{"id":"https://openalex.org/W4388145608","doi":"https://doi.org/10.1109/taslp.2023.3329378","title":"On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks","display_name":"On the Predictive Power of Objective Intelligibility Metrics for the Subjective Performance of Deep Complex Convolutional Recurrent Speech Enhancement Networks","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W4388145608","doi":"https://doi.org/10.1109/taslp.2023.3329378"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3329378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3329378","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","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/A5023774362","display_name":"Femke B. Gelderblom","orcid":"https://orcid.org/0000-0002-1034-4427"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]},{"id":"https://openalex.org/I4210163605","display_name":"Acoustics (Norway)","ror":"https://ror.org/05mxqzt83","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210163605"]},{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]},{"id":"https://openalex.org/I4387930215","display_name":"SINTEF Digital","ror":"https://ror.org/028m52w57","country_code":null,"type":"facility","lineage":["https://openalex.org/I173888879","https://openalex.org/I4387930215"]}],"countries":["NO"],"is_corresponding":true,"raw_author_name":"Femke B. Gelderblom","raw_affiliation_strings":["Acoustics group, Department of Sustainable Communication Technologies, SINTEF Digital, Trondheim, Norway","Signal Processing Group, Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Acoustics group, Department of Sustainable Communication Technologies, SINTEF Digital, Trondheim, Norway","institution_ids":["https://openalex.org/I173888879","https://openalex.org/I4210163605","https://openalex.org/I4387930215"]},{"raw_affiliation_string":"Signal Processing Group, Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071280038","display_name":"Tron Vedul Tronstad","orcid":"https://orcid.org/0000-0002-3329-7109"},"institutions":[{"id":"https://openalex.org/I4210163605","display_name":"Acoustics (Norway)","ror":"https://ror.org/05mxqzt83","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210163605"]},{"id":"https://openalex.org/I173888879","display_name":"SINTEF","ror":"https://ror.org/01f677e56","country_code":"NO","type":"facility","lineage":["https://openalex.org/I173888879"]},{"id":"https://openalex.org/I4387930215","display_name":"SINTEF Digital","ror":"https://ror.org/028m52w57","country_code":null,"type":"facility","lineage":["https://openalex.org/I173888879","https://openalex.org/I4387930215"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Tron Vedul Tronstad","raw_affiliation_strings":["Acoustics group, Department of Sustainable Communication Technologies, SINTEF Digital, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Acoustics group, Department of Sustainable Communication Technologies, SINTEF Digital, Trondheim, Norway","institution_ids":["https://openalex.org/I173888879","https://openalex.org/I4210163605","https://openalex.org/I4387930215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055323428","display_name":"Torbj\u00f8rn Svendsen","orcid":"https://orcid.org/0000-0003-0578-7941"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Torbj\u00f8rn Svendsen","raw_affiliation_strings":["Signal Processing Group, Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064171039","display_name":"Tor Andr\u00e9 Myrvoll","orcid":"https://orcid.org/0000-0001-6286-9148"},"institutions":[{"id":"https://openalex.org/I204778367","display_name":"Norwegian University of Science and Technology","ror":"https://ror.org/05xg72x27","country_code":"NO","type":"education","lineage":["https://openalex.org/I204778367"]}],"countries":["NO"],"is_corresponding":false,"raw_author_name":"Tor Andre Myrvoll","raw_affiliation_strings":["Signal Processing Group, Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway"],"affiliations":[{"raw_affiliation_string":"Signal Processing Group, Department of Electronic Systems, Norwegian University of Science and Technology, Trondheim, Norway","institution_ids":["https://openalex.org/I204778367"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5023774362"],"corresponding_institution_ids":["https://openalex.org/I173888879","https://openalex.org/I204778367","https://openalex.org/I4210163605","https://openalex.org/I4387930215"],"apc_list":null,"apc_paid":null,"fwci":1.4473,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.83141664,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"215","last_page":"226"},"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/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9994000196456909,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11233","display_name":"Advanced Adaptive Filtering Techniques","score":0.9973000288009644,"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/intelligibility","display_name":"Intelligibility (philosophy)","score":0.9114652872085571},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6857302188873291},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6637861728668213},{"id":"https://openalex.org/keywords/predictive-power","display_name":"Predictive power","score":0.6386759281158447},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46873506903648376},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.4281143248081207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3202434778213501},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.1194712221622467}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.9114652872085571},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6857302188873291},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6637861728668213},{"id":"https://openalex.org/C2778136018","wikidata":"https://www.wikidata.org/wiki/Q10350689","display_name":"Predictive power","level":2,"score":0.6386759281158447},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46873506903648376},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.4281143248081207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3202434778213501},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.1194712221622467},{"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/taslp.2023.3329378","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3329378","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W626405604","https://openalex.org/W653761051","https://openalex.org/W1552314771","https://openalex.org/W1582976041","https://openalex.org/W1649817501","https://openalex.org/W1893876709","https://openalex.org/W1985029311","https://openalex.org/W1985226152","https://openalex.org/W1998648683","https://openalex.org/W2057200980","https://openalex.org/W2063669828","https://openalex.org/W2067295501","https://openalex.org/W2080405943","https://openalex.org/W2086300622","https://openalex.org/W2092644348","https://openalex.org/W2114863372","https://openalex.org/W2141998673","https://openalex.org/W2153038597","https://openalex.org/W2164502538","https://openalex.org/W2364134690","https://openalex.org/W2516001803","https://openalex.org/W2599571402","https://openalex.org/W2745616330","https://openalex.org/W2750452568","https://openalex.org/W2804382237","https://openalex.org/W2809874909","https://openalex.org/W2819912438","https://openalex.org/W2893969570","https://openalex.org/W2901212597","https://openalex.org/W3016070314","https://openalex.org/W3032727804","https://openalex.org/W3045520545","https://openalex.org/W3095057960","https://openalex.org/W3096408984","https://openalex.org/W3097312999","https://openalex.org/W3103318788","https://openalex.org/W3160085755","https://openalex.org/W3160878746","https://openalex.org/W3161140524","https://openalex.org/W3161761462","https://openalex.org/W3162188526","https://openalex.org/W3163464523","https://openalex.org/W3166682767","https://openalex.org/W3196601925","https://openalex.org/W3196888558","https://openalex.org/W3196953047","https://openalex.org/W3197042120","https://openalex.org/W3197260772","https://openalex.org/W3197627016","https://openalex.org/W3198130028","https://openalex.org/W3201729870","https://openalex.org/W3203948062","https://openalex.org/W3214469553","https://openalex.org/W3217000580","https://openalex.org/W4241867481","https://openalex.org/W4253928870","https://openalex.org/W4311167834","https://openalex.org/W4312793361","https://openalex.org/W4366607133","https://openalex.org/W6619986412","https://openalex.org/W6772622344"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2127461790","https://openalex.org/W2069324367","https://openalex.org/W2542062716","https://openalex.org/W3096184950","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W4231424160"],"abstract_inverted_index":{"Speech":[0],"enhancement":[1,132],"(SE)":[2],"systems":[3,28,84],"aim":[4],"to":[5,39,54,73],"improve":[6,55],"the":[7,22,56,68,93,102,139,149],"quality":[8],"and":[9,116,122,144],"intelligibility":[10,23,33,57,76,150],"of":[11,21,25,58,67,70,96,138,151],"degraded":[12,59],"speech":[13,60,80,131,153],"signals":[14],"obtained":[15],"from":[16],"far-field":[17],"microphones.":[18],"Subjective":[19],"evaluation":[20],"performance":[24,42,95],"these":[26,71],"SE":[27,50],"is":[29,85],"uncommon.":[30],"Instead,":[31],"objective":[32],"measures":[34],"(OIMs)":[35],"are":[36,52],"generally":[37],"used":[38],"predict":[40,74],"subjective":[41,75,106],"increases.":[43],"Many":[44],"recent":[45],"deep":[46],"learning":[47],"(DL)":[48],"based":[49,130],"systems,":[51],"expected":[53],"as":[61],"measured":[62],"by":[63],"OIMs.":[64,99],"However,":[65],"validation":[66],"ability":[69],"OIMs":[72,140,147],"when":[77],"enhancing":[78],"a":[79],"signal":[81],"using":[82],"DL-based":[83],"lacking.":[86],"Therefore,":[87],"in":[88],"this":[89,109],"study,":[90],"we":[91,111],"evaluate":[92],"predictive":[94],"five":[97],"popular":[98],"We":[100,134],"compare":[101],"metrics'":[103],"predictions":[104],"with":[105],"results.":[107],"For":[108],"purpose,":[110],"recruited":[112],"50":[113],"human":[114],"listeners,":[115],"subjectively":[117],"tested":[118],"both":[119],"single":[120],"channel":[121],"multi-channel":[123],"Deep":[124],"Complex":[125],"Convolutional":[126],"Recurrent":[127],"Network":[128],"(DCCRN)":[129],"systems.":[133],"found":[135],"that":[136,145],"none":[137],"gave":[141],"reliable":[142],"predictions,":[143],"all":[146],"overestimated":[148],"\u2018enhanced\u2019":[152],"signals.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}