{"id":"https://openalex.org/W7124839971","doi":"https://doi.org/10.1109/cvmi66673.2025.11337370","title":"AI-Powered Diagnosis of Voice Disorders Using Mel-Frequency Feature and Machine Learning","display_name":"AI-Powered Diagnosis of Voice Disorders Using Mel-Frequency Feature and Machine Learning","publication_year":2025,"publication_date":"2025-10-12","ids":{"openalex":"https://openalex.org/W7124839971","doi":"https://doi.org/10.1109/cvmi66673.2025.11337370"},"language":null,"primary_location":{"id":"doi:10.1109/cvmi66673.2025.11337370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi66673.2025.11337370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-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/A5123446976","display_name":"Anshu Mala Kispotta","orcid":null},"institutions":[{"id":"https://openalex.org/I115715567","display_name":"Birla Institute of Technology, Mesra","ror":"https://ror.org/028vtqb15","country_code":"IN","type":"education","lineage":["https://openalex.org/I115715567"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Anshu Mala Kispotta","raw_affiliation_strings":["Birla Institute of Technology Mesra,Dept. of Electronics and Communication Engineering,Ranchi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology Mesra,Dept. of Electronics and Communication Engineering,Ranchi,India","institution_ids":["https://openalex.org/I115715567"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108540976","display_name":"Sinha Rk","orcid":null},"institutions":[{"id":"https://openalex.org/I115715567","display_name":"Birla Institute of Technology, Mesra","ror":"https://ror.org/028vtqb15","country_code":"IN","type":"education","lineage":["https://openalex.org/I115715567"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rupesh Kumar Sinha","raw_affiliation_strings":["Birla Institute of Technology Mesra,Dept. of Electronics and Communication Engineering,Ranchi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology Mesra,Dept. of Electronics and Communication Engineering,Ranchi,India","institution_ids":["https://openalex.org/I115715567"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000427644","display_name":"Sitanshu Sekhar Sahu","orcid":"https://orcid.org/0000-0003-1236-2255"},"institutions":[{"id":"https://openalex.org/I115715567","display_name":"Birla Institute of Technology, Mesra","ror":"https://ror.org/028vtqb15","country_code":"IN","type":"education","lineage":["https://openalex.org/I115715567"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sitanshu Sekhar Sahu","raw_affiliation_strings":["Birla Institute of Technology Mesra,Dept. of Electronics and Communication Engineering,Ranchi,India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Birla Institute of Technology Mesra,Dept. of Electronics and Communication Engineering,Ranchi,India","institution_ids":["https://openalex.org/I115715567"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64712874,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9972000122070312,"subfield":{"id":"https://openalex.org/subfields/2737","display_name":"Physiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12418","display_name":"Respiratory and Cough-Related Research","score":0.0005000000237487257,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12419","display_name":"Phonocardiography and Auscultation Techniques","score":0.0003000000142492354,"subfield":{"id":"https://openalex.org/subfields/2740","display_name":"Pulmonary and Respiratory Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.65420001745224},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.6294000148773193},{"id":"https://openalex.org/keywords/voice-disorder","display_name":"Voice Disorder","score":0.4643000066280365},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4424999952316284},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.41269999742507935},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.39629998803138733},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39070001244544983}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6833000183105469},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.65420001745224},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.6294000148773193},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6211000084877014},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.515999972820282},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.49239999055862427},{"id":"https://openalex.org/C2908717642","wikidata":"https://www.wikidata.org/wiki/Q4593337","display_name":"Voice Disorder","level":2,"score":0.4643000066280365},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4424999952316284},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.41269999742507935},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.39629998803138733},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39070001244544983},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.31049999594688416},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.30309998989105225},{"id":"https://openalex.org/C182964821","wikidata":"https://www.wikidata.org/wiki/Q7939498","display_name":"Voice analysis","level":2,"score":0.2946999967098236},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C125168437","wikidata":"https://www.wikidata.org/wiki/Q7625184","display_name":"Structured support vector machine","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C2780724565","wikidata":"https://www.wikidata.org/wiki/Q5227256","display_name":"Data classification","level":2,"score":0.25949999690055847}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvmi66673.2025.11337370","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvmi66673.2025.11337370","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Computer Vision and Machine Intelligence (CVMI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2790046776","https://openalex.org/W3014330170","https://openalex.org/W3112193599","https://openalex.org/W3152545903","https://openalex.org/W3152745858","https://openalex.org/W3216240934","https://openalex.org/W4225274058","https://openalex.org/W4280501153","https://openalex.org/W4308659657","https://openalex.org/W4319985571","https://openalex.org/W4384917559","https://openalex.org/W4385729616","https://openalex.org/W4391669270","https://openalex.org/W4404840100"],"related_works":[],"abstract_inverted_index":{"Automatic":[0],"classification":[1,58],"of":[2,39,83,95],"voice":[3,6,24,40,47,107],"disorders":[4],"using":[5,71],"signals":[7],"remains":[8],"a":[9],"challenging":[10],"task.":[11],"In":[12],"this":[13],"work,":[14],"spectral-domain":[15],"features,":[16],"specifically":[17],"Mel-Frequency":[18],"feature,":[19],"were":[20,69],"extracted":[21],"from":[22,51],"the":[23,52,93,96],"samples":[25],"and":[26,43,64,102],"used":[27],"as":[28],"input":[29],"to":[30],"machine":[31],"learning":[32],"classifiers":[33],"for":[34,106],"disorder":[35,108],"identification.":[36],"Three":[37],"types":[38],"disorders\u2014Polyp,":[41],"Cyst,":[42],"Laryngitis\u2014were":[44],"considered.":[45],"The":[46,77],"data":[48],"was":[49],"sourced":[50],"Saarbruecken":[53],"Voice":[54],"Database":[55],"(SVD).":[56],"Two":[57],"models,":[59],"Support":[60],"Vector":[61],"Classifier":[62,67],"(SVC)":[63],"Forest":[65],"Based":[66],"(FBC),":[68],"evaluated":[70],"an":[72,81],"80\u201320":[73],"hold-out":[74],"validation":[75],"strategy.":[76],"FBC":[78],"model":[79],"achieved":[80],"accuracy":[82],"99.82%,":[84],"surpassing":[85],"previously":[86],"reported":[87],"results":[88],"(85-97%).":[89],"These":[90],"findings":[91],"demonstrate":[92],"effectiveness":[94],"proposed":[97],"method":[98],"in":[99],"developing":[100],"reliable":[101],"non-invasive":[103],"diagnostic":[104],"tools":[105],"detection.":[109]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-01-21T00:00:00"}
