{"id":"https://openalex.org/W3096789095","doi":"https://doi.org/10.21437/interspeech.2020-2821","title":"Detection of Voicing and Place of Articulation of Fricatives with Deep Learning in a Virtual Speech and Language Therapy Tutor","display_name":"Detection of Voicing and Place of Articulation of Fricatives with Deep Learning in a Virtual Speech and Language Therapy Tutor","publication_year":2020,"publication_date":"2020-10-25","ids":{"openalex":"https://openalex.org/W3096789095","doi":"https://doi.org/10.21437/interspeech.2020-2821","mag":"3096789095"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2020-2821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10400.26/39944","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047921027","display_name":"Ivo Anjos","orcid":"https://orcid.org/0000-0002-9493-1564"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":true,"raw_author_name":"Ivo Anjos","raw_affiliation_strings":["NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal"],"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077285164","display_name":"Maxine Esk\u00e9nazi","orcid":null},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Maxine Eskenazi","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh, PA 15213, USA"],"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University 5000 Forbes Avenue, Pittsburgh, PA 15213, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000700188","display_name":"Nuno C. Marques","orcid":"https://orcid.org/0000-0002-3019-3304"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Nuno Marques","raw_affiliation_strings":["NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal"],"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112508899","display_name":"Margarida Grilo","orcid":null},"institutions":[{"id":"https://openalex.org/I4210148988","display_name":"Escola Superior de Sa\u00fade do Alcoit\u00e3o","ror":"https://ror.org/05gzcpj23","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210148988"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Margarida Grilo","raw_affiliation_strings":["Escola Superior de Sa\u00fade do Alcoit\u00e3o Rua Conde Bar\u00e3o, Alcoit\u00e3o, 2649-506 Alcabideche, Portugal"],"affiliations":[{"raw_affiliation_string":"Escola Superior de Sa\u00fade do Alcoit\u00e3o Rua Conde Bar\u00e3o, Alcoit\u00e3o, 2649-506 Alcabideche, Portugal","institution_ids":["https://openalex.org/I4210148988"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080135269","display_name":"Isabel Guimar\u00e3es","orcid":"https://orcid.org/0000-0001-8524-8731"},"institutions":[{"id":"https://openalex.org/I4210148988","display_name":"Escola Superior de Sa\u00fade do Alcoit\u00e3o","ror":"https://ror.org/05gzcpj23","country_code":"PT","type":"education","lineage":["https://openalex.org/I4210148988"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Isabel Guimar\u00e3es","raw_affiliation_strings":["Escola Superior de Sa\u00fade do Alcoit\u00e3o Rua Conde Bar\u00e3o, Alcoit\u00e3o, 2649-506 Alcabideche, Portugal"],"affiliations":[{"raw_affiliation_string":"Escola Superior de Sa\u00fade do Alcoit\u00e3o Rua Conde Bar\u00e3o, Alcoit\u00e3o, 2649-506 Alcabideche, Portugal","institution_ids":["https://openalex.org/I4210148988"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002705720","display_name":"Jo\u00e3o Magalh\u00e3es","orcid":"https://orcid.org/0000-0001-6290-5719"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Jo\u00e3o Magalh\u00e3es","raw_affiliation_strings":["NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal"],"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal","institution_ids":["https://openalex.org/I83558840"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079621273","display_name":"Sofia Cavaco","orcid":"https://orcid.org/0000-0001-7315-4543"},"institutions":[{"id":"https://openalex.org/I83558840","display_name":"Universidade Nova de Lisboa","ror":"https://ror.org/02xankh89","country_code":"PT","type":"education","lineage":["https://openalex.org/I83558840"]}],"countries":["PT"],"is_corresponding":false,"raw_author_name":"Sofia Cavaco","raw_affiliation_strings":["NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal"],"affiliations":[{"raw_affiliation_string":"NOVA LINCS, Department of Computer Science Faculdade de Ci\u00eancias e Tecnologia, Universidade NOVA de Lisboa 2829-516 Caparica, Portugal","institution_ids":["https://openalex.org/I83558840"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5047921027"],"corresponding_institution_ids":["https://openalex.org/I83558840"],"apc_list":null,"apc_paid":null,"fwci":0.5438,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74475623,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"3156","last_page":"3160"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9995999932289124,"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":0.9995999932289124,"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/T12031","display_name":"Speech and dialogue systems","score":0.9957000017166138,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9948999881744385,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/voice","display_name":"Voice","score":0.8880041837692261},{"id":"https://openalex.org/keywords/tutor","display_name":"TUTOR","score":0.7485860586166382},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6900014281272888},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6898155808448792},{"id":"https://openalex.org/keywords/place-of-articulation","display_name":"Place of articulation","score":0.6564556956291199},{"id":"https://openalex.org/keywords/articulation","display_name":"Articulation (sociology)","score":0.5829406976699829},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4500454366207123},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4392586946487427},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.38177022337913513},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3320508599281311},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.3292958736419678},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.09763157367706299},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.08170130848884583},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.07382968068122864}],"concepts":[{"id":"https://openalex.org/C552089266","wikidata":"https://www.wikidata.org/wiki/Q494510","display_name":"Voice","level":2,"score":0.8880041837692261},{"id":"https://openalex.org/C2778371403","wikidata":"https://www.wikidata.org/wiki/Q7672049","display_name":"TUTOR","level":2,"score":0.7485860586166382},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6900014281272888},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6898155808448792},{"id":"https://openalex.org/C36933642","wikidata":"https://www.wikidata.org/wiki/Q214090","display_name":"Place of articulation","level":4,"score":0.6564556956291199},{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.5829406976699829},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4500454366207123},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4392586946487427},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38177022337913513},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3320508599281311},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.3292958736419678},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.09763157367706299},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.08170130848884583},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.07382968068122864},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2020-2821","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2020-2821","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2020","raw_type":"proceedings-article"},{"id":"pmh:oai:comum.rcaap.pt:10400.26/39944","is_oa":true,"landing_page_url":"http://hdl.handle.net/10400.26/39944","pdf_url":null,"source":{"id":"https://openalex.org/S4306401666","display_name":"Reposit\u00f3rio Comum (Reposit\u00f3rio Cient\u00edfico de Acesso Aberto de Portugal)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"conference object"}],"best_oa_location":{"id":"pmh:oai:comum.rcaap.pt:10400.26/39944","is_oa":true,"landing_page_url":"http://hdl.handle.net/10400.26/39944","pdf_url":null,"source":{"id":"https://openalex.org/S4306401666","display_name":"Reposit\u00f3rio Comum (Reposit\u00f3rio Cient\u00edfico de Acesso Aberto de Portugal)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"conference object"},"sustainable_development_goals":[{"score":0.6600000262260437,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G3560745943","display_name":null,"funder_award_id":"PEest/UID/CEC/04516/2019","funder_id":"https://openalex.org/F4320331406","funder_display_name":"NOVA Laboratory for Computer Science and Informatics"},{"id":"https://openalex.org/G5766540765","display_name":null,"funder_award_id":"UID/CEC/04516/2019","funder_id":"https://openalex.org/F4320331406","funder_display_name":"NOVA Laboratory for Computer Science and Informatics"}],"funders":[{"id":"https://openalex.org/F4320331406","display_name":"NOVA Laboratory for Computer Science and Informatics","ror":null},{"id":"https://openalex.org/F4320335191","display_name":"Centro de Matem\u00e1tica Universidade do Porto","ror":"https://ror.org/043pwc612"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W164121789","https://openalex.org/W624399025","https://openalex.org/W1524333225","https://openalex.org/W1972440476","https://openalex.org/W2035011869","https://openalex.org/W2077902309","https://openalex.org/W2095705004","https://openalex.org/W2124810955","https://openalex.org/W2316803017","https://openalex.org/W2515079294","https://openalex.org/W2529403924","https://openalex.org/W2888029836","https://openalex.org/W2972026494","https://openalex.org/W3008372905","https://openalex.org/W3045485643"],"related_works":["https://openalex.org/W2111940130","https://openalex.org/W2041494451","https://openalex.org/W2991402433","https://openalex.org/W2088565884","https://openalex.org/W2063884308","https://openalex.org/W2053274757","https://openalex.org/W2008772709","https://openalex.org/W2740766505","https://openalex.org/W2075252927","https://openalex.org/W2025106137"],"abstract_inverted_index":{"Children":[0],"with":[1,78,111],"fricative":[2,55],"distortion":[3,38],"errors":[4,57],"have":[5],"to":[6,9,20,24,60,84],"learn":[7],"how":[8,59],"correctly":[10,25,61],"use":[11,21,62],"the":[12,27,82,86,124,132,136,139],"vocal":[13],"folds,":[14],"and":[15,47,58,74,95,107],"which":[16],"place":[17,92,104],"of":[18,81,93,101,105,123,134],"articulation":[19,94,106],"in":[22,88],"order":[23],"produce":[26],"different":[28],"fricatives.":[29],"Here":[30],"we":[31],"propose":[32],"a":[33,42,118],"virtual":[34,43,67],"tutor":[35,44,68],"for":[36,45,103,109],"fricatives":[37,87],"correction.":[39],"This":[40],"is":[41],"speech":[46,64,90],"language":[48],"therapy":[49],"that":[50,130],"helps":[51],"children":[52],"understand":[53],"their":[54,63],"production":[56],"organs.":[65],"The":[66],"uses":[69],"log":[70,140],"Mel":[71,141],"filter":[72,142],"banks":[73],"deep":[75],"learning":[76],"techniques":[77],"spectral-temporal":[79],"convolutions":[80],"data":[83,121],"classify":[85],"children\u2019s":[89,112],"by":[91],"voicing.":[96],"It":[97],"achieves":[98],"an":[99],"accuracy":[100],"90:40%":[102],"90:93%":[108],"voicing":[110],"speech.":[113],"Furthermore,":[114],"this":[115],"paper":[116],"discusses":[117],"multidimensional":[119],"advanced":[120],"analysis":[122],"first":[125],"layer":[126],"convolutional":[127],"kernel":[128],"filters":[129],"validates":[131],"usefulness":[133],"performing":[135],"convolution":[137],"on":[138],"bank.":[143]},"counts_by_year":[{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
