{"id":"https://openalex.org/W3096643087","doi":"https://doi.org/10.21437/interspeech.2020-1030","title":"Noise Tokens: Learning Neural Noise Templates for Environment-Aware Speech Enhancement","display_name":"Noise Tokens: Learning Neural Noise Templates for Environment-Aware Speech Enhancement","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096643087","doi":"https://doi.org/10.21437/interspeech.2020-1030","mag":"3096643087"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-1030","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100358569","display_name":"Haoyu Li","orcid":"https://orcid.org/0000-0002-7102-8348"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Haoyu Li","raw_affiliation_strings":["SOKENDAI, Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOKENDAI, Japan","institution_ids":["https://openalex.org/I200475212","https://openalex.org/I4210110163"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007639385","display_name":"Junichi Yamagishi","orcid":"https://orcid.org/0000-0003-2752-3955"},"institutions":[{"id":"https://openalex.org/I184597095","display_name":"National Institute of Informatics","ror":"https://ror.org/04ksd4g47","country_code":"JP","type":"facility","lineage":["https://openalex.org/I1319490839","https://openalex.org/I184597095","https://openalex.org/I4210158934"]},{"id":"https://openalex.org/I200475212","display_name":"The Graduate University for Advanced Studies, SOKENDAI","ror":"https://ror.org/0516ah480","country_code":"JP","type":"education","lineage":["https://openalex.org/I200475212"]},{"id":"https://openalex.org/I4210110163","display_name":"Nippon Soken (Japan)","ror":"https://ror.org/01yk36x23","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210110163"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Junichi Yamagishi","raw_affiliation_strings":["SOKENDAI, Japan","National Institute of Informatics, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SOKENDAI, Japan","institution_ids":["https://openalex.org/I200475212","https://openalex.org/I4210110163"]},{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2452","last_page":"2456"},"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/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"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":0.9983000159263611,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.7518517971038818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7452609539031982},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6776040196418762},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6409471035003662},{"id":"https://openalex.org/keywords/template","display_name":"Template","score":0.4655979573726654},{"id":"https://openalex.org/keywords/background-noise","display_name":"Background noise","score":0.4285685122013092},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.257443368434906},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10445258021354675}],"concepts":[{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.7518517971038818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7452609539031982},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6776040196418762},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6409471035003662},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.4655979573726654},{"id":"https://openalex.org/C100675267","wikidata":"https://www.wikidata.org/wiki/Q1371624","display_name":"Background noise","level":2,"score":0.4285685122013092},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.257443368434906},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10445258021354675},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2020-1030","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-1030","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/15","display_name":"Life in Land"}],"awards":[{"id":"https://openalex.org/G1526460031","display_name":null,"funder_award_id":"18H04112","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G1601555150","display_name":"Encoder Factorization for Capturing Dialect and Articulation Level in End-to-End Speech Synthesis","funder_award_id":"19K24372","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G1710514051","display_name":null,"funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G3582502417","display_name":null,"funder_award_id":"JPMJCR18A6","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G360976672","display_name":"Biometric Information Protection Utilization Infrastructure to Ensure Personal Convenience and Prevent Identity Theft","funder_award_id":"18H04120","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G4104777191","display_name":null,"funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G5216536157","display_name":null,"funder_award_id":"18H04120","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G5375717198","display_name":null,"funder_award_id":"18KT0051","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G6299358200","display_name":"PRISM: Speech privacy preservation based on selecting masking","funder_award_id":"18H04112","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6718509927","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G6954941931","display_name":"Communication System for Defending against Attacks of Media Clones","funder_award_id":"16H06302","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7623259429","display_name":"Robust voice cloning technologies in noisy environments and its applications","funder_award_id":"17H04687","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G7879866177","display_name":null,"funder_award_id":"CREST","funder_id":"https://openalex.org/F4320320912","funder_display_name":"Ministry of Education, Culture, Sports, Science and Technology"},{"id":"https://openalex.org/G8315410620","display_name":null,"funder_award_id":"JPMJCR18A6","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G8937069383","display_name":"Safe and secure speech information processing based on liveness detection and ASVspoof challenge","funder_award_id":"18KT0051","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320912","display_name":"Ministry of Education, Culture, Sports, Science and Technology","ror":"https://ror.org/048rj2z13"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1552314771","https://openalex.org/W1897240248","https://openalex.org/W2044893557","https://openalex.org/W2069681747","https://openalex.org/W2102113734","https://openalex.org/W2141998673","https://openalex.org/W2155998647","https://openalex.org/W2386192529","https://openalex.org/W2403766732","https://openalex.org/W2794490148","https://openalex.org/W2963902628","https://openalex.org/W2964195110","https://openalex.org/W2973062255","https://openalex.org/W2973133192","https://openalex.org/W2980878766","https://openalex.org/W2998572311","https://openalex.org/W3015626488","https://openalex.org/W3015826515","https://openalex.org/W3127686677","https://openalex.org/W4298580827","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3096184950","https://openalex.org/W4231424160","https://openalex.org/W2135485548","https://openalex.org/W2373767407","https://openalex.org/W774601707","https://openalex.org/W2187949121","https://openalex.org/W2376606440","https://openalex.org/W2251439150","https://openalex.org/W2964951088","https://openalex.org/W3011514165"],"abstract_inverted_index":{"In":[0],"recent":[1],"years,":[2],"speech":[3],"enhancement":[4],"(SE)":[5],"has":[6],"achieved":[7],"impressive":[8],"progress":[9],"with":[10,57,80],"the":[11,18,35,58,63,69,95,124],"success":[12],"of":[13,49,98,116],"deep":[14],"neural":[15,50,110],"networks":[16],"(DNNs).However,":[17],"DNN":[19,70,103],"approach":[20],"usually":[21],"fails":[22],"to":[23,26,72,76,112],"generalize":[24],"well":[25],"unseen":[27],"environmental":[28],"noise":[29,51,126],"that":[30,53,85,92],"is":[31,88],"not":[32],"included":[33],"in":[34],"training.To":[36],"address":[37],"this":[38],"problem,":[39],"we":[40,105],"propose":[41],"\"noise":[42],"tokens\"":[43],"(NTs),":[44],"which":[45],"are":[46,54],"a":[47,108],"set":[48],"templates":[52],"jointly":[55],"trained":[56],"SE":[59,99],"system.NTs":[60],"dynamically":[61],"capture":[62],"environment":[64],"variability":[65],"and":[66,134],"thus":[67],"enable":[68],"model":[71],"handle":[73],"various":[74],"environments":[75],"produce":[77],"STFT":[78,119],"magnitude":[79],"higher":[81],"quality.Experimental":[82],"results":[83],"show":[84,123],"using":[86],"NTs":[87],"an":[89],"effective":[90],"strategy":[91],"consistently":[93],"improves":[94],"generalization":[96],"ability":[97],"systems":[100],"across":[101],"different":[102],"architectures.Furthermore,":[104],"investigate":[106],"applying":[107],"state-of-the-art":[109],"vocoder":[111],"generate":[113],"waveform":[114,136],"instead":[115],"traditional":[117],"inverse":[118],"(ISTFT).Subjective":[120],"listening":[121],"tests":[122],"residual":[125],"can":[127],"be":[128],"significantly":[129],"suppressed":[130],"through":[131],"mel-spectrogram":[132],"correction":[133],"vocoder-based":[135],"synthesis.":[137]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}