{"id":"https://openalex.org/W3015278429","doi":"https://doi.org/10.1109/icassp40776.2020.9054563","title":"Low-Latency Single Channel Speech Enhancement Using U-Net Convolutional Neural Networks","display_name":"Low-Latency Single Channel Speech Enhancement Using U-Net Convolutional Neural Networks","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015278429","doi":"https://doi.org/10.1109/icassp40776.2020.9054563","mag":"3015278429"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 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/A5072597547","display_name":"Ahmet Bulut","orcid":"https://orcid.org/0000-0002-9435-287X"},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ahmet E. Bulut","raw_affiliation_strings":["Center for Robust Speech Systems, University of Texas at Dallas, TX"],"affiliations":[{"raw_affiliation_string":"Center for Robust Speech Systems, University of Texas at Dallas, TX","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084879161","display_name":"Kazuhito Koishida","orcid":"https://orcid.org/0000-0002-3111-5375"},"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":"Kazuhito Koishida","raw_affiliation_strings":["Microsoft Corporation, One Microsoft Way, Redmond, WA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, One Microsoft Way, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5072597547"],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":2.7276,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.90908492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6214","last_page":"6218"},"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":0.9977999925613403,"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":0.9933000206947327,"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/pesq","display_name":"PESQ","score":0.9671004414558411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7809684872627258},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7231865525245667},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6901482939720154},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6183601021766663},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5967239141464233},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4192691743373871},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4179840385913849},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.41370153427124023},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3084733486175537},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30452704429626465},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.11465275287628174},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.10241875052452087}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9671004414558411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809684872627258},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7231865525245667},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6901482939720154},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6183601021766663},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5967239141464233},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4192691743373871},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4179840385913849},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.41370153427124023},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3084733486175537},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30452704429626465},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.11465275287628174},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.10241875052452087},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054563","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054563","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1510355813","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W1901129140","https://openalex.org/W1983108229","https://openalex.org/W2044893557","https://openalex.org/W2048142341","https://openalex.org/W2070126272","https://openalex.org/W2078528584","https://openalex.org/W2094461119","https://openalex.org/W2094721231","https://openalex.org/W2099471712","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2141411743","https://openalex.org/W2141998673","https://openalex.org/W2168379380","https://openalex.org/W2291877678","https://openalex.org/W2322799359","https://openalex.org/W2405774341","https://openalex.org/W2407127962","https://openalex.org/W2476548250","https://openalex.org/W2603567530","https://openalex.org/W2711335087","https://openalex.org/W2746457594","https://openalex.org/W2757519008","https://openalex.org/W2802304149","https://openalex.org/W2889442120","https://openalex.org/W2892356933","https://openalex.org/W2902132730","https://openalex.org/W2905649134","https://openalex.org/W2929274168","https://openalex.org/W2940177920","https://openalex.org/W2962879692","https://openalex.org/W2963073614","https://openalex.org/W2963341071","https://openalex.org/W2963453742","https://openalex.org/W2964121744","https://openalex.org/W2972481755","https://openalex.org/W3147539069","https://openalex.org/W4253928870","https://openalex.org/W4289242435","https://openalex.org/W4295521014","https://openalex.org/W4320013936","https://openalex.org/W6631190155","https://openalex.org/W6639824700","https://openalex.org/W6684924409","https://openalex.org/W6713658392","https://openalex.org/W6729966448","https://openalex.org/W6735913928","https://openalex.org/W6751445809","https://openalex.org/W6756251360","https://openalex.org/W6757668070"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W1823208675","https://openalex.org/W2342810974","https://openalex.org/W3016109656","https://openalex.org/W2513767140","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2037635165","https://openalex.org/W4200562864"],"abstract_inverted_index":{"Single-channel":[0],"speech":[1,18,104],"enhancement":[2],"(SE)":[3],"can":[4],"be":[5],"described,":[6],"in":[7,98,115],"its":[8],"simplest":[9],"terms,":[10],"as":[11],"learning":[12],"a":[13,28,42],"transformation":[14],"from":[15],"single-channel":[16],"noisy":[17],"to":[19,56,69,141],"the":[20,86,93,96,120,131,146,154],"clean":[21],"speech.":[22],"To":[23,51],"do":[24],"this,":[25],"we":[26,54],"propose":[27],"simple":[29],"but":[30],"effective":[31],"U-Net":[32],"convolutional":[33],"neural":[34],"network":[35],"(CNN)":[36],"based":[37],"architecture":[38],"with":[39,41],"skip-connections":[40],"focus":[43],"on":[44,67,82,88],"real-time":[45],"applications":[46],"which":[47],"require":[48],"low-latency":[49],"processing.":[50],"that":[52,114],"end,":[53],"choose":[55],"process":[57],"relatively":[58],"small":[59],"temporal":[60],"windows":[61],"and":[62,85,126,135,150],"apply":[63],"time-frequency":[64],"(T-F)":[65],"featurization":[66],"it":[68],"achieve":[70],"magnitude":[71],"estimation.":[72],"Two":[73],"state-of-the-art":[74],"systems":[75,97,133],"are":[76],"picked":[77],"for":[78],"bench-marking:":[79],"One":[80],"operating":[81],"spectral-domain":[83],"[1]":[84],"other":[87],"temporal-domain":[89],"[2].":[90],"We":[91,143],"evaluate":[92],"performance":[94,149],"of":[95,100,103,117,153],"terms":[99,116],"perceptual":[101],"evaluation":[102],"quality":[105],"(PESQ),":[106],"short-time":[107],"objective":[108],"intelligibility":[109],"(STOI).":[110],"Experimental":[111],"results":[112],"show":[113],"PESQ":[118],"measure":[119],"proposed":[121,155],"method":[122],"provides":[123],"around":[124],"27%":[125],"11%":[127],"relative":[128],"improvement":[129],"over":[130],"baseline":[132],"respectively":[134],"has":[136],"significantly":[137],"lower":[138],"latency":[139,152],"compared":[140],"them.":[142],"further":[144],"investigate":[145],"trade-off":[147],"between":[148],"overall":[151],"system.":[156]},"counts_by_year":[{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}