{"id":"https://openalex.org/W2930648092","doi":"https://doi.org/10.1109/icassp.2019.8683130","title":"Speech Denoising by Parametric Resynthesis","display_name":"Speech Denoising by Parametric Resynthesis","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2930648092","doi":"https://doi.org/10.1109/icassp.2019.8683130","mag":"2930648092"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5010858961","display_name":"Soumi Maiti","orcid":"https://orcid.org/0000-0001-6940-0115"},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]},{"id":"https://openalex.org/I83041322","display_name":"Brooklyn College","ror":"https://ror.org/019k4jq75","country_code":"US","type":"education","lineage":["https://openalex.org/I83041322"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["The CUNY Graduate Center and Brooklyn College, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The CUNY Graduate Center and Brooklyn College, New York, NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I83041322"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I121847817","display_name":"The Graduate Center, CUNY","ror":"https://ror.org/00awd9g61","country_code":"US","type":"education","lineage":["https://openalex.org/I121847817"]},{"id":"https://openalex.org/I83041322","display_name":"Brooklyn College","ror":"https://ror.org/019k4jq75","country_code":"US","type":"education","lineage":["https://openalex.org/I83041322"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael I Mandel","raw_affiliation_strings":["The CUNY Graduate Center and Brooklyn College, New York, NY"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The CUNY Graduate Center and Brooklyn College, New York, NY","institution_ids":["https://openalex.org/I121847817","https://openalex.org/I83041322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9558,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.72085616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"6995","last_page":"6999"},"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":0.9998999834060669,"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":0.9970999956130981,"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/speech-recognition","display_name":"Speech recognition","score":0.7614102959632874},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7525975704193115},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.72963547706604},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.7177541255950928},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.6413872241973877},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6312271952629089},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.5430857539176941},{"id":"https://openalex.org/keywords/wiener-filter","display_name":"Wiener filter","score":0.5429399609565735},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5325018167495728},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5086575150489807},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.47284796833992004},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4708523154258728},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4360729455947876},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4169837236404419},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32705554366111755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10624101758003235}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7614102959632874},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7525975704193115},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.72963547706604},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.7177541255950928},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.6413872241973877},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6312271952629089},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.5430857539176941},{"id":"https://openalex.org/C18537770","wikidata":"https://www.wikidata.org/wiki/Q25523","display_name":"Wiener filter","level":2,"score":0.5429399609565735},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5325018167495728},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5086575150489807},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.47284796833992004},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4708523154258728},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4360729455947876},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4169837236404419},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32705554366111755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10624101758003235},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683130","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683130","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 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","display_name":"Peace, Justice and strong institutions","score":0.7900000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W95152782","https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1552314771","https://openalex.org/W2027081853","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2158904676","https://openalex.org/W2179369514","https://openalex.org/W2289394825","https://openalex.org/W2471520273","https://openalex.org/W2519091744","https://openalex.org/W2598638573","https://openalex.org/W2749130229","https://openalex.org/W2889455712","https://openalex.org/W2889517470","https://openalex.org/W2913144232","https://openalex.org/W2962866211","https://openalex.org/W2963103134","https://openalex.org/W2964121744","https://openalex.org/W6603838645","https://openalex.org/W6631190155"],"related_works":["https://openalex.org/W2106793170","https://openalex.org/W1577562165","https://openalex.org/W10581632","https://openalex.org/W1927421023","https://openalex.org/W2028846388","https://openalex.org/W2072015625","https://openalex.org/W4295210860","https://openalex.org/W3149582125","https://openalex.org/W2438843077","https://openalex.org/W2161534637"],"abstract_inverted_index":{"This":[0],"work":[1],"proposes":[2],"the":[3,11,64,69,86,90,99,111,122,141],"use":[4],"of":[5,68],"clean":[6],"speech":[7,18,50,80],"vocoder":[8],"parameters":[9,21],"as":[10],"target":[12],"for":[13,25,135,160],"a":[14,57,104,154],"neural":[15,42],"network":[16],"performing":[17],"enhancement.":[19],"These":[20],"have":[22,45],"been":[23,47],"designed":[24],"text-to-speech":[26,59],"synthesis":[27],"so":[28],"that":[29,61,130,153],"they":[30],"both":[31],"produce":[32,77],"high-quality":[33],"resyntheses":[34],"and":[35,103,118,120,151],"also":[36],"are":[37],"straightforward":[38],"to":[39,56,76,85,95],"model":[40,73,109,156],"with":[41,137,148],"networks,":[43],"but":[44],"not":[46],"utilized":[48],"in":[49,89,115],"enhancement":[51],"until":[52],"now.":[53],"In":[54,93],"comparison":[55,94],"matched":[58],"system":[60],"is":[62,74,132],"given":[63],"ground":[65],"truth":[66],"transcripts":[67],"noisy":[70,91],"speech,":[71],"our":[72,108],"able":[75],"more":[78],"natural":[79],"because":[81],"it":[82],"has":[83],"access":[84],"true":[87],"prosody":[88],"speech.":[92],"two":[96,149],"denoising":[97],"systems,":[98],"oracle":[100,112,142],"Wiener":[101,113,143],"mask":[102,106,114],"DNN-based":[105],"predictor,":[107],"equals":[110],"subjective":[116],"quality":[117],"intelligibility":[119],"surpasses":[121],"realistic":[123],"system.":[124],"A":[125],"vocoder-based":[126],"upper":[127],"bound":[128],"shows":[129],"there":[131],"still":[133],"room":[134],"improvement":[136],"this":[138],"approach":[139],"beyond":[140],"mask.":[144],"We":[145],"test":[146],"speaker-dependence":[147],"speakers":[150],"show":[152],"single":[155],"can":[157],"be":[158],"used":[159],"multiple":[161],"speakers.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}