{"id":"https://openalex.org/W2899693363","doi":"https://doi.org/10.1109/iwaenc.2018.8521400","title":"Time-Frequency Masking Strategies for Single-Channel Low-Latency Speech Enhancement Using Neural Networks","display_name":"Time-Frequency Masking Strategies for Single-Channel Low-Latency Speech Enhancement Using Neural Networks","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2899693363","doi":"https://doi.org/10.1109/iwaenc.2018.8521400","mag":"2899693363"},"language":"en","primary_location":{"id":"doi:10.1109/iwaenc.2018.8521400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","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/A5058140225","display_name":"Mikko Parviainen","orcid":"https://orcid.org/0000-0003-2128-8173"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Mikko Parviainen","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology, Tampere, FINLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology, Tampere, FINLAND","institution_ids":["https://openalex.org/I4210121626","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075555953","display_name":"Pasi Pertil\u00e4","orcid":"https://orcid.org/0000-0003-1413-6091"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Pasi Pertila","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology, Tampere, FINLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology, Tampere, FINLAND","institution_ids":["https://openalex.org/I4210121626","https://openalex.org/I4210133110"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049691461","display_name":"Tuomas Virtanen","orcid":"https://orcid.org/0000-0002-4604-9729"},"institutions":[{"id":"https://openalex.org/I4210121626","display_name":"Signal Processing (United States)","ror":"https://ror.org/021gzyw51","country_code":"US","type":"company","lineage":["https://openalex.org/I4210121626"]},{"id":"https://openalex.org/I4210133110","display_name":"Tampere University","ror":null,"country_code":"FI","type":null,"lineage":["https://openalex.org/I4210133110"]}],"countries":["FI","US"],"is_corresponding":false,"raw_author_name":"Tuomas Virtanen","raw_affiliation_strings":["Laboratory of Signal Processing, Tampere University of Technology, Tampere, FINLAND"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Laboratory of Signal Processing, Tampere University of Technology, Tampere, FINLAND","institution_ids":["https://openalex.org/I4210121626","https://openalex.org/I4210133110"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078194825","display_name":"Peter Grosche","orcid":"https://orcid.org/0000-0002-5525-5233"},"institutions":[{"id":"https://openalex.org/I4210166625","display_name":"Huawei German Research Center","ror":"https://ror.org/00z59w514","country_code":"DE","type":"facility","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210129353","https://openalex.org/I4210166625"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Peter Grosche","raw_affiliation_strings":["Huawei European Research Center, Munich, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei European Research Center, Munich, Germany","institution_ids":["https://openalex.org/I4210166625"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3325,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58065567,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"abs 1412 6980","issue":null,"first_page":"51","last_page":"55"},"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":0.9991000294685364,"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":0.9966999888420105,"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/masking","display_name":"Masking (illustration)","score":0.7643296718597412},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7020748257637024},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.6686520576477051},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5667575001716614},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5090858340263367},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4764983057975769},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4296303391456604},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.20840302109718323},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1505926251411438}],"concepts":[{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.7643296718597412},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7020748257637024},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6686520576477051},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5667575001716614},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5090858340263367},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4764983057975769},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4296303391456604},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.20840302109718323},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1505926251411438},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/iwaenc.2018.8521400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iwaenc.2018.8521400","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 16th International Workshop on Acoustic Signal Enhancement (IWAENC)","raw_type":"proceedings-article"},{"id":"pmh:oai:trepo.tuni.fi:10024/214427","is_oa":false,"landing_page_url":"https://trepo.tuni.fi/handle/10024/214427","pdf_url":null,"source":{"id":"https://openalex.org/S7407055260","display_name":"Trepo - Institutional Repository of Tampere University","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"conference"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.46000000834465027,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W1522301498","https://openalex.org/W1563829901","https://openalex.org/W1897240248","https://openalex.org/W2020997493","https://openalex.org/W2051428568","https://openalex.org/W2127851351","https://openalex.org/W2141411743","https://openalex.org/W2146502635","https://openalex.org/W2149535104","https://openalex.org/W2158336491","https://openalex.org/W2168379380","https://openalex.org/W2289394825","https://openalex.org/W2291877678","https://openalex.org/W2407685581","https://openalex.org/W2563215737","https://openalex.org/W2746904187","https://openalex.org/W2964121744","https://openalex.org/W4239273178","https://openalex.org/W6600284362","https://openalex.org/W6631190155","https://openalex.org/W6681435938"],"related_works":["https://openalex.org/W3081694532","https://openalex.org/W1969211203","https://openalex.org/W1517958729","https://openalex.org/W2092272653","https://openalex.org/W4387002515","https://openalex.org/W2770665941","https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2275432853","https://openalex.org/W197907117"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,108],"low-latency":[4,109],"neural":[5,49,56],"network":[6,57],"based":[7],"speech":[8,16,29,67,79],"enhancement":[9,68],"system.":[10],"Low-latency":[11],"operation":[12,110],"is":[13,73,113],"critical":[14],"for":[15],"communication":[17],"applications.":[18],"The":[19,39,70],"system":[20,72],"uses":[21],"the":[22,32,36,52,93,102],"time-frequency":[23],"(TF)":[24],"masking":[25],"approach":[26],"to":[27,62,89,116],"retain":[28],"and":[30,66,75,92],"remove":[31],"non-speech":[33,99],"content":[34,100],"from":[35,86],"observed":[37],"signal.":[38],"ideal":[40],"TF":[41],"mask":[42],"are":[43,59],"obtained":[44],"by":[45],"supervised":[46],"training":[47],"of":[48,98],"networks.":[50],"As":[51],"main":[53],"contribution":[54],"different":[55],"models":[58],"experimentally":[60],"compared":[61],"investigate":[63],"computational":[64],"complexity":[65],"performance.":[69],"proposed":[71],"trained":[74],"tested":[76],"on":[77],"noisy":[78],"data":[80],"where":[81],"signal-to-noise":[82],"ratio":[83],"(SNR)":[84],"ranges":[85],"-5":[87],"dB":[88,91],"+5":[90],"results":[94],"show":[95],"significant":[96],"reduction":[97],"in":[101],"resulting":[103],"signal":[104],"while":[105],"still":[106],"meeting":[107],"criterion,":[111],"which":[112],"here":[114],"considered":[115],"be":[117],"less":[118],"than":[119],"20":[120],"ms.":[121]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
