55],"STFT":[56,86],"(iSTFT)":[57],"is":[58,83,92,123,181],"also":[59],"performed":[60],"using":[61],"same":[63],"size.":[65],"To":[66],"reduce":[67,198],"this":[68,106],"inherent":[69],"latency,":[70],"we":[71,109,143,190],"adapt":[72],"conventional":[74],"dual-window-size":[75],"approach,":[76],"where":[77,117],"regular":[79],"input":[80],"size":[82],"for":[85,94,96,114,162,225],"but":[87],"shorter":[89],"output":[90],"overlap-add,":[95],"STFT-domain":[97,218],"deep":[98,119],"frame-online":[101,115,151,168],"Based":[104],"on":[105,203],"STFT-iSTFT":[107],"configuration,":[108],"employ":[110],"complex":[111],"spectral":[112],"mapping":[113],"enhancement,":[116],"neural":[120],"network":[121],"(DNN)":[122],"trained":[124],"predict":[126],"real":[128],"imaginary":[130],"(RI)":[131],"components":[132,148],"target":[134],"from":[136],"mixture":[138],"RI":[139,147],"components.":[140],"In":[141],"addition,":[142],"use":[144],"DNN-predicted":[146],"conduct":[150],"beamforming,":[152],"results":[154],"which":[156],"are":[157],"extra":[160],"features":[161],"second":[164],"DNN":[165],"perform":[167],"postfiltering.":[169],"The":[170],"frequency-domain":[171],"beamformer":[172],"be":[174],"easily":[175],"integrated":[176],"with":[177,215,234],"our":[178,217],"DNNs":[179],"designed":[182],"not":[184],"incur":[185],"any":[186],"latency.":[188,201],"Additionally,":[189],"propose":[191],"future-frame":[193],"prediction":[194],"technique":[195],"further":[197],"Evaluation":[202],"noisy-reverberant":[204],"shows":[207],"effectiveness":[209],"proposed":[212],"algorithms.":[213],"Compared":[214],"Conv-TasNet,":[216],"system":[219],"achieve":[221],"performance":[224,233,239],"comparable":[227,232],"amount":[228],"computation,":[230,236],"or":[231],"less":[235],"maintaining":[237],"strong":[238],"at":[240],"low":[245],"2":[247]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":18},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":12}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}