{"id":"https://openalex.org/W2748130992","doi":"https://doi.org/10.21437/interspeech.2017-378","title":"Dominant Distortion Classification for Pre-Processing of Vowels in Remote Biomedical Voice Analysis","display_name":"Dominant Distortion Classification for Pre-Processing of Vowels in Remote Biomedical Voice Analysis","publication_year":2017,"publication_date":"2017-08-16","ids":{"openalex":"https://openalex.org/W2748130992","doi":"https://doi.org/10.21437/interspeech.2017-378","mag":"2748130992"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2017-378","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://vbn.aau.dk/da/publications/9688fdcf-1a34-431e-8a91-af14ac891a6e","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019002740","display_name":"Amir Hossein Poorjam","orcid":"https://orcid.org/0000-0002-6882-4618"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Amir Hossein Poorjam","raw_affiliation_strings":["Audio Analysis Lab"],"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab","institution_ids":["https://openalex.org/I4210123192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041263382","display_name":"Jesper Rindom Jensen","orcid":"https://orcid.org/0000-0001-6023-8270"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jesper Rindom Jensen","raw_affiliation_strings":["Institut for Arkitektur og Medieteknologi"],"affiliations":[{"raw_affiliation_string":"Institut for Arkitektur og Medieteknologi","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018028924","display_name":"Max A. Little","orcid":"https://orcid.org/0000-0002-1507-3822"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Max A. Little","raw_affiliation_strings":["Aston University; Massachusetts Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Aston University; Massachusetts Institute of Technology","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026658144","display_name":"Mads Gr\u00e6sb\u00f8ll Christensen","orcid":"https://orcid.org/0000-0003-3586-7969"},"institutions":[{"id":"https://openalex.org/I4210123192","display_name":"International Audio Laboratories Erlangen","ror":"https://ror.org/02mkz3e80","country_code":"DE","type":"facility","lineage":["https://openalex.org/I181369854","https://openalex.org/I4210123192","https://openalex.org/I4210124274","https://openalex.org/I4923324"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mads Gr\u00e6sb\u00f8ll Christensen","raw_affiliation_strings":["Audio Analysis Lab"],"affiliations":[{"raw_affiliation_string":"Audio Analysis Lab","institution_ids":["https://openalex.org/I4210123192"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5019002740"],"corresponding_institution_ids":["https://openalex.org/I4210123192"],"apc_list":null,"apc_paid":null,"fwci":2.3382,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.88468005,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"289","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.9997000098228455,"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":0.9997000098228455,"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/T10860","display_name":"Speech and Audio Processing","score":0.9987000226974487,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7012131810188293},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.6983342170715332},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6772153377532959},{"id":"https://openalex.org/keywords/clipping","display_name":"Clipping (morphology)","score":0.5023281574249268},{"id":"https://openalex.org/keywords/cepstrum","display_name":"Cepstrum","score":0.46740442514419556},{"id":"https://openalex.org/keywords/voice-activity-detection","display_name":"Voice activity detection","score":0.4235406816005707},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42177602648735046},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.41857296228408813},{"id":"https://openalex.org/keywords/mel-frequency-cepstrum","display_name":"Mel-frequency cepstrum","score":0.41784876585006714},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.36080241203308105},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.31025809049606323},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.20229974389076233},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.14929673075675964}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7012131810188293},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.6983342170715332},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6772153377532959},{"id":"https://openalex.org/C2776848632","wikidata":"https://www.wikidata.org/wiki/Q853463","display_name":"Clipping (morphology)","level":2,"score":0.5023281574249268},{"id":"https://openalex.org/C88485024","wikidata":"https://www.wikidata.org/wiki/Q1054571","display_name":"Cepstrum","level":2,"score":0.46740442514419556},{"id":"https://openalex.org/C204201278","wikidata":"https://www.wikidata.org/wiki/Q1332614","display_name":"Voice activity detection","level":3,"score":0.4235406816005707},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42177602648735046},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.41857296228408813},{"id":"https://openalex.org/C151989614","wikidata":"https://www.wikidata.org/wiki/Q440370","display_name":"Mel-frequency cepstrum","level":3,"score":0.41784876585006714},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.36080241203308105},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.31025809049606323},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.20229974389076233},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.14929673075675964},{"id":"https://openalex.org/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.21437/interspeech.2017-378","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2017-378","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2017","raw_type":"proceedings-article"},{"id":"pmh:oai:pure.atira.dk:openaire/9688fdcf-1a34-431e-8a91-af14ac891a6e","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/9688fdcf-1a34-431e-8a91-af14ac891a6e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Poorjam, A H, Jensen, J R, Little, M A & Christensen, M G 2017, Dominant distortion classification for pre-processing of vowels in remote biomedical voice analysis. in Proc. INTERSPEECH 2017. Proceedings of the International Conference on Spoken Language Processing, pp. 289-293, Interspeech 2017, Stockholm, Sweden, 20/08/2017. https://doi.org/10.21437/Interspeech.2017-378","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:publications.aston.ac.uk:33124","is_oa":true,"landing_page_url":"https://publications.aston.ac.uk/view/author/55854151225fae1984fe9ab94da9b586.html>","pdf_url":"https://publications.aston.ac.uk/id/eprint/33124/1/Dominant_Distortion_Classification_for_Pre_Processing_of_Vowels_in_Remote.pdf","source":{"id":"https://openalex.org/S4306400483","display_name":"Aston Publications Explorer (Aston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169199633","host_organization_name":"Aston University","host_organization_lineage":["https://openalex.org/I169199633"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"NonPeerReviewed"},{"id":"pmh:oai:publications.aston.ac.uk:32040","is_oa":true,"landing_page_url":"http://publications.aston.ac.uk/id/eprint/32040/","pdf_url":null,"source":{"id":"https://openalex.org/S4306400483","display_name":"Aston Publications Explorer (Aston University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I169199633","host_organization_name":"Aston University","host_organization_lineage":["https://openalex.org/I169199633"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:pure.atira.dk:publications/9688fdcf-1a34-431e-8a91-af14ac891a6e","is_oa":true,"landing_page_url":"https://pdfs.semanticscholar.org/203a/5fd38d8f071d567985d44f8df73f30518bdc.pdf?_ga=2.169117736.804976170.1515957833-873092488.1497009173","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"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":"Poorjam , A H , Jensen , J R , Little , M A & Christensen , M G 2017 , Dominant distortion classification for pre-processing of vowels in remote biomedical voice analysis . in Proc. INTERSPEECH 2017 . Proceedings of the International Conference on Spoken Language Processing , pp. 289-293 , Interspeech 2017 , Stockholm , Sweden , 20/08/2017 . https://doi.org/10.21437/Interspeech.2017-378","raw_type":"contributionToPeriodical"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/9688fdcf-1a34-431e-8a91-af14ac891a6e","is_oa":true,"landing_page_url":"https://vbn.aau.dk/da/publications/9688fdcf-1a34-431e-8a91-af14ac891a6e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401731","display_name":"VBN Forskningsportal (Aalborg Universitet)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I891191580","host_organization_name":"Aalborg University","host_organization_lineage":["https://openalex.org/I891191580"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Poorjam, A H, Jensen, J R, Little, M A & Christensen, M G 2017, Dominant distortion classification for pre-processing of vowels in remote biomedical voice analysis. in Proc. INTERSPEECH 2017. Proceedings of the International Conference on Spoken Language Processing, pp. 289-293, Interspeech 2017, Stockholm, Sweden, 20/08/2017. https://doi.org/10.21437/Interspeech.2017-378","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W144594064","https://openalex.org/W1493163583","https://openalex.org/W1602583412","https://openalex.org/W1672023655","https://openalex.org/W1963664254","https://openalex.org/W1993224291","https://openalex.org/W2006715209","https://openalex.org/W2062826588","https://openalex.org/W2064926064","https://openalex.org/W2084627109","https://openalex.org/W2089317962","https://openalex.org/W2095134828","https://openalex.org/W2104953067","https://openalex.org/W2114294947","https://openalex.org/W2117678320","https://openalex.org/W2121771908","https://openalex.org/W2136682440","https://openalex.org/W2147187716","https://openalex.org/W2154278880","https://openalex.org/W2157562541","https://openalex.org/W2157605697","https://openalex.org/W2165806037","https://openalex.org/W2562673262","https://openalex.org/W2620402097","https://openalex.org/W4233131682","https://openalex.org/W4239510810","https://openalex.org/W4297675714"],"related_works":["https://openalex.org/W2018086531","https://openalex.org/W1980297060","https://openalex.org/W2387604097","https://openalex.org/W4385672897","https://openalex.org/W2373675101","https://openalex.org/W106160982","https://openalex.org/W2359140082","https://openalex.org/W1556565948","https://openalex.org/W1614028504","https://openalex.org/W2953493266"],"abstract_inverted_index":{"Advances":[0],"in":[1,27,66,86,104,131,154],"speech":[2],"signal":[3,43],"analysis":[4],"facilitate":[5],"the":[6,16,35,39,50,82,100,125,142,148,151],"development":[7],"of":[8,18,52,56,129,133,150],"techniques":[9,20],"for":[10,44],"remote":[11],"biomedical":[12,87],"voice":[13,42,46,67,88,106,136],"assessment.":[14],"However,":[15],"performance":[17],"these":[19],"is":[21],"affected":[22],"by":[23],"noise":[24],"and":[25,48,74,116,127,144,157],"distortion":[26,57,95,103,130,155],"signals.":[28,107],"In":[29],"this":[30],"paper,":[31],"we":[32,91],"focus":[33],"on":[34,76],"vowel":[36],"/a/":[37],"as":[38,113,121],"most":[40,83,101],"widely-used":[41,84],"pathological":[45],"assessments":[47],"investigate":[49],"impact":[51],"four":[53],"major":[54],"types":[55],"that":[58],"are":[59],"commonly":[60],"present":[61],"during":[62],"recording":[63],"or":[64],"transmission":[65],"analysis,":[68],"namely:":[69],"background":[70],"noise,":[71],"reverberation,":[72],"clipping":[73],"compression,":[75],"Mel-frequency":[77],"cepstral":[78],"coefficients":[79],"(MFCCs)":[80],"-":[81],"features":[85,115],"analysis.":[89],"Then,":[90],"propose":[92],"a":[93,117,134],"new":[94],"classification":[96],"approach":[97,153],"to":[98,123],"detect":[99,124],"dominant":[102],"such":[105],"The":[108],"proposed":[109,152],"method":[110],"involves":[111],"MFCCs":[112],"frame-level":[114],"support":[118],"vector":[119],"machine":[120],"classifier":[122],"presence":[126],"type":[128],"frames":[132],"given":[135],"signal.":[137],"Experimental":[138],"results":[139],"obtained":[140],"from":[141],"healthy":[143],"Parkinson's":[145],"voices":[146],"show":[147],"effectiveness":[149],"detection":[156],"classification.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":5}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}