{"id":"https://openalex.org/W3196660985","doi":"https://doi.org/10.23919/eusipco54536.2021.9616081","title":"Task-aware Warping Factors in Mask-based Speech Enhancement","display_name":"Task-aware Warping Factors in Mask-based Speech Enhancement","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3196660985","doi":"https://doi.org/10.23919/eusipco54536.2021.9616081","mag":"3196660985"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9616081","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616081","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5101991100","display_name":"Qiongqiong Wang","orcid":"https://orcid.org/0000-0002-9903-0618"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Qiongqiong Wang","raw_affiliation_strings":["Biometrics Research Laboratories, NEC Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Biometrics Research Laboratories, NEC Corporation, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004287909","display_name":"Kong Aik Lee","orcid":"https://orcid.org/0000-0001-9133-3000"},"institutions":[{"id":"https://openalex.org/I89630735","display_name":"Yokohama City University","ror":"https://ror.org/0135d1r83","country_code":"JP","type":"education","lineage":["https://openalex.org/I89630735"]},{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["JP","SG"],"is_corresponding":false,"raw_author_name":"Kong Aik Lee","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore and the School of Data Science, Yokohama City University, Japan","Institute for Infocomm Research, A&#x002A","STAR, Singapore and the School of Data Science, Yokohama City University, Japan"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore and the School of Data Science, Yokohama City University, Japan","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I89630735"]},{"raw_affiliation_string":"Institute for Infocomm Research, A&#x002A","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"STAR, Singapore and the School of Data Science, Yokohama City University, Japan","institution_ids":["https://openalex.org/I89630735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031109112","display_name":"Takafumi Koshinaka","orcid":"https://orcid.org/0000-0002-2343-5125"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I89630735","display_name":"Yokohama City University","ror":"https://ror.org/0135d1r83","country_code":"JP","type":"education","lineage":["https://openalex.org/I89630735"]}],"countries":["JP","SG"],"is_corresponding":false,"raw_author_name":"Takafumi Koshinaka","raw_affiliation_strings":["Institute for Infocomm Research, A*STAR, Singapore and the School of Data Science, Yokohama City University, Japan","Institute for Infocomm Research, A&#x002A","STAR, Singapore and the School of Data Science, Yokohama City University, Japan"],"affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research, A*STAR, Singapore and the School of Data Science, Yokohama City University, Japan","institution_ids":["https://openalex.org/I3005327000","https://openalex.org/I89630735"]},{"raw_affiliation_string":"Institute for Infocomm Research, A&#x002A","institution_ids":["https://openalex.org/I3005327000"]},{"raw_affiliation_string":"STAR, Singapore and the School of Data Science, Yokohama City University, Japan","institution_ids":["https://openalex.org/I89630735"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031351840","display_name":"Koji Okabe","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Koji Okabe","raw_affiliation_strings":["Biometrics Research Laboratories, NEC Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Biometrics Research Laboratories, NEC Corporation, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059740393","display_name":"H. Yamamoto","orcid":"https://orcid.org/0000-0001-7966-2629"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hitoshi Yamamoto","raw_affiliation_strings":["Biometrics Research Laboratories, NEC Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"Biometrics Research Laboratories, NEC Corporation, Japan","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101991100"],"corresponding_institution_ids":["https://openalex.org/I118347220"],"apc_list":null,"apc_paid":null,"fwci":0.3441,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.51981195,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"476","last_page":"480"},"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":0.9994000196456909,"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":0.9984999895095825,"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":0.8051055669784546},{"id":"https://openalex.org/keywords/image-warping","display_name":"Image warping","score":0.7979865074157715},{"id":"https://openalex.org/keywords/pesq","display_name":"PESQ","score":0.7534985542297363},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7217761278152466},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6647894382476807},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5875779986381531},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.5294997692108154},{"id":"https://openalex.org/keywords/dynamic-time-warping","display_name":"Dynamic time warping","score":0.5086989998817444},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.46504130959510803},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.3878612816333771},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3263242840766907},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2831149101257324},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07004964351654053}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051055669784546},{"id":"https://openalex.org/C157202957","wikidata":"https://www.wikidata.org/wiki/Q1659609","display_name":"Image warping","level":2,"score":0.7979865074157715},{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.7534985542297363},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7217761278152466},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6647894382476807},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5875779986381531},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.5294997692108154},{"id":"https://openalex.org/C88516994","wikidata":"https://www.wikidata.org/wiki/Q1268863","display_name":"Dynamic time warping","level":2,"score":0.5086989998817444},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.46504130959510803},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.3878612816333771},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3263242840766907},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2831149101257324},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07004964351654053},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9616081","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9616081","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2078528584","https://openalex.org/W2141411743","https://openalex.org/W2150341604","https://openalex.org/W2219249508","https://openalex.org/W2291877678","https://openalex.org/W2407127962","https://openalex.org/W2516764878","https://openalex.org/W2593116425","https://openalex.org/W2889031312","https://openalex.org/W2890964092","https://openalex.org/W2899754108","https://openalex.org/W2940275453","https://openalex.org/W2945472816","https://openalex.org/W2962780374","https://openalex.org/W2962866211","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2963868408","https://openalex.org/W2972425344","https://openalex.org/W2981087920","https://openalex.org/W2998161426","https://openalex.org/W3003901600","https://openalex.org/W3016120385","https://openalex.org/W3025783616","https://openalex.org/W3030102521","https://openalex.org/W3082484524","https://openalex.org/W3096991551","https://openalex.org/W3097906045","https://openalex.org/W3100464335","https://openalex.org/W3142252347","https://openalex.org/W4205947740","https://openalex.org/W4253928870","https://openalex.org/W4289302904","https://openalex.org/W6662018355","https://openalex.org/W6668037159","https://openalex.org/W6743462201","https://openalex.org/W6769867024"],"related_works":["https://openalex.org/W2166831097","https://openalex.org/W2037635165","https://openalex.org/W2965825901","https://openalex.org/W2140410589","https://openalex.org/W4200562864","https://openalex.org/W2886543975","https://openalex.org/W4378191934","https://openalex.org/W1531156847","https://openalex.org/W3196660985","https://openalex.org/W4302293282"],"abstract_inverted_index":{"This":[0],"paper":[1],"proposes":[2],"the":[3,17,27,30,47,80,88,123,130,151,165,169,204],"use":[4,170],"of":[5,32,115,140,171,203],"two":[6],"task-aware":[7,172,205],"warping":[8,146,173,206],"factors":[9,91,207],"in":[10,23,39,150,236],"mask-based":[11,95],"speech":[12,55,72,137,175],"enhancement":[13,33],"(SE).":[14],"One":[15],"controls":[16,29],"balance":[18],"between":[19],"speech-maintenance":[20],"and":[21,70,98,129,136,191,217,223,232],"noise-removal":[22],"training":[24],"phases,":[25],"while":[26,184],"other":[28,61],"degree":[31],"applied":[34],"to":[35,53,59,86,93,106,160,234],"specific":[36],"downstream":[37,62],"tasks":[38,109],"testing":[40,152],"phases.":[41],"Our":[42],"proposal":[43],"is":[44,84,229],"based":[45],"on":[46,122,198,211],"observation":[48],"that":[49,144],"SE":[50,96,103,157],"systems":[51],"trained":[52],"improve":[54,60],"quality":[56,138,176,224],"often":[57],"fail":[58],"tasks,":[63],"such":[64],"as":[65],"automatic":[66,71],"speaker":[67],"verification":[68],"(ASV)":[69],"recognition":[73],"(ASR),":[74],"because":[75],"they":[76],"do":[77],"not":[78],"share":[79],"same":[81],"objectives.":[82],"It":[83],"easy":[85,233],"apply":[87,235],"proposed":[89,117,227],"dual-warping":[90],"approach":[92,118],"any":[94],"method,":[97],"it":[99],"allows":[100],"a":[101,155,187,194],"single":[102,156],"base":[104,158],"module":[105,159],"handle":[107],"multiple":[108],"without":[110],"task-dependent":[111],"training.":[112],"The":[113,201,226],"effectiveness":[114,202],"our":[116],"has":[119],"been":[120],"confirmed":[121],"SITW":[124],"dataset":[125],"for":[126,134,154,215,221],"ASV":[127,185,216],"evaluation":[128],"LibriSpeech":[131,218],"test-clean":[132],"set":[133,214,220],"ASR":[135,192,222],"evaluations":[139],"0-20dB.":[141],"We":[142],"show":[143],"different":[145],"values":[147],"are":[148],"necessary":[149],"phases":[153],"achieve":[161],"optimal":[162],"performance":[163],"w.r.t.":[164],"three":[166],"tasks.":[167],"With":[168],"factors,":[174],"was":[177],"improved":[178],"by":[179],"an":[180],"84.7%":[181],"PESQ":[182],"increase,":[183],"had":[186,193],"22.4%":[188],"EER":[189],"reduction,":[190,197],"52.2%":[195],"WER":[196],"0dB":[199],"speech.":[200],"were":[208],"also":[209],"cross-validated":[210],"VoxCeleb-1":[212],"test":[213],"dev-clean":[219],"evaluations.":[225],"method":[228],"highly":[230],"effective":[231],"practice.":[237]},"counts_by_year":[{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}