{"id":"https://openalex.org/W2952220610","doi":"https://doi.org/10.1109/waspaa.2019.8937165","title":"Parametric Resynthesis With Neural Vocoders","display_name":"Parametric Resynthesis With Neural Vocoders","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2952220610","doi":"https://doi.org/10.1109/waspaa.2019.8937165","mag":"2952220610"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa.2019.8937165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1906.06762","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"]},{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soumi Maiti","raw_affiliation_strings":["The Graduate Center, CUNY Computer Science, New York, NY, USA","City University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Graduate Center, CUNY Computer Science, New York, NY, USA","institution_ids":["https://openalex.org/I121847817"]},{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043596676","display_name":"Michael Mandel","orcid":null},"institutions":[{"id":"https://openalex.org/I174216632","display_name":"City University of New York","ror":"https://ror.org/00453a208","country_code":"US","type":"education","lineage":["https://openalex.org/I174216632"]},{"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, NY, USA","City University of New York"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brooklyn College, Computer and Information Science, NY, USA","institution_ids":["https://openalex.org/I83041322"]},{"raw_affiliation_string":"City University of New York","institution_ids":["https://openalex.org/I174216632"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1912,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.33176201,"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":"303","last_page":"307"},"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":0.9994000196456909,"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":0.9980999827384949,"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/spectrogram","display_name":"Spectrogram","score":0.8098841905593872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.719238817691803},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6572198867797852},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6396076679229736},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.5888514518737793},{"id":"https://openalex.org/keywords/oracle","display_name":"Oracle","score":0.5705996155738831},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5625517964363098},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.5070571899414062},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4823881685733795},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4145321846008301},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34491586685180664},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10797250270843506},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10290661454200745}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.8098841905593872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.719238817691803},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6572198867797852},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6396076679229736},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.5888514518737793},{"id":"https://openalex.org/C55166926","wikidata":"https://www.wikidata.org/wiki/Q2892946","display_name":"Oracle","level":2,"score":0.5705996155738831},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5625517964363098},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5070571899414062},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4823881685733795},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4145321846008301},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34491586685180664},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10797250270843506},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10290661454200745},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"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/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/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/waspaa.2019.8937165","is_oa":false,"landing_page_url":"https://doi.org/10.1109/waspaa.2019.8937165","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1906.06762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.06762","pdf_url":"https://arxiv.org/pdf/1906.06762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},{"id":"mag:2952220610","is_oa":true,"landing_page_url":"https://arxiv.org/abs/1906.06762","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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.1906.06762","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1906.06762","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1906.06762","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1906.06762","pdf_url":"https://arxiv.org/pdf/1906.06762","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":"","raw_type":"text"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6899999976158142}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2952220610.pdf","grobid_xml":"https://content.openalex.org/works/W2952220610.grobid-xml"},"referenced_works_count":40,"referenced_works":["https://openalex.org/W1952824372","https://openalex.org/W2064675550","https://openalex.org/W2067295501","https://openalex.org/W2130813098","https://openalex.org/W2289394825","https://openalex.org/W2471520273","https://openalex.org/W2600556233","https://openalex.org/W2604184139","https://openalex.org/W2608207374","https://openalex.org/W2749130229","https://openalex.org/W2749651610","https://openalex.org/W2766812927","https://openalex.org/W2769810959","https://openalex.org/W2777302760","https://openalex.org/W2788851830","https://openalex.org/W2792995953","https://openalex.org/W2889455712","https://openalex.org/W2889517470","https://openalex.org/W2891405874","https://openalex.org/W2898847420","https://openalex.org/W2902132730","https://openalex.org/W2930648092","https://openalex.org/W2949382160","https://openalex.org/W2952917250","https://openalex.org/W2962866211","https://openalex.org/W2963103134","https://openalex.org/W2963139417","https://openalex.org/W2963341071","https://openalex.org/W2963685250","https://openalex.org/W6679369443","https://openalex.org/W6695676441","https://openalex.org/W6736356763","https://openalex.org/W6745697700","https://openalex.org/W6746700228","https://openalex.org/W6748409065","https://openalex.org/W6752910514","https://openalex.org/W6755592152","https://openalex.org/W6756251360","https://openalex.org/W6843673214","https://openalex.org/W6917585676"],"related_works":["https://openalex.org/W2998498479","https://openalex.org/W2995343943","https://openalex.org/W2912237252","https://openalex.org/W3157804362","https://openalex.org/W3023846453","https://openalex.org/W2783185598","https://openalex.org/W2783984851","https://openalex.org/W2155244316","https://openalex.org/W2967086982","https://openalex.org/W2557990606","https://openalex.org/W2787650696","https://openalex.org/W3127397449","https://openalex.org/W1998890473","https://openalex.org/W3197753364","https://openalex.org/W1980741455","https://openalex.org/W2893399179","https://openalex.org/W2797110164","https://openalex.org/W3016109656","https://openalex.org/W2102232231","https://openalex.org/W2237671050"],"abstract_inverted_index":{"Noise":[0],"suppression":[1],"systems":[2],"generally":[3],"produce":[4],"output":[5],"speech":[6,17,38,51],"with":[7],"compromised":[8],"quality.":[9],"We":[10,26],"propose":[11],"to":[12,31],"utilize":[13],"the":[14,53,69,86,100,107],"high":[15],"quality":[16,66,83,103],"generation":[18],"capability":[19],"of":[20,109],"neural":[21,29,43],"vocoders":[22],"for":[23,48],"noise":[24],"suppression.":[25],"use":[27],"a":[28],"network":[30],"predict":[32],"clean":[33,50],"mel-spectrogram":[34],"features":[35],"from":[36,52],"noisy":[37],"and":[39,46,59,64,76,96],"then":[40],"compare":[41],"two":[42],"vocoders,":[44],"WaveNet":[45,58,75,95,98],"WaveGlow,":[47,97],"synthesizing":[49],"predicted":[54],"mel":[55],"spectrogram.":[56],"Both":[57],"WaveGlow":[60,77],"achieve":[61,79],"better":[62,81],"subjective":[63,82,102],"objective":[65],"scores":[67],"than":[68,85],"source":[70],"separation":[71],"model":[72],"Chimera++.":[73],"Further,":[74],"also":[78],"significantly":[80],"ratings":[84],"oracle":[87],"Wiener":[88],"mask.":[89],"Moreover,":[90],"we":[91],"observe":[92],"that":[93],"between":[94],"achieves":[99],"best":[101],"scores,":[104],"although":[105],"at":[106],"cost":[108],"much":[110],"slower":[111],"waveform":[112],"generation.":[113]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
