{"id":"https://openalex.org/W4385151928","doi":"https://doi.org/10.1109/taslp.2023.3297961","title":"Improvement of Accent Classification Models Through Grad-Transfer From Spectrograms and Gradient-Weighted Class Activation Mapping","display_name":"Improvement of Accent Classification Models Through Grad-Transfer From Spectrograms and Gradient-Weighted Class Activation Mapping","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4385151928","doi":"https://doi.org/10.1109/taslp.2023.3297961"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2023.3297961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3297961","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":true,"oa_status":"green","oa_url":"https://buleria.unileon.es/bitstream/10612/23238/1/Improvement_Accent_Classification_Models_Grad-Transfer.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000784556","display_name":"Andr\u00e9s Carofilis","orcid":"https://orcid.org/0000-0001-9446-0152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andr\u00e9s Carofilis","raw_affiliation_strings":["Department of Electrical, Electronics and System Engineering, Universidad de León, León, Spain"],"raw_orcid":"https://orcid.org/0000-0001-9446-0152","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronics and System Engineering, Universidad de León, León, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020546469","display_name":"Enrique Alegre","orcid":"https://orcid.org/0000-0003-2081-774X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Enrique Alegre","raw_affiliation_strings":["Department of Electrical, Electronics and System Engineering, Universidad de León, León, Spain"],"raw_orcid":"https://orcid.org/0000-0003-2081-774X","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronics and System Engineering, Universidad de León, León, Spain","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034818449","display_name":"Eduardo Fidalgo","orcid":"https://orcid.org/0000-0003-1202-5232"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eduardo Fidalgo","raw_affiliation_strings":["Department of Electrical, Electronics and System Engineering, Universidad de León, León, Spain"],"raw_orcid":"https://orcid.org/0000-0003-1202-5232","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronics and System Engineering, Universidad de León, León, Spain","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014935641","display_name":"Laura Fern\u00e1ndez-Robles","orcid":"https://orcid.org/0000-0001-6573-8477"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura Fern\u00e1ndez-Robles","raw_affiliation_strings":["Department of Mechanical, Informatics and Aeroespace Engineering, Universidad de León, León, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6573-8477","affiliations":[{"raw_affiliation_string":"Department of Mechanical, Informatics and Aeroespace Engineering, Universidad de León, León, Spain","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.2603,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88767493,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"31","issue":null,"first_page":"2859","last_page":"2871"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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/T11309","display_name":"Music and Audio Processing","score":0.9998999834060669,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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":0.6084577441215515},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5883293151855469},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.5466575622558594},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.522742748260498},{"id":"https://openalex.org/keywords/stress","display_name":"Stress (linguistics)","score":0.5093048810958862},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4807686507701874},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.462943434715271},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.46143078804016113},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4452979564666748},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44315749406814575},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.43071550130844116},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3645484447479248},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.09277912974357605}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.6084577441215515},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5883293151855469},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.5466575622558594},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.522742748260498},{"id":"https://openalex.org/C2776756274","wikidata":"https://www.wikidata.org/wiki/Q181767","display_name":"Stress (linguistics)","level":2,"score":0.5093048810958862},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4807686507701874},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.462943434715271},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.46143078804016113},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4452979564666748},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44315749406814575},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.43071550130844116},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3645484447479248},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.09277912974357605}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/taslp.2023.3297961","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2023.3297961","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"},{"id":"pmh:oai:buleria.unileon.es:10612/23238","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10190103","pdf_url":"https://buleria.unileon.es/bitstream/10612/23238/1/Improvement_Accent_Classification_Models_Grad-Transfer.pdf","source":{"id":"https://openalex.org/S4306401642","display_name":"Buleria (Universidad de Le\u00f3n)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169046204","host_organization_name":"Universidad Aut\u00f3noma de Nuevo Le\u00f3n","host_organization_lineage":["https://openalex.org/I169046204"],"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":null,"raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:zenodo.org:10130430","is_oa":true,"landing_page_url":"https://doi.org/10.1109/TASLP.2023.3297961","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"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":"IEEE/ACM Transactions on Audio, Speech, and Language Processing, 31, 2859 - 2871, (2023-07-21)","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:buleria.unileon.es:10612/23238","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10190103","pdf_url":"https://buleria.unileon.es/bitstream/10612/23238/1/Improvement_Accent_Classification_Models_Grad-Transfer.pdf","source":{"id":"https://openalex.org/S4306401642","display_name":"Buleria (Universidad de Le\u00f3n)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169046204","host_organization_name":"Universidad Aut\u00f3noma de Nuevo Le\u00f3n","host_organization_lineage":["https://openalex.org/I169046204"],"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":null,"raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[{"score":0.5899999737739563,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385151928.pdf","grobid_xml":"https://content.openalex.org/works/W4385151928.grobid-xml"},"referenced_works_count":90,"referenced_works":["https://openalex.org/W77790951","https://openalex.org/W124356247","https://openalex.org/W184888313","https://openalex.org/W232876404","https://openalex.org/W1563795667","https://openalex.org/W1579838312","https://openalex.org/W1595289649","https://openalex.org/W1600470703","https://openalex.org/W1849277567","https://openalex.org/W1922658220","https://openalex.org/W1977556410","https://openalex.org/W1978986151","https://openalex.org/W1980850109","https://openalex.org/W1985258161","https://openalex.org/W2002499281","https://openalex.org/W2040357394","https://openalex.org/W2041823554","https://openalex.org/W2078350191","https://openalex.org/W2078455576","https://openalex.org/W2101066392","https://openalex.org/W2102893423","https://openalex.org/W2105594594","https://openalex.org/W2124940540","https://openalex.org/W2125168896","https://openalex.org/W2133803203","https://openalex.org/W2142878924","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2210153255","https://openalex.org/W2295598076","https://openalex.org/W2347141333","https://openalex.org/W2505434962","https://openalex.org/W2515121265","https://openalex.org/W2526050071","https://openalex.org/W2531409750","https://openalex.org/W2594633041","https://openalex.org/W2777468850","https://openalex.org/W2907384076","https://openalex.org/W2912740705","https://openalex.org/W2962851944","https://openalex.org/W2962858109","https://openalex.org/W2963604492","https://openalex.org/W2969426323","https://openalex.org/W2972798094","https://openalex.org/W2981087920","https://openalex.org/W2993640112","https://openalex.org/W2994448930","https://openalex.org/W3009009611","https://openalex.org/W3012371808","https://openalex.org/W3012374325","https://openalex.org/W3014279133","https://openalex.org/W3033326607","https://openalex.org/W3036601975","https://openalex.org/W3049079173","https://openalex.org/W3049278490","https://openalex.org/W3094581495","https://openalex.org/W3111336239","https://openalex.org/W3114905094","https://openalex.org/W3132764260","https://openalex.org/W3160475509","https://openalex.org/W3162508345","https://openalex.org/W3164115648","https://openalex.org/W3191417718","https://openalex.org/W3197561413","https://openalex.org/W3198429080","https://openalex.org/W3209059054","https://openalex.org/W3209984917","https://openalex.org/W3211384831","https://openalex.org/W3211552069","https://openalex.org/W4200362612","https://openalex.org/W4231029117","https://openalex.org/W4239510810","https://openalex.org/W4256202811","https://openalex.org/W4293861706","https://openalex.org/W4379549064","https://openalex.org/W6607595036","https://openalex.org/W6609126827","https://openalex.org/W6633802082","https://openalex.org/W6639204139","https://openalex.org/W6644682428","https://openalex.org/W6675220957","https://openalex.org/W6683584131","https://openalex.org/W6685133223","https://openalex.org/W6734194636","https://openalex.org/W6739575509","https://openalex.org/W6757782831","https://openalex.org/W6759825495","https://openalex.org/W6771864852","https://openalex.org/W6780218876","https://openalex.org/W6799652625"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W2011227383","https://openalex.org/W4375868962","https://openalex.org/W2088854863","https://openalex.org/W1976719989","https://openalex.org/W2942893872","https://openalex.org/W2065606036","https://openalex.org/W3179495260","https://openalex.org/W3127543252","https://openalex.org/W2979740303"],"abstract_inverted_index":{"Automatic":[0],"accent":[1,76,155,216],"classification":[2,77,217],"is":[3,82,209],"an":[4,174],"active":[5],"research":[6],"field":[7],"concerning":[8],"speech":[9,43],"processing.":[10],"It":[11],"can":[12,23],"be":[13,24],"useful":[14],"to":[15,92,115,152,199,211,223],"identify":[16],"a":[17,49,73,90,93,189,200],"speaker's":[18],"region":[19],"of":[20,41,119,137,156,176,215],"origin,":[21],"which":[22,81],"applied":[25],"in":[26,184,226],"police":[27],"investigations":[28],"carried":[29,164],"out":[30,165],"by":[31,89,109,188],"Law":[32],"Enforcement":[33],"Agencies,":[34],"as":[35,37],"well":[36],"for":[38,75,125],"the":[39,56,86,104,117,120,138,147,153,157,168,185,213,221],"improvement":[40],"current":[42],"recognition":[44],"systems.":[45],"This":[46,205],"paper":[47,99],"presents":[48],"novel":[50],"descriptor":[51],"called":[52],"Grad-Transfer,":[53,80],"extracted":[54],"using":[55,159],"Gradient-weighted":[57],"Class":[58],"Activation":[59],"Mapping":[60],"(Grad-CAM)":[61],"method":[62],"based":[63,83],"on":[64,84,101,111,167],"convolutional":[65],"neural":[66],"network":[67],"(CNN)":[68],"interpretability.":[69],"Additionally,":[70],"we":[71],"propose":[72],"methodology":[74],"that":[78,122,207],"implements":[79],"transferring":[85],"knowledge":[87],"acquired":[88],"CNN":[91],"classical":[94],"machine":[95],"learning":[96],"algorithm.":[97],"The":[98],"works":[100],"two":[102],"hypotheses:":[103],"coarse":[105],"localization":[106],"maps":[107],"produced":[108],"Grad-CAM":[110],"spectrograms":[112,121],"are":[113,123],"able":[114,210],"highlight":[116],"regions":[118],"important":[124],"predicting":[126],"accents,":[127],"and":[128,180,219],"Grad-Transfer":[129,149,208],"descriptors":[130,150],"computed":[131],"from":[132],"audios":[133,158],"represent":[134],"distinctive":[135],"descriptions":[136],"target":[139],"accents.":[140],"These":[141],"hypotheses":[142],"were":[143],"demonstrated":[144],"experimentally,":[145],"clustering":[146],"generated":[148],"according":[151],"original":[154],"Birch":[160],"and$k$-means":[161],"algorithms.":[162],"We":[163],"experiments":[166],"Voice":[169],"Cloning":[170],"Toolkit":[171],"dataset,":[172],"seeing":[173],"increase":[175],"macro":[177],"average":[178,182],"accuracy,":[179],"unweighted":[181],"recall":[183],"results":[186],"obtained":[187],"Gaussian":[190],"Naive":[191],"Bayes":[192],"classifier":[193],"up":[194],"to$23.00\\%$,":[195],"and$23.58\\%$,":[196],"respectively,":[197],"compared":[198],"model":[201],"trained":[202],"with":[203],"spectrograms.":[204],"demonstrates":[206],"improve":[212],"performance":[214],"models":[218],"opens":[220],"door":[222],"new":[224],"implementations":[225],"similar":[227],"tasks.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}