{"id":"https://openalex.org/W3149824848","doi":"https://doi.org/10.1109/slt48900.2021.9383507","title":"Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model","display_name":"Enhancing Low-Quality Voice Recordings Using Disentangled Channel Factor and Neural Waveform Model","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3149824848","doi":"https://doi.org/10.1109/slt48900.2021.9383507","mag":"3149824848"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","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":["National Institute of Informatics, Japan","SOKENDAI, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"SOKENDAI, Japan","institution_ids":["https://openalex.org/I200475212","https://openalex.org/I4210110163"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045907056","display_name":"Yang Ai","orcid":"https://orcid.org/0000-0001-6668-022X"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Ai","raw_affiliation_strings":["University of Science and Technology of China, P.R.China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Science and Technology of China, P.R.China","institution_ids":["https://openalex.org/I126520041"]}]},{"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":["National Institute of Informatics, Japan","SOKENDAI, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Institute of Informatics, Japan","institution_ids":["https://openalex.org/I184597095"]},{"raw_affiliation_string":"SOKENDAI, Japan","institution_ids":["https://openalex.org/I200475212","https://openalex.org/I4210110163"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"9","issue":null,"first_page":"734","last_page":"741"},"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":0.9995999932289124,"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":0.9995999932289124,"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":0.8311136960983276},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.8164950609207153},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7102514505386353},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.675904393196106},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6548522710800171},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.5631161332130432},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5542459487915039},{"id":"https://openalex.org/keywords/factor","display_name":"Factor (programming language)","score":0.4883675277233124},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4592985212802887},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.440775066614151},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.43410632014274597},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.41753631830215454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33854448795318604},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.12859606742858887},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.07515695691108704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8311136960983276},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8164950609207153},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7102514505386353},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.675904393196106},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6548522710800171},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.5631161332130432},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5542459487915039},{"id":"https://openalex.org/C2781039887","wikidata":"https://www.wikidata.org/wiki/Q1391724","display_name":"Factor (programming language)","level":2,"score":0.4883675277233124},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4592985212802887},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.440775066614151},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.43410632014274597},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.41753631830215454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33854448795318604},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.12859606742858887},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.07515695691108704},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383507","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383507","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1897240248","https://openalex.org/W1952824372","https://openalex.org/W2044893557","https://openalex.org/W2067295501","https://openalex.org/W2086381917","https://openalex.org/W2086796102","https://openalex.org/W2098832077","https://openalex.org/W2102003408","https://openalex.org/W2121973264","https://openalex.org/W2128653836","https://openalex.org/W2164502538","https://openalex.org/W2187089797","https://openalex.org/W2386192529","https://openalex.org/W2504718840","https://openalex.org/W2519091744","https://openalex.org/W2794490148","https://openalex.org/W2883440650","https://openalex.org/W2907262790","https://openalex.org/W2940385941","https://openalex.org/W2949382160","https://openalex.org/W2963341071","https://openalex.org/W2963403868","https://openalex.org/W2963902628","https://openalex.org/W2964121744","https://openalex.org/W2964243274","https://openalex.org/W2964307104","https://openalex.org/W2972359262","https://openalex.org/W2973220283","https://openalex.org/W2987137416","https://openalex.org/W2998161426","https://openalex.org/W3015626488","https://openalex.org/W3015676952","https://openalex.org/W3096080837","https://openalex.org/W3096159803","https://openalex.org/W3096643087","https://openalex.org/W4298580827","https://openalex.org/W4385245566","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6748409065","https://openalex.org/W6750489868","https://openalex.org/W6753016063","https://openalex.org/W6761768988","https://openalex.org/W6770001000"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W3127543252","https://openalex.org/W2065606036","https://openalex.org/W2942893872"],"abstract_inverted_index":{"High-quality":[0],"speech":[1,8,12,102,116,128],"corpora":[2],"are":[3,14,20],"essential":[4],"foundations":[5],"for":[6],"most":[7],"applications.":[9],"However,":[10],"such":[11],"data":[13],"expensive":[15],"and":[16],"limited":[17],"since":[18],"they":[19],"collected":[21],"in":[22],"professional":[23,41,114],"recording":[24],"environments.":[25],"In":[26],"this":[27,79],"work,":[28],"we":[29,48,68,94],"propose":[30],"an":[31,81],"encoder-decoder":[32],"neural":[33,97],"network":[34,63],"to":[35,40,87,99],"automatically":[36],"enhance":[37],"low-quality":[38],"recordings":[39],"high-quality":[42,115,120],"recordings.":[43],"To":[44],"address":[45],"channel":[46,53,71],"variability,":[47],"first":[49],"filter":[50],"out":[51],"the":[52,56,61,70,89,101,108,123],"characteristics":[54],"from":[55,73],"original":[57],"input":[58],"audio":[59,121],"using":[60],"encoder":[62],"with":[64,132],"adversarial":[65],"training.":[66],"Next,":[67],"disentangle":[69],"factor":[72],"a":[74,96,113],"reference":[75],"audio.":[76],"Conditioned":[77],"on":[78],"factor,":[80],"auto-regressive":[82],"decoder":[83],"is":[84],"then":[85],"used":[86],"predict":[88],"target-environment":[90],"Mel":[91],"spectrogram.":[92],"Finally,":[93],"apply":[95],"vocoder":[98],"synthesize":[100],"waveform.":[103],"Experimental":[104],"results":[105],"show":[106],"that":[107],"proposed":[109],"system":[110],"can":[111],"generate":[112],"waveform":[117],"when":[118],"setting":[119],"as":[122],"reference.":[124],"It":[125],"also":[126],"improves":[127],"enhancement":[129],"performance":[130],"compared":[131],"several":[133],"state-of-the-art":[134],"baseline":[135],"systems.":[136]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}