{"id":"https://openalex.org/W4221144223","doi":"https://doi.org/10.1109/taslp.2022.3209937","title":"Consonant-Vowel Transition Models Based on Deep Learning for Objective Evaluation of Articulation","display_name":"Consonant-Vowel Transition Models Based on Deep Learning for Objective Evaluation of Articulation","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4221144223","doi":"https://doi.org/10.1109/taslp.2022.3209937","pmid":"https://pubmed.ncbi.nlm.nih.gov/36712557"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3209937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209937","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2203.10054","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Vikram C. Mathad","orcid":"https://orcid.org/0000-0001-5509-8955"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Vikram C. Mathad","raw_affiliation_strings":["Zapr media labs, Bengaluru, India"],"raw_orcid":"https://orcid.org/0000-0001-5509-8955","affiliations":[{"raw_affiliation_string":"Zapr media labs, Bengaluru, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056934840","display_name":"Julie Liss","orcid":"https://orcid.org/0000-0001-8782-2901"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Julie M. Liss","raw_affiliation_strings":["College of Health Solutions, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Health Solutions, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082367412","display_name":"Kathy Chapman","orcid":"https://orcid.org/0000-0002-1236-9185"},"institutions":[{"id":"https://openalex.org/I223532165","display_name":"University of Utah","ror":"https://ror.org/03r0ha626","country_code":"US","type":"education","lineage":["https://openalex.org/I223532165"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathy Chapman","raw_affiliation_strings":["Department of Communication Sciences and Disorders, University of Utah, Salt Lake City, UT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Communication Sciences and Disorders, University of Utah, Salt Lake City, UT, USA","institution_ids":["https://openalex.org/I223532165"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022887197","display_name":"Nancy J. Scherer","orcid":"https://orcid.org/0000-0001-5175-0192"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nancy Scherer","raw_affiliation_strings":["College of Health Solutions, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Health Solutions, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021646973","display_name":"Visar Berisha","orcid":"https://orcid.org/0000-0001-8804-8874"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Visar Berisha","raw_affiliation_strings":["College of Health Solutions and School of Electrical, Computer, &amp; Energy Engineering, Arizona State University, Tempe, AZ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Health Solutions and School of Electrical, Computer, &amp; Energy Engineering, Arizona State University, Tempe, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"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":0.03269785,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"31","issue":null,"first_page":"86","last_page":"95"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9417999982833862,"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"}},"topics":[{"id":"https://openalex.org/T10403","display_name":"Phonetics and Phonology Research","score":0.9417999982833862,"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"}},{"id":"https://openalex.org/T10863","display_name":"Voice and Speech Disorders","score":0.04100000113248825,"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/T10730","display_name":"Language Development and Disorders","score":0.0038999998942017555,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational 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/articulation","display_name":"Articulation (sociology)","score":0.839250922203064},{"id":"https://openalex.org/keywords/consonant","display_name":"Consonant","score":0.7689538598060608},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.7627099752426147},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.6646038293838501},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.659197986125946},{"id":"https://openalex.org/keywords/manner-of-articulation","display_name":"Manner of articulation","score":0.6391603946685791},{"id":"https://openalex.org/keywords/place-of-articulation","display_name":"Place of articulation","score":0.62702876329422},{"id":"https://openalex.org/keywords/transition","display_name":"Transition (genetics)","score":0.5339969396591187},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49127262830734253},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4445454776287079},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4340302050113678},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4104927182197571},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3259744644165039},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32001352310180664},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2939779758453369},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2169966995716095}],"concepts":[{"id":"https://openalex.org/C2779337067","wikidata":"https://www.wikidata.org/wiki/Q4800961","display_name":"Articulation (sociology)","level":3,"score":0.839250922203064},{"id":"https://openalex.org/C2778203577","wikidata":"https://www.wikidata.org/wiki/Q38035","display_name":"Consonant","level":3,"score":0.7689538598060608},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.7627099752426147},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.6646038293838501},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.659197986125946},{"id":"https://openalex.org/C66029223","wikidata":"https://www.wikidata.org/wiki/Q210847","display_name":"Manner of articulation","level":2,"score":0.6391603946685791},{"id":"https://openalex.org/C36933642","wikidata":"https://www.wikidata.org/wiki/Q214090","display_name":"Place of articulation","level":4,"score":0.62702876329422},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.5339969396591187},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49127262830734253},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4445454776287079},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4340302050113678},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4104927182197571},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3259744644165039},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32001352310180664},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2939779758453369},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2169966995716095},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","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}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/taslp.2022.3209937","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3209937","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},{"id":"pmid:36712557","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/36712557","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM transactions on audio, speech, and language processing","raw_type":null},{"id":"pmh:oai:arXiv.org:2203.10054","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.10054","pdf_url":"https://arxiv.org/pdf/2203.10054","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},{"id":"pmh:oai:pubmedcentral.nih.gov:9879020","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9879020","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE/ACM Trans Audio Speech Lang Process","raw_type":"Text"},{"id":"doi:10.48550/arxiv.2203.10054","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2203.10054","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2203.10054","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2203.10054","pdf_url":"https://arxiv.org/pdf/2203.10054","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W14146365","https://openalex.org/W134744901","https://openalex.org/W1494198834","https://openalex.org/W1553115114","https://openalex.org/W1707296401","https://openalex.org/W1973664945","https://openalex.org/W1977643007","https://openalex.org/W2024946937","https://openalex.org/W2030909238","https://openalex.org/W2032759346","https://openalex.org/W2046764647","https://openalex.org/W2064610785","https://openalex.org/W2077581463","https://openalex.org/W2077814521","https://openalex.org/W2079641914","https://openalex.org/W2118225053","https://openalex.org/W2128144746","https://openalex.org/W2136884102","https://openalex.org/W2139008940","https://openalex.org/W2174736112","https://openalex.org/W2747874407","https://openalex.org/W2888954148","https://openalex.org/W2898999375","https://openalex.org/W2938850633","https://openalex.org/W2940925973","https://openalex.org/W2962858109","https://openalex.org/W2963448630","https://openalex.org/W2990555328","https://openalex.org/W2997477382","https://openalex.org/W3047775423","https://openalex.org/W3110175868","https://openalex.org/W3135041399","https://openalex.org/W3196861376","https://openalex.org/W3208504364","https://openalex.org/W6631362777","https://openalex.org/W6803793192"],"related_works":["https://openalex.org/W310111","https://openalex.org/W924084","https://openalex.org/W7410956","https://openalex.org/W4019956","https://openalex.org/W9878820","https://openalex.org/W12518202","https://openalex.org/W10932266","https://openalex.org/W7316513","https://openalex.org/W11778797","https://openalex.org/W4051035"],"abstract_inverted_index":{"Spectro-temporal":[0],"dynamics":[1],"of":[2,24,50,79,89,98],"consonant-vowel":[3],"(CV)":[4],"transition":[5],"regions":[6,63],"are":[7],"considered":[8],"to":[9,14,56],"provide":[10],"robust":[11],"cues":[12],"related":[13],"articulation.":[15],"In":[16],"this":[17],"work,":[18],"we":[19],"propose":[20],"an":[21],"objective":[22,29],"measure":[23,31],"precise":[25],"articulation,":[26],"dubbed":[27],"the":[28,35,48,69,87],"articulation":[30],"(OAM),":[32],"by":[33],"analyzing":[34],"CV":[36,62],"transitions":[37],"segmented":[38],"around":[39],"vowel":[40],"onsets.":[41],"The":[42],"OAM":[43,70],"is":[44,71],"derived":[45],"based":[46],"on":[47],"posteriors":[49],"a":[51,77,96],"convolutional":[52],"neural":[53],"network":[54],"pre-trained":[55],"classify":[57],"between":[58],"different":[59],"consonants":[60],"using":[61],"as":[64],"input.":[65],"We":[66],"demonstrate":[67],"that":[68],"correlated":[72],"with":[73,91],"perceptual":[74],"measures":[75],"in":[76],"variety":[78],"contexts":[80],"including":[81],"(a)":[82],"adult":[83],"dysarthric":[84],"speech,":[85],"(b)":[86],"speech":[88,101],"children":[90],"cleft":[92],"lip/palate,":[93],"and":[94,105],"(c)":[95],"database":[97],"accented":[99],"English":[100],"from":[102],"native":[103],"Mandarin":[104],"Spanish":[106],"speakers.":[107]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2022-04-03T00:00:00"}
