{"id":"https://openalex.org/W3015844538","doi":"https://doi.org/10.1109/icassp40776.2020.9054230","title":"Fully Convolutional Recurrent Networks for Speech Enhancement","display_name":"Fully Convolutional Recurrent Networks for Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015844538","doi":"https://doi.org/10.1109/icassp40776.2020.9054230","mag":"3015844538"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9054230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054230","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/A5074981761","display_name":"Maximilian Strake","orcid":null},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Maximilian Strake","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, 38106, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034770088","display_name":"Bruno Defraene","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134434","display_name":"NXP (Belgium)","ror":"https://ror.org/031v4g827","country_code":"BE","type":"company","lineage":["https://openalex.org/I109147379","https://openalex.org/I4210134434"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bruno Defraene","raw_affiliation_strings":["NXP Semiconductors, Product Line Voice and Audio Solutions, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"NXP Semiconductors, Product Line Voice and Audio Solutions, Leuven, Belgium","institution_ids":["https://openalex.org/I4210134434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075598267","display_name":"Kristoff Fluyt","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134434","display_name":"NXP (Belgium)","ror":"https://ror.org/031v4g827","country_code":"BE","type":"company","lineage":["https://openalex.org/I109147379","https://openalex.org/I4210134434"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Kristoff Fluyt","raw_affiliation_strings":["NXP Semiconductors, Product Line Voice and Audio Solutions, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"NXP Semiconductors, Product Line Voice and Audio Solutions, Leuven, Belgium","institution_ids":["https://openalex.org/I4210134434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018190338","display_name":"Wouter Tirry","orcid":null},"institutions":[{"id":"https://openalex.org/I4210134434","display_name":"NXP (Belgium)","ror":"https://ror.org/031v4g827","country_code":"BE","type":"company","lineage":["https://openalex.org/I109147379","https://openalex.org/I4210134434"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Wouter Tirry","raw_affiliation_strings":["NXP Semiconductors, Product Line Voice and Audio Solutions, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"NXP Semiconductors, Product Line Voice and Audio Solutions, Leuven, Belgium","institution_ids":["https://openalex.org/I4210134434"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002593702","display_name":"Tim Fingscheidt","orcid":"https://orcid.org/0000-0002-8895-5041"},"institutions":[{"id":"https://openalex.org/I94509681","display_name":"Technische Universit\u00e4t Braunschweig","ror":"https://ror.org/010nsgg66","country_code":"DE","type":"education","lineage":["https://openalex.org/I94509681"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tim Fingscheidt","raw_affiliation_strings":["Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, 38106, Germany"],"affiliations":[{"raw_affiliation_string":"Institute for Communications Technology, Technische Universit\u00e4t Braunschweig, 38106, Germany","institution_ids":["https://openalex.org/I94509681"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5074981761"],"corresponding_institution_ids":["https://openalex.org/I94509681"],"apc_list":null,"apc_paid":null,"fwci":5.4552,"has_fulltext":false,"cited_by_count":48,"citation_normalized_percentile":{"value":0.9678736,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6674","last_page":"6678"},"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":0.9993000030517578,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.8276153206825256},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.6823534369468689},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6131494641304016},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6061902046203613},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5777955055236816},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.5698021650314331},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5664509534835815},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5659496784210205},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4807265102863312},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.4732307195663452},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47016996145248413},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4559193253517151},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.441104918718338},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23994556069374084},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.22684231400489807},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.17348012328147888},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.06850779056549072}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8276153206825256},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.6823534369468689},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6131494641304016},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6061902046203613},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5777955055236816},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.5698021650314331},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5664509534835815},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5659496784210205},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4807265102863312},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.4732307195663452},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47016996145248413},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4559193253517151},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.441104918718338},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23994556069374084},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.22684231400489807},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.17348012328147888},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.06850779056549072},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp40776.2020.9054230","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9054230","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":[{"score":0.41999998688697815,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1485009520","https://openalex.org/W1495679096","https://openalex.org/W1506438021","https://openalex.org/W1522301498","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2151484683","https://openalex.org/W2774389566","https://openalex.org/W2809824582","https://openalex.org/W2889442120","https://openalex.org/W2900004752","https://openalex.org/W2940275453","https://openalex.org/W2962843322","https://openalex.org/W2963453742","https://openalex.org/W2963751183","https://openalex.org/W2964121744","https://openalex.org/W2967086982","https://openalex.org/W2997901485","https://openalex.org/W2998155746","https://openalex.org/W4245919820","https://openalex.org/W6628877408","https://openalex.org/W6631190155","https://openalex.org/W6746567100","https://openalex.org/W6748795944","https://openalex.org/W6766766128"],"related_works":["https://openalex.org/W2058482658","https://openalex.org/W3016109656","https://openalex.org/W1973895194","https://openalex.org/W2546593254","https://openalex.org/W3135613579","https://openalex.org/W2166831097","https://openalex.org/W4386746628","https://openalex.org/W4388016426","https://openalex.org/W1980687383","https://openalex.org/W3209446892"],"abstract_inverted_index":{"Convolutional":[0],"recurrent":[1,119],"neural":[2],"networks":[3],"(CRNs)":[4],"using":[5,156],"convolutional":[6,32,57,108,118],"encoder-decoder":[7],"(CED)":[8],"structures":[9],"have":[10],"shown":[11],"promising":[12],"performance":[13],"for":[14,63],"single-channel":[15],"speech":[16],"enhancement.":[17],"These":[18],"CRNs":[19,68],"handle":[20,152],"temporal":[21],"modeling":[22],"through":[23,85],"integrating":[24],"long":[25],"short-term":[26],"memory":[27],"(LSTM)":[28],"layers":[29],"in":[30,37,46,177],"between":[31],"encoder":[33],"and":[34,49,111,182],"decoder.":[35],"However,":[36],"such":[38],"a":[39,90,107,116],"CRN,":[40],"the":[41,50,56,74,79,82,103,113,124,127,144],"organization":[42,129],"of":[43,55,81,93,130,147,174,179],"internal":[44],"representations":[45],"feature":[47,75,133],"maps":[48],"focus":[51],"on":[52],"local":[53],"structure":[54,146],"mappings":[58],"has":[59],"to":[60,101,141,151],"be":[61,70],"discarded":[62],"fully-connected":[64,87,104],"LSTM":[65,105,109],"processing.":[66],"Furthermore,":[67],"can":[69,136],"quite":[71],"restricted":[72],"concerning":[73],"space":[76],"dimension":[77],"at":[78],"input":[80,132,154],"LSTM,":[83],"which,":[84],"its":[86,131],"nature,":[88],"requires":[89],"large":[91],"amount":[92],"trainable":[94,158,175],"parameters.":[95],"As":[96],"first":[97],"novelty,":[98],"we":[99,135],"propose":[100],"replace":[102],"by":[106],"(ConvLSTM)":[110],"call":[112],"resulting":[114],"network":[115,120],"fully":[117],"(FCRN).":[121],"Secondly,":[122],"since":[123],"ConvLSTM":[125],"retains":[126],"structured":[128],"maps,":[134],"show":[137],"that":[138],"this":[139],"helps":[140],"internally":[142],"represent":[143],"harmonic":[145],"speech,":[148],"allowing":[149],"us":[150],"high-dimensional":[153],"features":[155],"less":[157],"parameters":[159,176],"than":[160],"an":[161],"LSTM.":[162],"The":[163],"proposed":[164],"FCRN":[165],"clearly":[166],"outperforms":[167],"CRN":[168],"reference":[169],"models":[170],"with":[171],"similar":[172],"amounts":[173],"terms":[178],"PESQ,":[180],"STOI,":[181],"segmental":[183],"\u0394SNR.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":9},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}