{"id":"https://openalex.org/W4388727243","doi":"https://doi.org/10.1109/gcce59613.2023.10315264","title":"Non-intrusive Speech Intelligibility Prediction of Speech with Additive Noise and Reverberation Using Multiple Deep Learning-Based Speech Enhancement","display_name":"Non-intrusive Speech Intelligibility Prediction of Speech with Additive Noise and Reverberation Using Multiple Deep Learning-Based Speech Enhancement","publication_year":2023,"publication_date":"2023-10-10","ids":{"openalex":"https://openalex.org/W4388727243","doi":"https://doi.org/10.1109/gcce59613.2023.10315264"},"language":"en","primary_location":{"id":"doi:10.1109/gcce59613.2023.10315264","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce59613.2023.10315264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 12th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5050141594","display_name":"Kazushi Nakazawa","orcid":null},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazushi Nakazawa","raw_affiliation_strings":["Yamagata University,Yonezawa,Japan","Yamagata University, Yonezawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University,Yonezawa,Japan","institution_ids":["https://openalex.org/I112524849"]},{"raw_affiliation_string":"Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054505593","display_name":"Kazuhiro Kondo","orcid":"https://orcid.org/0000-0003-2160-8683"},"institutions":[{"id":"https://openalex.org/I112524849","display_name":"Yamagata University","ror":"https://ror.org/00xy44n04","country_code":"JP","type":"education","lineage":["https://openalex.org/I112524849"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Kondo","raw_affiliation_strings":["Yamagata University,Yonezawa,Japan","Yamagata University, Yonezawa, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yamagata University,Yonezawa,Japan","institution_ids":["https://openalex.org/I112524849"]},{"raw_affiliation_string":"Yamagata University, Yonezawa, Japan","institution_ids":["https://openalex.org/I112524849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I112524849"],"apc_list":null,"apc_paid":null,"fwci":0.2417,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.46942362,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"63","issue":null,"first_page":"918","last_page":"920"},"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":0.9988999962806702,"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/T10822","display_name":"Acoustic Wave Phenomena Research","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/2204","display_name":"Biomedical Engineering"},"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":0.8931075930595398},{"id":"https://openalex.org/keywords/reverberation","display_name":"Reverberation","score":0.8086735010147095},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7823954820632935},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6228265762329102},{"id":"https://openalex.org/keywords/speech-enhancement","display_name":"Speech enhancement","score":0.6056318283081055},{"id":"https://openalex.org/keywords/correlation","display_name":"Correlation","score":0.44560280442237854},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.4382028579711914},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.29691797494888306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2814919948577881},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24081280827522278},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.2048596441745758},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.05620136857032776}],"concepts":[{"id":"https://openalex.org/C60048801","wikidata":"https://www.wikidata.org/wiki/Q1433889","display_name":"Intelligibility (philosophy)","level":2,"score":0.8931075930595398},{"id":"https://openalex.org/C95851461","wikidata":"https://www.wikidata.org/wiki/Q468809","display_name":"Reverberation","level":2,"score":0.8086735010147095},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7823954820632935},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6228265762329102},{"id":"https://openalex.org/C2776182073","wikidata":"https://www.wikidata.org/wiki/Q7575395","display_name":"Speech enhancement","level":3,"score":0.6056318283081055},{"id":"https://openalex.org/C117220453","wikidata":"https://www.wikidata.org/wiki/Q5172842","display_name":"Correlation","level":2,"score":0.44560280442237854},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.4382028579711914},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.29691797494888306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2814919948577881},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24081280827522278},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.2048596441745758},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.05620136857032776},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce59613.2023.10315264","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce59613.2023.10315264","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE 12th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6299999952316284,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2125114513","https://openalex.org/W2334976295","https://openalex.org/W2602577565","https://openalex.org/W2952218014","https://openalex.org/W3099330747","https://openalex.org/W3151851237","https://openalex.org/W3167533889","https://openalex.org/W3197912330","https://openalex.org/W4312096595","https://openalex.org/W4385411334","https://openalex.org/W6887998241"],"related_works":["https://openalex.org/W1986772939","https://openalex.org/W2037635165","https://openalex.org/W2738829087","https://openalex.org/W2542062716","https://openalex.org/W1505346162","https://openalex.org/W4200562864","https://openalex.org/W2120771489","https://openalex.org/W2051376034","https://openalex.org/W2955597484","https://openalex.org/W3110551121"],"abstract_inverted_index":{"In":[0,23],"the":[1,40,52,72],"field":[2],"of":[3,54,91],"non-intrusive":[4],"speech":[5,15,32,69],"intelligibility":[6,28],"estimation,":[7],"we":[8,26,82],"have":[9],"proposed":[10],"a":[11,36,65,78,87],"model":[12],"that":[13,42],"uses":[14],"enhancement":[16],"as":[17,59],"an":[18],"auxiliary":[19],"signal":[20],"for":[21,48,93],"prediction.":[22],"this":[24],"study,":[25],"performed":[27],"estimation":[29,73],"using":[30,67,77],"multiple":[31,44,68],"enhancers,":[33],"not":[34],"just":[35],"single":[37,79],"one,":[38],"with":[39],"expectation":[41],"combining":[43],"enhancers":[45,70],"would":[46],"allow":[47],"error":[49],"interpolation":[50],"in":[51],"presence":[53],"various":[55],"degradation":[56],"factors":[57],"such":[58],"additive":[60],"noise":[61],"and":[62,81],"reverberation.":[63],"As":[64],"result,":[66],"improved":[71],"accuracy":[74],"compared":[75],"to":[76,85],"model,":[80],"were":[83],"able":[84],"achieve":[86],"maximum":[88],"correlation":[89],"coefficient":[90],"0.674":[92],"estimation.":[94]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}