{"id":"https://openalex.org/W2989251843","doi":"https://doi.org/10.1109/icassp40776.2020.9053296","title":"Speaker Independence of Neural Vocoders and Their Effect on Parametric Resynthesis Speech Enhancement","display_name":"Speaker Independence of Neural Vocoders and Their Effect on Parametric Resynthesis Speech Enhancement","publication_year":2020,"publication_date":"2020-04-09","ids":{"openalex":"https://openalex.org/W2989251843","doi":"https://doi.org/10.1109/icassp40776.2020.9053296","mag":"2989251843"},"language":"en","primary_location":{"id":"doi:10.1109/icassp40776.2020.9053296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053296","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":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.06266","any_repository_has_fulltext":true},"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"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["The Graduate Center, CUNY, Computer Science, New York, NY, USA","Computer Science,The Graduate Center, CUNY,New York,NY,USA"],"affiliations":[{"raw_affiliation_string":"The Graduate Center, CUNY, Computer Science, New York, NY, USA","institution_ids":["https://openalex.org/I121847817"]},{"raw_affiliation_string":"Computer Science,The Graduate Center, CUNY,New York,NY,USA","institution_ids":["https://openalex.org/I121847817"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"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":["Brooklyn College, Computer and Information Science, Brooklyn, NY, USA","Computer and Information Science,Brooklyn College,Brooklyn,NY,USA"],"affiliations":[{"raw_affiliation_string":"Brooklyn College, Computer and Information Science, Brooklyn, NY, USA","institution_ids":["https://openalex.org/I83041322"]},{"raw_affiliation_string":"Computer and Information Science,Brooklyn College,Brooklyn,NY,USA","institution_ids":["https://openalex.org/I83041322"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5010858961"],"corresponding_institution_ids":["https://openalex.org/I121847817"],"apc_list":null,"apc_paid":null,"fwci":0.3048,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.50795001,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"206","last_page":"210"},"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":0.9984999895095825,"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/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9908999800682068,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7335245609283447},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7326816916465759},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5484576225280762},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.49507084488868713},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.476977676153183},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4430360496044159},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4367198646068573},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.4164777100086212},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.36135220527648926},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26333773136138916},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.18081268668174744},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09965565800666809}],"concepts":[{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7335245609283447},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7326816916465759},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5484576225280762},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.49507084488868713},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.476977676153183},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4430360496044159},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4367198646068573},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.4164777100086212},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.36135220527648926},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26333773136138916},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.18081268668174744},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09965565800666809},{"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/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},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp40776.2020.9053296","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp40776.2020.9053296","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"},{"id":"pmh:oai:arXiv.org:1911.06266","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.06266","pdf_url":"https://arxiv.org/pdf/1911.06266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2989251843","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1911.06266v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.06266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.06266","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/ng8t-kt74","is_oa":true,"landing_page_url":"https://doi.org/10.17023/ng8t-kt74","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.06266","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.06266","pdf_url":"https://arxiv.org/pdf/1911.06266","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2989251843.pdf","grobid_xml":"https://content.openalex.org/works/W2989251843.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W1482149378","https://openalex.org/W1522301498","https://openalex.org/W1924770834","https://openalex.org/W1952824372","https://openalex.org/W1983108229","https://openalex.org/W2067295501","https://openalex.org/W2069681747","https://openalex.org/W2113131123","https://openalex.org/W2154920538","https://openalex.org/W2471520273","https://openalex.org/W2591927543","https://openalex.org/W2598638573","https://openalex.org/W2600556233","https://openalex.org/W2654729393","https://openalex.org/W2788851830","https://openalex.org/W2898847420","https://openalex.org/W2902132730","https://openalex.org/W2930648092","https://openalex.org/W2949382160","https://openalex.org/W2952220610","https://openalex.org/W2952917250","https://openalex.org/W2963091184","https://openalex.org/W2963103134","https://openalex.org/W2963341071","https://openalex.org/W2998498479","https://openalex.org/W4232282348","https://openalex.org/W6631190155","https://openalex.org/W6640212811","https://openalex.org/W6734815144","https://openalex.org/W6748409065","https://openalex.org/W6751512325","https://openalex.org/W6752910514","https://openalex.org/W6755592152","https://openalex.org/W6756251360"],"related_works":["https://openalex.org/W3015626488","https://openalex.org/W2067821332","https://openalex.org/W3037730521","https://openalex.org/W1967726656","https://openalex.org/W3157724195","https://openalex.org/W1970405784","https://openalex.org/W1552784139","https://openalex.org/W2118415306","https://openalex.org/W3204950929","https://openalex.org/W2121860382","https://openalex.org/W2738829087","https://openalex.org/W3148935696","https://openalex.org/W2289873871","https://openalex.org/W2562962191","https://openalex.org/W1973050578","https://openalex.org/W2005709450","https://openalex.org/W2071638348","https://openalex.org/W2021430990","https://openalex.org/W3035123403","https://openalex.org/W2103450640"],"abstract_inverted_index":{"Traditional":[0],"speech":[1,5,17,26,45,80,130],"enhancement":[2,131],"systems":[3,41,132],"produce":[4],"with":[6,88],"compromised":[7],"quality.":[8],"Here":[9,64],"we":[10,37,65,106],"propose":[11],"to":[12],"use":[13],"the":[14,108,128,144],"high":[15,43],"quality":[16,25,44,90,111,124],"generation":[18],"capability":[19],"of":[20,112],"neural":[21,52],"vocoders":[22,59,77,100],"for":[23,46],"better":[24],"enhancement.":[27],"We":[28],"term":[29],"this":[30],"parametric":[31],"resynthesis":[32],"(PR).":[33],"In":[34],"previous":[35],"work,":[36],"showed":[38],"that":[39,68,119],"PR":[40,113,142],"generate":[42,79],"a":[47,102],"single":[48],"speaker":[49,62],"using":[50,97],"two":[51,99],"vocoders,":[53],"WaveNet":[54],"and":[55,86,101,117,122,135],"WaveGlow.":[56],"Both":[57],"these":[58,76,98],"are":[60],"traditionally":[61],"dependent.":[63],"first":[66],"show":[67,118],"when":[69],"trained":[70],"on":[71,114],"data":[72],"from":[73,81],"enough":[74],"speakers,":[75,83],"can":[78],"unseen":[82,115],"both":[84],"male":[85],"female,":[87],"similar":[89],"as":[91],"seen":[92],"speakers":[93,116],"in":[94,138],"training.":[95],"Next":[96],"new":[103],"vocoder":[104],"LPCNet,":[105],"evaluate":[107],"noise":[109],"reduction":[110],"objective":[120],"signal":[121],"overall":[123],"is":[125],"higher":[126],"than":[127],"state-of-the-art":[129],"Wave-U-Net,":[133],"Wavenet-denoise,":[134],"SEGAN.":[136],"Moreover,":[137],"subjective":[139],"quality,":[140],"multiple-speaker":[141],"out-performs":[143],"oracle":[145],"Wiener":[146],"mask.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}