{"id":"https://openalex.org/W4412623142","doi":"https://doi.org/10.1007/s11760-025-04527-4","title":"Voice pathology identification using mel spectrogram features and deep learning","display_name":"Voice pathology identification using mel spectrogram features and deep learning","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4412623142","doi":"https://doi.org/10.1007/s11760-025-04527-4"},"language":"en","primary_location":{"id":"doi:10.1007/s11760-025-04527-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11760-025-04527-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11760-025-04527-4.pdf","source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s11760-025-04527-4.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016019901","display_name":"Rab Nawaz Bashir","orcid":"https://orcid.org/0000-0001-7409-1775"},"institutions":[{"id":"https://openalex.org/I142024983","display_name":"Prince Sultan University","ror":"https://ror.org/053mqrf26","country_code":"SA","type":"education","lineage":["https://openalex.org/I142024983"]},{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK","SA"],"is_corresponding":false,"raw_author_name":"Rab Nawaz Bashir","raw_affiliation_strings":["AIDA Laboratory College of Computer & Information Sciences (CCIS) Prince Sultan University, Rafha,  Riyadh, 11586, Saudi Arabia","Department of Computer Science, COMSATS University Islamabad Vehari Campus, Vehari, 61100, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIDA Laboratory College of Computer & Information Sciences (CCIS) Prince Sultan University, Rafha,  Riyadh, 11586, Saudi Arabia","institution_ids":["https://openalex.org/I142024983"]},{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad Vehari Campus, Vehari, 61100, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868909","display_name":"Muhammad Ali Shahid","orcid":"https://orcid.org/0009-0003-3493-1532"},"institutions":[{"id":"https://openalex.org/I2802902501","display_name":"Namal University","ror":"https://ror.org/00zcxra43","country_code":"PK","type":"education","lineage":["https://openalex.org/I2802902501"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Muhammad Ali Shahid","raw_affiliation_strings":["Department of Computer Science, NAMAL university Minawali, Street, Minawali, 42250, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, NAMAL university Minawali, Street, Minawali, 42250, Pakistan","institution_ids":["https://openalex.org/I2802902501"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065801825","display_name":"Tarik A. Rashid","orcid":"https://orcid.org/0000-0002-8661-258X"},"institutions":[{"id":"https://openalex.org/I16076960","display_name":"COMSATS University Islamabad","ror":"https://ror.org/00nqqvk19","country_code":"PK","type":"education","lineage":["https://openalex.org/I16076960"]}],"countries":["PK"],"is_corresponding":false,"raw_author_name":"Tahir Rashid","raw_affiliation_strings":["Department of Computer Science, COMSATS University Islamabad Vehari Campus, Vehari, 61100, Pakistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, COMSATS University Islamabad Vehari Campus, Vehari, 61100, Pakistan","institution_ids":["https://openalex.org/I16076960"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113665999","display_name":"Muhammad Faheem","orcid":"https://orcid.org/0000-0003-4628-4486"},"institutions":[{"id":"https://openalex.org/I87653560","display_name":"VTT Technical Research Centre of Finland","ror":"https://ror.org/04b181w54","country_code":"FI","type":"nonprofit","lineage":["https://openalex.org/I4210089493","https://openalex.org/I87653560"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Muhammad Faheem","raw_affiliation_strings":["VTT-Technical Research Centre of Finland Ltd., Maarintie 3, Espoo, 02150, Finland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VTT-Technical Research Centre of Finland Ltd., Maarintie 3, Espoo, 02150, Finland","institution_ids":["https://openalex.org/I87653560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108326563","display_name":"Taoufik Saidani","orcid":null},"institutions":[{"id":"https://openalex.org/I4210120708","display_name":"Prince Mohammad Bin Salman College of Business and Entrepreneurship","ror":"https://ror.org/01ywkr738","country_code":"SA","type":"education","lineage":["https://openalex.org/I4210120708"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Taoufik Saidani","raw_affiliation_strings":["Center for Scientific Research and Entrepreneurship, Street, Arar, 73213, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Scientific Research and Entrepreneurship, Street, Arar, 73213, Saudi Arabia","institution_ids":["https://openalex.org/I4210120708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059667465","display_name":"Oumaima Saidani","orcid":"https://orcid.org/0000-0001-9520-3174"},"institutions":[{"id":"https://openalex.org/I106778892","display_name":"Princess Nourah bint Abdulrahman University","ror":"https://ror.org/05b0cyh02","country_code":"SA","type":"education","lineage":["https://openalex.org/I106778892"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Oumaima Saidani","raw_affiliation_strings":["Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O Box, 84428, Riyadh 11671, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P.O Box, 84428, Riyadh 11671, Saudi Arabia","institution_ids":["https://openalex.org/I106778892"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062125413","display_name":"Amjad Rehman","orcid":"https://orcid.org/0000-0002-3817-2655"},"institutions":[{"id":"https://openalex.org/I142024983","display_name":"Prince Sultan University","ror":"https://ror.org/053mqrf26","country_code":"SA","type":"education","lineage":["https://openalex.org/I142024983"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Amjad Rehman Khan","raw_affiliation_strings":["AIDA Laboratory College of Computer & Information Sciences (CCIS) Prince Sultan University, Rafha,  Riyadh, 11586, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIDA Laboratory College of Computer & Information Sciences (CCIS) Prince Sultan University, Rafha,  Riyadh, 11586, Saudi Arabia","institution_ids":["https://openalex.org/I142024983"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5113665999"],"corresponding_institution_ids":["https://openalex.org/I87653560"],"apc_list":{"value":2390,"currency":"EUR","value_usd":2990},"apc_paid":{"value":2390,"currency":"EUR","value_usd":2990},"fwci":5.708,"has_fulltext":true,"cited_by_count":5,"citation_normalized_percentile":{"value":0.96349995,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"19","issue":"11","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9975000023841858,"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":0.9975000023841858,"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":0.9965000152587891,"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/T11309","display_name":"Music and Audio Processing","score":0.9890999794006348,"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":0.860844075679779},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.701798677444458},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4919991195201874},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4608454704284668},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.44984692335128784},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.42264658212661743},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39598193764686584},{"id":"https://openalex.org/keywords/pathology","display_name":"Pathology","score":0.3665127158164978},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3374834656715393},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.33361369371414185},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.3239176571369171},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.2807946801185608}],"concepts":[{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.860844075679779},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.701798677444458},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4919991195201874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4608454704284668},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.44984692335128784},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.42264658212661743},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39598193764686584},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.3665127158164978},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3374834656715393},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.33361369371414185},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3239176571369171},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.2807946801185608},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s11760-025-04527-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11760-025-04527-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11760-025-04527-4.pdf","source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s11760-025-04527-4","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11760-025-04527-4","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11760-025-04527-4.pdf","source":{"id":"https://openalex.org/S156904493","display_name":"Signal Image and Video Processing","issn_l":"1863-1703","issn":["1863-1703","1863-1711"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Signal, Image and Video Processing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3528696576","display_name":null,"funder_award_id":"NBU-CRP-2025-2225","funder_id":"https://openalex.org/F4320328654","funder_display_name":"Northern Border University"},{"id":"https://openalex.org/G4714153462","display_name":null,"funder_award_id":"PNURSP2025R760","funder_id":"https://openalex.org/F4320322484","funder_display_name":"Princess Nourah Bint Abdulrahman University"},{"id":"https://openalex.org/G7107681410","display_name":null,"funder_award_id":"11586","funder_id":"https://openalex.org/F4320327702","funder_display_name":"Prince Sultan University"}],"funders":[{"id":"https://openalex.org/F4320322484","display_name":"Princess Nourah Bint Abdulrahman University","ror":"https://ror.org/05b0cyh02"},{"id":"https://openalex.org/F4320327702","display_name":"Prince Sultan University","ror":"https://ror.org/053mqrf26"},{"id":"https://openalex.org/F4320328654","display_name":"Northern Border University","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412623142.pdf","grobid_xml":"https://content.openalex.org/works/W4412623142.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1980761422","https://openalex.org/W2030681221","https://openalex.org/W2065772006","https://openalex.org/W2080263974","https://openalex.org/W2738314890","https://openalex.org/W2895305862","https://openalex.org/W2914428489","https://openalex.org/W2959813266","https://openalex.org/W3031948080","https://openalex.org/W3106009882","https://openalex.org/W3106436761","https://openalex.org/W3112193599","https://openalex.org/W3125384922","https://openalex.org/W4205267278","https://openalex.org/W4213127059","https://openalex.org/W4233394865","https://openalex.org/W4304688131","https://openalex.org/W4313178214","https://openalex.org/W4385729616","https://openalex.org/W4391669270","https://openalex.org/W4403229076"],"related_works":["https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W2088854863","https://openalex.org/W4402568167","https://openalex.org/W2942893872","https://openalex.org/W3179495260","https://openalex.org/W1976719989","https://openalex.org/W2897924318","https://openalex.org/W2138997758"],"abstract_inverted_index":{"Abstract":[0],"Voice":[1,39],"pathology":[2,20],"is":[3],"very":[4],"important":[5],"in":[6,104,140,161,192,197,210],"the":[7,29,37,46,76,80,105,174],"identification":[8,30,106],"of":[9,14,31,48,90,94,100,107,121,135,155],"vocal":[10,221],"disorders.":[11],"Traditional":[12],"methods":[13],"diagnosing":[15],"voice":[16,19,77,199,202,224],"disorders":[17,200,222],"using":[18,36,70,201,223],"are":[21],"expensive,":[22],"time-consuming,":[23],"and":[24,33,56,63,96,102,109,126,137,146,157,167],"subjective.":[25],"The":[26,43,82,113,129,149,183,204],"study":[27,44],"proposed":[28,184,205],"normal":[32,62,108,125,145,166],"pathological":[34,64,110,127,147,168],"voices":[35],"Arabic":[38],"Pathology":[40],"Database":[41],"(AVPD).":[42],"evaluated":[45],"performance":[47,139,160],"Support":[49],"Vector":[50],"Machine":[51],"(SVM),":[52],"hybrid":[53,130],"deep":[54],"learning,":[55],"transfer":[57,83,114,175,185],"learning":[58,84,115,171,176,186],"approaches":[59,196,218],"for":[60,123,219],"identifying":[61,198,220],"voices.":[65,128,148,169],"These":[66],"models":[67],"were":[68],"trained":[69],"Mel":[71],"spectrogram":[72],"features":[73],"extracted":[74],"from":[75,79],"data":[78],"AVPD.":[81],"model":[85,116,131,151,187],"outperformed":[86,178],"with":[87,216],"an":[88,118,133,153],"accuracy":[89,134,154,193],"96.88%,":[91],"a":[92,98,189],"precision":[93],"0.96":[95,103],"0.98,":[97],"recall":[99],"0.98":[101],"voices,":[111],"respectively.":[112],"showed":[117,132,158],"F1":[119],"score":[120],"0.97":[122],"both":[124],"92.71%":[136],"superior":[138],"classification":[141,162],"metrics":[142,163],"to":[143,164],"identify":[144,165],"SVM":[150],"achieved":[152,188],"86.46%":[156],"low":[159],"Deep":[170],"models,":[172],"particularly":[173],"model,":[177],"across":[179],"all":[180],"evaluation":[181],"metrics.":[182],"1.53%":[190],"increase":[191],"over":[194],"state-of-the-art":[195],"pathology.":[203,225],"solution":[206],"has":[207],"several":[208],"applications":[209],"medical":[211],"diagnosis,":[212],"addressing":[213],"issues":[214],"associated":[215],"traditional":[217]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
