{"id":"https://openalex.org/W3015337486","doi":"https://doi.org/10.1109/icassp40776.2020.9053925","title":"Self-Supervised Denoising Autoencoder with Linear Regression Decoder for Speech Enhancement","display_name":"Self-Supervised Denoising Autoencoder with Linear Regression Decoder for Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W3015337486","doi":"https://doi.org/10.1109/icassp40776.2020.9053925","mag":"3015337486"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053925","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/A5030281426","display_name":"Ryandhimas E. Zezario","orcid":"https://orcid.org/0000-0001-7319-8263"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Ryandhimas E. Zezario","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089443958","display_name":"Tassadaq Hussain","orcid":"https://orcid.org/0000-0003-1396-5429"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Tassadaq Hussain","raw_affiliation_strings":["Taiwan International Graduate Program in Social Network and Human-Centered Computing, Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Taiwan International Graduate Program in Social Network and Human-Centered Computing, Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034792613","display_name":"Xugang Lu","orcid":"https://orcid.org/0000-0001-7075-448X"},"institutions":[{"id":"https://openalex.org/I90023481","display_name":"National Institute of Information and Communications Technology","ror":"https://ror.org/016bgq349","country_code":"JP","type":"facility","lineage":["https://openalex.org/I90023481"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Xugang Lu","raw_affiliation_strings":["National Institute of Information and Communications Technology, Japan"],"affiliations":[{"raw_affiliation_string":"National Institute of Information and Communications Technology, Japan","institution_ids":["https://openalex.org/I90023481"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071214181","display_name":"Hsin\u2010Min Wang","orcid":"https://orcid.org/0000-0003-3599-5071"},"institutions":[{"id":"https://openalex.org/I4210098366","display_name":"Institute of Information Science, Academia Sinica","ror":"https://ror.org/00z83z196","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210098366","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Hsin-Min Wang","raw_affiliation_strings":["Institute of Information Science, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Institute of Information Science, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210098366"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044008055","display_name":"Yu Tsao","orcid":"https://orcid.org/0000-0001-6956-0418"},"institutions":[{"id":"https://openalex.org/I4210086894","display_name":"Research Center for Information Technology Innovation, Academia Sinica","ror":"https://ror.org/000zgvm20","country_code":"TW","type":"facility","lineage":["https://openalex.org/I4210086894","https://openalex.org/I84653119"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yu Tsao","raw_affiliation_strings":["Research Center for Information Technology Innovation, Academia Sinica, Taiwan"],"affiliations":[{"raw_affiliation_string":"Research Center for Information Technology Innovation, Academia Sinica, Taiwan","institution_ids":["https://openalex.org/I4210086894"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030281426"],"corresponding_institution_ids":["https://openalex.org/I4210086894"],"apc_list":null,"apc_paid":null,"fwci":2.8791,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.91481238,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6669","last_page":"6673"},"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":0.9937999844551086,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9930999875068665,"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/autoencoder","display_name":"Autoencoder","score":0.707818865776062},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6670839190483093},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6648561358451843},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.6096714735031128},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5989004373550415},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5494087934494019},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.5469810962677002},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5344288349151611},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5215282440185547},{"id":"https://openalex.org/keywords/noise-measurement","display_name":"Noise measurement","score":0.42612895369529724},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3725772202014923},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.20069637894630432}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.707818865776062},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6670839190483093},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6648561358451843},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.6096714735031128},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5989004373550415},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5494087934494019},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.5469810962677002},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5344288349151611},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5215282440185547},{"id":"https://openalex.org/C29265498","wikidata":"https://www.wikidata.org/wiki/Q7047719","display_name":"Noise measurement","level":3,"score":0.42612895369529724},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3725772202014923},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.20069637894630432},{"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:10.1109/icassp40776.2020.9053925","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053925","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","score":0.7799999713897705,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W2966661","https://openalex.org/W1482149378","https://openalex.org/W1492775261","https://openalex.org/W1495679096","https://openalex.org/W1552314771","https://openalex.org/W1604717235","https://openalex.org/W1952003395","https://openalex.org/W1963950237","https://openalex.org/W1992475611","https://openalex.org/W2000916836","https://openalex.org/W2039708501","https://openalex.org/W2044893557","https://openalex.org/W2053757129","https://openalex.org/W2100495367","https://openalex.org/W2100556411","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2141998673","https://openalex.org/W2153894152","https://openalex.org/W2296167893","https://openalex.org/W2326115863","https://openalex.org/W2394498270","https://openalex.org/W2404637451","https://openalex.org/W2405774341","https://openalex.org/W2515930231","https://openalex.org/W2516342150","https://openalex.org/W2550397165","https://openalex.org/W2586068394","https://openalex.org/W2594607416","https://openalex.org/W2605589342","https://openalex.org/W2649558613","https://openalex.org/W2747161606","https://openalex.org/W2755891984","https://openalex.org/W2765164841","https://openalex.org/W2809824582","https://openalex.org/W2892356933","https://openalex.org/W2899406861","https://openalex.org/W2941290535","https://openalex.org/W2962866211","https://openalex.org/W2963853675","https://openalex.org/W2972425344","https://openalex.org/W3091830790","https://openalex.org/W3127686677","https://openalex.org/W3147539069","https://openalex.org/W4245919820","https://openalex.org/W6629448772","https://openalex.org/W6633117090","https://openalex.org/W6711896204","https://openalex.org/W6713658392","https://openalex.org/W6744261651","https://openalex.org/W6762150201","https://openalex.org/W7005873353"],"related_works":["https://openalex.org/W3037110488","https://openalex.org/W4292947472","https://openalex.org/W4287867034","https://openalex.org/W3108403339","https://openalex.org/W2022538999","https://openalex.org/W4312773500","https://openalex.org/W2162712524","https://openalex.org/W1955763106","https://openalex.org/W2002243964","https://openalex.org/W3090086172"],"abstract_inverted_index":{"Nonlinear":[0],"spectral":[1],"mapping-based":[2],"models":[3],"based":[4],"on":[5],"supervised":[6,16,53,157],"learning":[7,17,54,63,96],"have":[8],"successfully":[9],"applied":[10],"for":[11,39,65,77,106],"speech":[12,26,66,78,86,158],"enhancement.":[13,79],"However,":[14],"as":[15,87,152],"approaches,":[18,160],"a":[19,48,94,103],"large":[20],"amount":[21],"of":[22,52],"labelled":[23],"data":[24,182],"(noisy-clean":[25],"pairs)":[27],"should":[28],"be":[29,112],"provided":[30],"to":[31,132,154,175],"train":[32],"those":[33],"models.":[34],"In":[35,56,98],"addition,":[36,99],"their":[37],"performances":[38,173],"unseen":[40,165],"noisy":[41,85],"conditions":[42],"are":[43],"not":[44],"guaranteed,":[45],"which":[46],"is":[47,82],"common":[49],"weak":[50],"point":[51],"approaches.":[55],"this":[57],"study,":[58],"we":[59,169],"proposed":[60,135,141],"an":[61],"unsupervised":[62],"approach":[64],"enhancement,":[67],"i.e.,":[68],"denoising":[69],"autoencoder":[70],"with":[71,84,100],"linear":[72,123],"regression":[73,124],"decoder":[74],"(DAELD)":[75],"model":[76],"The":[80],"DAELD":[81,142,178],"trained":[83],"both":[88,162],"input":[89],"and":[90,146,164,188],"target":[91],"output":[92],"in":[93,161],"self-supervised":[95],"manner.":[97],"properly":[101],"setting":[102],"shrinkage":[104],"threshold":[105],"internal":[107],"hidden":[108,119],"representations,":[109],"noise":[110,166,186],"could":[111,143],"removed":[113],"during":[114],"the":[115,118,122,134,140,155,180],"reconstruction":[116],"from":[117],"representations":[120],"via":[121],"decoder.":[125],"Speech":[126],"enhancement":[127,150,159],"experiments":[128],"were":[129],"carried":[130],"out":[131],"test":[133],"model.":[136],"Results":[137],"confirmed":[138],"that":[139,171],"achieve":[144,176],"comparable":[145],"sometimes":[147],"even":[148],"better":[149],"performance":[151],"compared":[153],"conventional":[156],"seen":[163],"environments.":[167],"Moreover,":[168],"observe":[170],"higher":[172],"tend":[174],"by":[177],"when":[179],"training":[181],"cover":[183],"more":[184],"diverse":[185],"types":[187],"signal-tonoise-ratio":[189],"(SNR)":[190],"levels.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}