{"id":"https://openalex.org/W4384557786","doi":"https://doi.org/10.3390/s23146438","title":"Investigations on the Optimal Estimation of Speech Envelopes for the Two-Stage Speech Enhancement","display_name":"Investigations on the Optimal Estimation of Speech Envelopes for the Two-Stage Speech Enhancement","publication_year":2023,"publication_date":"2023-07-16","ids":{"openalex":"https://openalex.org/W4384557786","doi":"https://doi.org/10.3390/s23146438","pmid":"https://pubmed.ncbi.nlm.nih.gov/37514732"},"language":"en","primary_location":{"id":"doi:10.3390/s23146438","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23146438","pdf_url":"https://www.mdpi.com/1424-8220/23/14/6438/pdf?version=1689577471","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1424-8220/23/14/6438/pdf?version=1689577471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007667052","display_name":"Yanjue Song","orcid":"https://orcid.org/0000-0002-9684-6611"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Yanjue Song","raw_affiliation_strings":["IDLab, Ghent University\u2014imec, 9000 Gent, Belgium"],"raw_orcid":"https://orcid.org/0000-0002-9684-6611","affiliations":[{"raw_affiliation_string":"IDLab, Ghent University\u2014imec, 9000 Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081844255","display_name":"Nilesh Madhu","orcid":"https://orcid.org/0000-0001-9131-3309"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Nilesh Madhu","raw_affiliation_strings":["IDLab, Ghent University\u2014imec, 9000 Gent, Belgium"],"raw_orcid":"https://orcid.org/0000-0001-9131-3309","affiliations":[{"raw_affiliation_string":"IDLab, Ghent University\u2014imec, 9000 Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007667052"],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":{"value":2400,"currency":"CHF","value_usd":2673},"apc_paid":{"value":2400,"currency":"CHF","value_usd":2673},"fwci":0.133,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38055487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"23","issue":"14","first_page":"6438","last_page":"6438"},"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":0.9987000226974487,"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":0.9984999895095825,"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/codebook","display_name":"Codebook","score":0.8659015893936157},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7048347592353821},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6939971446990967},{"id":"https://openalex.org/keywords/intelligibility","display_name":"Intelligibility (philosophy)","score":0.6433303952217102},{"id":"https://openalex.org/keywords/envelope","display_name":"Envelope (radar)","score":0.49758079648017883},{"id":"https://openalex.org/keywords/linear-predictive-coding","display_name":"Linear predictive coding","score":0.4605063796043396},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4557270109653473},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.4332980215549469},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4276352524757385},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.3814677596092224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33579039573669434},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3339093029499054}],"concepts":[{"id":"https://openalex.org/C127759330","wikidata":"https://www.wikidata.org/wiki/Q637416","display_name":"Codebook","level":2,"score":0.8659015893936157},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7048347592353821},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6939971446990967},{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.6433303952217102},{"id":"https://openalex.org/C65155139","wikidata":"https://www.wikidata.org/wiki/Q5380912","display_name":"Envelope (radar)","level":3,"score":0.49758079648017883},{"id":"https://openalex.org/C59883199","wikidata":"https://www.wikidata.org/wiki/Q1826438","display_name":"Linear predictive coding","level":3,"score":0.4605063796043396},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4557270109653473},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.4332980215549469},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4276352524757385},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3814677596092224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33579039573669434},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3339093029499054},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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":[{"descriptor_ui":"D003071","descriptor_name":"Cognition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003071","descriptor_name":"Cognition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003071","descriptor_name":"Cognition","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009622","descriptor_name":"Noise","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013060","descriptor_name":"Speech","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D013067","descriptor_name":"Speech Perception","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":6,"locations":[{"id":"doi:10.3390/s23146438","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23146438","pdf_url":"https://www.mdpi.com/1424-8220/23/14/6438/pdf?version=1689577471","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},{"id":"pmid:37514732","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37514732","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors (Basel, Switzerland)","raw_type":null},{"id":"pmh:oai:archive.ugent.be:01H9MV475WRVWV0KXZH3XNP7V7","is_oa":true,"landing_page_url":"https://biblio.ugent.be/publication/01H9MV475WRVWV0KXZH3XNP7V7","pdf_url":"https://biblio.ugent.be/publication/01H9MV475WRVWV0KXZH3XNP7V7/file/01H9MV54CNV2G936SXH1E6DBFT.pdf","source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1424-8220","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:pubmedcentral.nih.gov:10384514","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/10384514","pdf_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC10384514/pdf/sensors-23-06438.pdf","source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors (Basel)","raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:0e3c7e9a2a144e03b78772217666f4a8","is_oa":true,"landing_page_url":"https://doaj.org/article/0e3c7e9a2a144e03b78772217666f4a8","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors, Vol 23, Iss 14, p 6438 (2023)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/1424-8220/23/14/6438/","is_oa":true,"landing_page_url":"https://dx.doi.org/10.3390/s23146438","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Sensors; Volume 23; Issue 14; Pages: 6438","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/s23146438","is_oa":true,"landing_page_url":"https://doi.org/10.3390/s23146438","pdf_url":"https://www.mdpi.com/1424-8220/23/14/6438/pdf?version=1689577471","source":{"id":"https://openalex.org/S101949793","display_name":"Sensors","issn_l":"1424-8220","issn":["1424-8220"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sensors","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8199999928474426,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4384557786.pdf","grobid_xml":"https://content.openalex.org/works/W4384557786.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1966264494","https://openalex.org/W1976876353","https://openalex.org/W2012241238","https://openalex.org/W2025515167","https://openalex.org/W2035859817","https://openalex.org/W2051428568","https://openalex.org/W2067295501","https://openalex.org/W2091270830","https://openalex.org/W2121973264","https://openalex.org/W2134383396","https://openalex.org/W2135248248","https://openalex.org/W2144561273","https://openalex.org/W2164715564","https://openalex.org/W2560824463","https://openalex.org/W2612685246","https://openalex.org/W2889273017","https://openalex.org/W2963351212","https://openalex.org/W2972777526","https://openalex.org/W3095248373","https://openalex.org/W3147539069","https://openalex.org/W3160129476","https://openalex.org/W3176969530","https://openalex.org/W4214498238","https://openalex.org/W4285186686","https://openalex.org/W4375869327"],"related_works":["https://openalex.org/W2171564668","https://openalex.org/W2110375858","https://openalex.org/W2365863649","https://openalex.org/W2367622526","https://openalex.org/W1986772939","https://openalex.org/W2372081722","https://openalex.org/W2014919663","https://openalex.org/W3211091508","https://openalex.org/W1586537451","https://openalex.org/W4252671892"],"abstract_inverted_index":{"Using":[0],"the":[1,25,31,41,48,75,100,109,116,128,142,153,179,193,217,251,261,273,276,279,287,304],"source-filter":[2],"model":[3],"of":[4,33,45,50,67,77,165,240,250,278,312],"speech":[5,8,35,37,54,78,102,187,199,313],"production,":[6],"clean":[7],"signals":[9],"can":[10,39,58,70,258],"be":[11,59,71],"decomposed":[12],"into":[13],"an":[14,18],"excitation":[15],"component":[16,20],"and":[17,43,159,200,238,253,314],"envelope":[19,32,122,130,144,157,174],"that":[21,170,184,196,226,245],"is":[22,55,123,189,282],"related":[23],"to":[24,73,98,177,192,212,216,293],"phoneme":[26],"being":[27],"uttered.":[28],"Therefore,":[29],"restoring":[30],"degraded":[34,82,129,143,214],"during":[36],"enhancement":[38],"improve":[40,74,260],"intelligibility":[42],"quality":[44],"output.":[46],"As":[47],"number":[49,66,239],"phonemes":[51],"in":[52,84,94,221,298],"spoken":[53],"limited,":[56],"they":[57],"adequately":[60],"represented":[61],"by":[62,126,137,162,286],"a":[63,81,85,95,163,185,235,247,255,264,295],"correspondingly":[64],"limited":[65,285,296],"envelopes.":[68],"This":[69,302],"exploited":[72],"estimation":[76,311],"envelopes":[79,90,215],"from":[80,108,115,141,272],"signal":[83],"data-driven":[86],"manner.":[87],"The":[88,120],"improved":[89,121],"are":[91,105],"then":[92],"used":[93],"second":[96],"stage":[97],"refine":[99],"final":[101],"estimate.":[103],"Envelopes":[104],"typically":[106],"derived":[107],"linear":[110],"prediction":[111],"coefficients":[112,118],"(LPCs)":[113],"or":[114,136],"cepstral":[117],"(CCs).":[119],"obtained":[124],"either":[125],"mapping":[127],"onto":[131],"pre-trained":[132],"codebooks":[133],"(classification":[134],"approach)":[135],"directly":[138],"estimating":[139],"it":[140],"(regression":[145],"approach).":[146],"In":[147],"this":[148],"work,":[149],"we":[150,182,206],"first":[151],"investigate":[152,207],"optimal":[154,218],"features":[155],"for":[156,306,316],"representation":[158,175],"codebook":[160,188,195,219],"generation":[161],"series":[164],"oracle":[166,274],"tests.":[167],"We":[168,224,242],"demonstrate":[169,183,244],"CCs":[171],"provide":[172],"better":[173],"compared":[176,191],"using":[178],"LPCs.":[180],"Further,":[181],"unified":[186],"advantageous":[190],"typical":[194],"manually":[197],"splits":[198],"silence":[201],"as":[202,269],"separate":[203],"entries.":[204],"Next,":[205],"low-complexity":[208],"neural":[209,229],"network":[210],"architectures":[211],"map":[213],"entry":[220],"practical":[222],"systems.":[223],"confirm":[225],"simple":[227],"recurrent":[228],"networks":[230],"yield":[231],"good":[232],"performance":[233,262],"with":[234,246],"low":[236],"complexity":[237],"parameters.":[241],"also":[243,270],"careful":[248],"choice":[249],"feature":[252],"architecture,":[254],"regression":[256],"approach":[257],"further":[259,307],"at":[263],"lower":[265],"computational":[266],"cost.":[267],"However,":[268],"seen":[271],"tests,":[275],"benefit":[277],"two-stage":[280],"framework":[281],"now":[283],"chiefly":[284],"statistical":[288],"noise":[289,315],"floor":[290],"estimate,":[291],"leading":[292],"only":[294],"improvement":[297],"extremely":[299],"adverse":[300],"conditions.":[301],"highlights":[303],"need":[305],"research":[308],"on":[309],"joint":[310],"optimum":[317],"enhancement.":[318]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}