{"id":"https://openalex.org/W4211015359","doi":"https://doi.org/10.1109/access.2022.3150728","title":"Differentiable Measures for Speech Spectral Modeling","display_name":"Differentiable Measures for Speech Spectral Modeling","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4211015359","doi":"https://doi.org/10.1109/access.2022.3150728"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3150728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3150728","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09709279.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09709279.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021252790","display_name":"Miguel Arjona Ram\u00edrez","orcid":"https://orcid.org/0000-0002-7107-0888"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Miguel Arjona Ramirez","raw_affiliation_strings":["Department of Electronic Systems Engineering, Polytechnic School of the University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-7107-0888","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems Engineering, Polytechnic School of the University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024992483","display_name":"Wesley Beccaro","orcid":"https://orcid.org/0000-0001-6599-2344"},"institutions":[{"id":"https://openalex.org/I17974374","display_name":"Universidade de S\u00e3o Paulo","ror":"https://ror.org/036rp1748","country_code":"BR","type":"education","lineage":["https://openalex.org/I17974374"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Wesley Beccaro","raw_affiliation_strings":["Department of Electronic Systems Engineering, Polytechnic School of the University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-6599-2344","affiliations":[{"raw_affiliation_string":"Department of Electronic Systems Engineering, Polytechnic School of the University of S\u00e3o Paulo, S\u00e3o Paulo, Brazil","institution_ids":["https://openalex.org/I17974374"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063050171","display_name":"Dem\u00f3stenes Zegarra Rodr\u00edguez","orcid":"https://orcid.org/0000-0001-5401-7551"},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Demostenes Zegarra Rodriguez","raw_affiliation_strings":["Department of Computer Science, Federal University of Lavras, Lavras, Brazil"],"raw_orcid":"https://orcid.org/0000-0001-5401-7551","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Lavras, Lavras, Brazil","institution_ids":["https://openalex.org/I1315085146"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054066072","display_name":"Renata Lopes Rosa","orcid":"https://orcid.org/0000-0002-7595-7187"},"institutions":[{"id":"https://openalex.org/I1315085146","display_name":"Universidade Federal de Lavras","ror":"https://ror.org/0122bmm03","country_code":"BR","type":"education","lineage":["https://openalex.org/I1315085146"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Renata Lopes Rosa","raw_affiliation_strings":["Department of Computer Science, Federal University of Lavras, Lavras, Brazil"],"raw_orcid":"https://orcid.org/0000-0002-7595-7187","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Federal University of Lavras, Lavras, Brazil","institution_ids":["https://openalex.org/I1315085146"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2326,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.40611408,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"17609","last_page":"17618"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9990000128746033,"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":0.9990000128746033,"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/T10534","display_name":"Structural Health Monitoring Techniques","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11447","display_name":"Blind Source Separation Techniques","score":0.9962999820709229,"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/pesq","display_name":"PESQ","score":0.9214212894439697},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7725931406021118},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.6308919191360474},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6003046035766602},{"id":"https://openalex.org/keywords/spectral-envelope","display_name":"Spectral envelope","score":0.514239490032196},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.4871794581413269},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.48119932413101196},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.42622411251068115},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3995029926300049},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37997540831565857},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.36500102281570435},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.27894335985183716},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.17485728859901428},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.16535696387290955},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.10198974609375}],"concepts":[{"id":"https://openalex.org/C103734657","wikidata":"https://www.wikidata.org/wiki/Q2739975","display_name":"PESQ","level":4,"score":0.9214212894439697},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7725931406021118},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6308919191360474},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6003046035766602},{"id":"https://openalex.org/C54926389","wikidata":"https://www.wikidata.org/wiki/Q7575188","display_name":"Spectral envelope","level":2,"score":0.514239490032196},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.4871794581413269},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.48119932413101196},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.42622411251068115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3995029926300049},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37997540831565857},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.36500102281570435},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.27894335985183716},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.17485728859901428},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.16535696387290955},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.10198974609375},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2022.3150728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3150728","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09709279.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:repositorio.ufla.br:1/50638","is_oa":true,"landing_page_url":"https://repositorio.ufla.br/handle/1/50638","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"instacron:UFLA","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:003074363","is_oa":true,"landing_page_url":"https://doi.org/10.1109/ACCESS.2022.3150728","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"reponame:Reposit\u00f3rio Institucional da USP (Biblioteca Digital da Produ\u00e7\u00e3o Intelectual)","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:doaj.org/article:941a1102ba7346b591135894f3631dad","is_oa":true,"landing_page_url":"https://doaj.org/article/941a1102ba7346b591135894f3631dad","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":"IEEE Access, Vol 10, Pp 17609-17618 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3150728","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3150728","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9668973/09709279.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6600000262260437,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G295657101","display_name":null,"funder_award_id":"2019/","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G497127911","display_name":"Center for Artificial Intelligence","funder_award_id":"19/07665-4","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"},{"id":"https://openalex.org/G7880187886","display_name":"Audio-Visual Speech Processing by Machine Learning","funder_award_id":"18/26455-8","funder_id":"https://openalex.org/F4320320997","funder_display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo"}],"funders":[{"id":"https://openalex.org/F4320320997","display_name":"Funda\u00e7\u00e3o de Amparo \u00e0 Pesquisa do Estado de S\u00e3o Paulo","ror":"https://ror.org/02ddkpn78"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4211015359.pdf","grobid_xml":"https://content.openalex.org/works/W4211015359.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W1501095260","https://openalex.org/W1552314771","https://openalex.org/W1558044293","https://openalex.org/W1728888090","https://openalex.org/W2020024436","https://openalex.org/W2022554507","https://openalex.org/W2048916503","https://openalex.org/W2096765209","https://openalex.org/W2108429076","https://openalex.org/W2114352222","https://openalex.org/W2137089646","https://openalex.org/W2209071687","https://openalex.org/W2761952131","https://openalex.org/W2771756038","https://openalex.org/W2783657448","https://openalex.org/W2805225436","https://openalex.org/W2959133507","https://openalex.org/W3013185341","https://openalex.org/W3016011332","https://openalex.org/W3032514799","https://openalex.org/W3094594436","https://openalex.org/W3097412542","https://openalex.org/W3109302118","https://openalex.org/W3165891254","https://openalex.org/W3196593883","https://openalex.org/W3197590976","https://openalex.org/W4212863985"],"related_works":["https://openalex.org/W3118578380","https://openalex.org/W4294326507","https://openalex.org/W2144085034","https://openalex.org/W2166153901","https://openalex.org/W2100095452","https://openalex.org/W4309426801","https://openalex.org/W2400169245","https://openalex.org/W1990055248","https://openalex.org/W4375933195","https://openalex.org/W1965576734"],"abstract_inverted_index":{"Autoregressive":[0],"models":[1,56,88,103,128,158,237,241,281],"for":[2,152,183,225,282,290,314],"the":[3,14,27,31,35,40,55,72,78,86,94,99,110,131,144,149,153,156,160,171,179,188,194,201,211,214,217,222,226,235,239,248,258,261,276,283,291,301],"envelope":[4,286],"of":[5,85,113,127,155,167,260,287,293],"speech":[6,114,288,319],"power":[7],"spectral":[8,16,23,42,87,157,172,249,285],"densities":[9],"(PSDs)":[10],"are":[11,89,122,229,252],"refined":[12],"by":[13,82,109,203,242],"self-supervised":[15],"learning":[17,277],"machine":[18,278],"(S3LM)":[19],"provided":[20],"with":[21,159,192,208,318],"differentiable":[22,298],"objective":[24,132],"functions,":[25,300],"including":[26],"Itakura-Saito":[28],"divergence":[29,33,119],"(ISD),":[30],"Kullback-Leibler":[32],"(KLD),":[34],"reverse":[36],"KLD":[37,215],"(RKLD)":[38],"and":[39,101,117,176,206,216,232,234,321],"log":[41],"distortion":[43],"(LSD),":[44],"which":[45,121],"display":[46],"more":[47,57],"significant":[48],"results.":[49],"However,":[50],"in":[51,104],"order":[52,105],"to":[53,106,139,199,210,255,266,270],"assess":[54],"perceptually,":[58],"a":[59,125,140],"method":[60],"is":[61,146,174,197,264],"proposed":[62],"based":[63],"upon":[64],"perturbations":[65],"around":[66],"perfect":[67],"reconstruction":[68],"analysis-synthesis":[69,74],"configurations.":[70],"In":[71,274,308],"cross-excitation":[73],"assessment":[75,303],"(CEASA)":[76],"method,":[77],"residual":[79],"signals":[80],"generated":[81],"analysis":[83,320],"filters":[84,96],"injected":[90],"as":[91,148,178],"excitation":[92],"into":[93],"synthesis":[95],"derived":[97],"from":[98],"same":[100],"other":[102,315],"be":[107,312],"evaluated":[108],"perceptual":[111],"evaluation":[112,292],"quality":[115],"(PESQ)":[116],"Itakura":[118],"(ID),":[120],"averaged":[123],"over":[124],"set":[126],"obtained":[129,191],"using":[130,187],"functions":[133],"mentioned":[134],"above.":[135],"The":[136,165],"results":[137],"lead":[138],"superior":[141],"performance":[142,202,295],"when":[143],"RKLD":[145,195,236],"used":[147,313],"loss":[150,196,228,299],"function":[151],"estimation":[154],"ISD":[161,227,240],"ranking":[162],"close":[163],"behind.":[164],"focus":[166],"these":[168],"divergences":[169],"on":[170,244],"peaks":[173],"argued":[175],"pointed":[177],"most":[180],"important":[181],"factor":[182],"this":[184],"behavior.":[185],"Specifically,":[186],"PESQ":[189],"scores":[190],"CEASA,":[193],"found":[198],"improve":[200],"1.0%,":[204],"4.0%":[205],"19.3%":[207],"respect":[209],"open-loop":[212],"analysis,":[213],"LSD":[218],"models,":[219],"respectively,":[220],"while":[221],"corresponding":[223],"improvements":[224],"0.1%,":[230],"3.0%":[231],"18.2%,":[233],"excel":[238],"1.0%":[243],"average.":[245],"Even":[246],"though":[247],"measures":[250],"alone":[251],"not":[253],"able":[254],"unequivocally":[256],"distinguish":[257,271],"better":[259],"two,":[262],"CEASA":[263,302,310],"shown":[265],"have":[267],"enough":[268],"sensitivity":[269],"their":[272],"performances.":[273],"summary,":[275],"S3LM":[279],"fits":[280],"short-term":[284],"and,":[289],"its":[294],"under":[296],"several":[297],"tool":[304],"has":[305],"been":[306],"developed.":[307],"addition,":[309],"may":[311],"assessments":[316],"connected":[317],"synthesis.":[322]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2022-02-13T00:00:00"}