{"id":"https://openalex.org/W2807317037","doi":"https://doi.org/10.21437/interspeech.2018-1351","title":"A Deep Learning Method for Pathological Voice Detection Using Convolutional Deep Belief Networks","display_name":"A Deep Learning Method for Pathological Voice Detection Using Convolutional Deep Belief Networks","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2807317037","doi":"https://doi.org/10.21437/interspeech.2018-1351","mag":"2807317037"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1351","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/A5112370036","display_name":"Huiyi Wu","orcid":"https://orcid.org/0000-0002-1809-9729"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Huiyi Wu","raw_affiliation_strings":["Centre for Signal and Image Processing, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Signal and Image Processing, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Scotland","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109249395","display_name":"John Soraghan","orcid":null},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"John Soraghan","raw_affiliation_strings":["Centre for Signal and Image Processing, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Signal and Image Processing, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Scotland","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002043077","display_name":"Anja Lowit","orcid":"https://orcid.org/0000-0003-0842-584X"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Anja Lowit","raw_affiliation_strings":["Speech and Language Therapy, School of Psychological Sciences and Health, University of Strathclyde, Glasgow, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech and Language Therapy, School of Psychological Sciences and Health, University of Strathclyde, Glasgow, Scotland","institution_ids":["https://openalex.org/I181647926"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009371598","display_name":"Gaetano Di Caterina","orcid":"https://orcid.org/0000-0002-7256-0897"},"institutions":[{"id":"https://openalex.org/I181647926","display_name":"University of Strathclyde","ror":"https://ror.org/00n3w3b69","country_code":"GB","type":"education","lineage":["https://openalex.org/I181647926"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Gaetano Di-Caterina","raw_affiliation_strings":["Centre for Signal and Image Processing, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Scotland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Signal and Image Processing, Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow, Scotland","institution_ids":["https://openalex.org/I181647926"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181647926"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":107,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"446","last_page":"450"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9948999881744385,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9848999977111816,"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/T11309","display_name":"Music and Audio Processing","score":0.9833999872207642,"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/computer-science","display_name":"Computer science","score":0.7820034623146057},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.7670174837112427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6905087232589722},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5403002500534058},{"id":"https://openalex.org/keywords/deep-belief-network","display_name":"Deep belief network","score":0.5251046419143677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.47370144724845886},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3774945139884949}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820034623146057},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7670174837112427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6905087232589722},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5403002500534058},{"id":"https://openalex.org/C97385483","wikidata":"https://www.wikidata.org/wiki/Q16954980","display_name":"Deep belief network","level":3,"score":0.5251046419143677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.47370144724845886},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3774945139884949}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.21437/interspeech.2018-1351","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1351","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","raw_type":"proceedings-article"},{"id":"pmh:oai:strathprints.strath.ac.uk:64290","is_oa":false,"landing_page_url":"https://strathprints.strath.ac.uk/view/author/1078516.html>","pdf_url":null,"source":{"id":"https://openalex.org/S4306402226","display_name":"Strathprints: The University of Strathclyde institutional repository (University of Strathclyde)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I181647926","host_organization_name":"University of Strathclyde","host_organization_lineage":["https://openalex.org/I181647926"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Conference or Workshop Item"},{"id":"pmh:oai:spiral.imperial.ac.uk:10044/1/104141","is_oa":false,"landing_page_url":"http://hdl.handle.net/10044/1/104141","pdf_url":null,"source":{"id":"https://openalex.org/S4306401396","display_name":"Spiral (Imperial College London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I47508984","host_organization_name":"Imperial College London","host_organization_lineage":["https://openalex.org/I47508984"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Interspeech 2018","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.4300000071525574,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1988974600","https://openalex.org/W1995562189","https://openalex.org/W2130325614","https://openalex.org/W2148411079","https://openalex.org/W2160815625","https://openalex.org/W2165806037","https://openalex.org/W2271840356","https://openalex.org/W2339666751","https://openalex.org/W2506429203","https://openalex.org/W2755256826"],"related_works":["https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W1530536511","https://openalex.org/W2585432886","https://openalex.org/W3167935049","https://openalex.org/W2165991108","https://openalex.org/W3029198973","https://openalex.org/W3082895349"],"abstract_inverted_index":{"Automatically":[0],"detecting":[1],"pathological":[2,42,50,75],"voice":[3,43,51],"disorders":[4,44],"such":[5],"as":[6,58,78,101],"vocal":[7],"cord":[8],"paralysis":[9],"or":[10],"Reinke\u2019s":[11],"edema":[12],"is":[13,62,119,160],"an":[14],"important":[15],"medical":[16],"classification":[17,147],"problem.":[18],"While":[19],"deep":[20,150],"learning":[21,124,151],"techniques":[22],"have":[23],"achieved":[24],"significant":[25],"progress":[26],"in":[27,38,64,146],"the":[28,39,59,79,82,94,107,110,129,157,166],"speech":[29,76],"recognition":[30],"field,":[31],"there":[32],"has":[33],"been":[34],"less":[35],"research":[36],"work":[37],"area":[40],"of":[41,72,96,109,137,156],"detection.":[45],"A":[46,153],"novel":[47,68,158],"system":[48,69],"for":[49],"detection":[52],"using":[53,113,121,162],"Convolutional":[54,85],"Neural":[55],"Network":[56,88],"(CNN)":[57],"basic":[60],"architecture":[61],"presented":[63],"this":[65,149],"work.":[66],"The":[67],"uses":[70],"spectrograms":[71],"normal":[73],"and":[74],"recordings":[77],"input":[80,111],"to":[81,92,105,126,142],"network.":[83],"Initially":[84],"Deep":[86],"Belief":[87],"(CDBN)":[89],"are":[90],"used":[91,141],"pre-train":[93],"weights":[95],"CNN":[97,118],"system.":[98],"This":[99],"acts":[100],"a":[102,117,134],"generative":[103],"model":[104],"explore":[106],"structure":[108],"data":[112,138,164],"statistical":[114],"methods.":[115],"Then":[116],"trained":[120],"supervised":[122],"back-propagation":[123],"algorithm":[125],"fine":[127],"tune":[128],"weights.":[130],"Results":[131],"show":[132],"that":[133],"small":[135],"amount":[136],"can":[139],"be":[140],"achieve":[143],"good":[144],"results":[145],"with":[148],"approach.":[152],"performance":[154],"analysis":[155],"method":[159],"provided":[161],"real":[163],"from":[165],"Saarbrucken":[167],"Voice":[168],"database.":[169]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":20},{"year":2023,"cited_by_count":17},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":12},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2}],"updated_date":"2026-07-17T09:13:05.818461","created_date":"2025-10-10T00:00:00"}