{"id":"https://openalex.org/W4285821278","doi":"https://doi.org/10.1109/taslp.2022.3192096","title":"Modeling Concurrent Vowel Scores Using the Time Delay Neural Network and Multitask Learning","display_name":"Modeling Concurrent Vowel Scores Using the Time Delay Neural Network and Multitask Learning","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4285821278","doi":"https://doi.org/10.1109/taslp.2022.3192096"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2022.3192096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3192096","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":["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/A5073629131","display_name":"Atharva Anand Joshi","orcid":"https://orcid.org/0000-0002-9554-3467"},"institutions":[{"id":"https://openalex.org/I74796645","display_name":"Birla Institute of Technology and Science, Pilani","ror":"https://ror.org/001p3jz28","country_code":"IN","type":"education","lineage":["https://openalex.org/I74796645"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Atharva Anand Joshi","raw_affiliation_strings":["Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science, Vidya Vihar, Rajasthan, India"],"raw_orcid":"https://orcid.org/0000-0002-9554-3467","affiliations":[{"raw_affiliation_string":"Department of Electrical and Electronics Engineering, Birla Institute of Technology and Science, Vidya Vihar, Rajasthan, India","institution_ids":["https://openalex.org/I74796645"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017706358","display_name":"Harshavardhan Settibhaktini","orcid":"https://orcid.org/0000-0003-4441-2018"},"institutions":[{"id":"https://openalex.org/I885392262","display_name":"GITAM University","ror":"https://ror.org/0440p1d37","country_code":"IN","type":"education","lineage":["https://openalex.org/I885392262"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Harshavardhan Settibhaktini","raw_affiliation_strings":["Department of Electrical, Electronics, and Communication Engineering, GITAM School of Technology, GITAM Deemed to be University, Visakhapatnam, Andhra Pradesh, India","Department of Electrical, Electronics, and Communication Engineering and GITAM School of Technology, GITAM Deemed to be University, Visakhapatnam, Andhra Pradesh, India"],"raw_orcid":"https://orcid.org/0000-0003-4441-2018","affiliations":[{"raw_affiliation_string":"Department of Electrical, Electronics, and Communication Engineering, GITAM School of Technology, GITAM Deemed to be University, Visakhapatnam, Andhra Pradesh, India","institution_ids":["https://openalex.org/I885392262"]},{"raw_affiliation_string":"Department of Electrical, Electronics, and Communication Engineering and GITAM School of Technology, GITAM Deemed to be University, Visakhapatnam, Andhra Pradesh, India","institution_ids":["https://openalex.org/I885392262"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010108963","display_name":"Ananthakrishna Chintanpalli","orcid":"https://orcid.org/0000-0002-2310-3366"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ananthakrishna Chintanpalli","raw_affiliation_strings":["Department of Communication Engineering, School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India","Department of Communication Engineering and School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India"],"raw_orcid":"https://orcid.org/0000-0002-2310-3366","affiliations":[{"raw_affiliation_string":"Department of Communication Engineering, School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India","institution_ids":["https://openalex.org/I876193797"]},{"raw_affiliation_string":"Department of Communication Engineering and School of Electronics Engineering, Vellore Institute of Technology, Vellore, Tamil Nadu, India","institution_ids":["https://openalex.org/I876193797"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5073629131"],"corresponding_institution_ids":["https://openalex.org/I74796645"],"apc_list":null,"apc_paid":null,"fwci":0.4709,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.59582811,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"30","issue":null,"first_page":"2452","last_page":"2459"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10283","display_name":"Hearing Loss and Rehabilitation","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.9973000288009644,"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/artificial-neural-network","display_name":"Artificial neural network","score":0.6950035691261292},{"id":"https://openalex.org/keywords/vowel","display_name":"Vowel","score":0.6584344506263733},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5863021612167358},{"id":"https://openalex.org/keywords/formant","display_name":"Formant","score":0.5762637257575989},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4959181249141693},{"id":"https://openalex.org/keywords/time-delay-neural-network","display_name":"Time delay neural network","score":0.49218884110450745},{"id":"https://openalex.org/keywords/multilayer-perceptron","display_name":"Multilayer perceptron","score":0.43948304653167725},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3680219054222107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.328804075717926}],"concepts":[{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6950035691261292},{"id":"https://openalex.org/C2779581591","wikidata":"https://www.wikidata.org/wiki/Q36244","display_name":"Vowel","level":2,"score":0.6584344506263733},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5863021612167358},{"id":"https://openalex.org/C158215666","wikidata":"https://www.wikidata.org/wiki/Q1414685","display_name":"Formant","level":3,"score":0.5762637257575989},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4959181249141693},{"id":"https://openalex.org/C175202392","wikidata":"https://www.wikidata.org/wiki/Q2434543","display_name":"Time delay neural network","level":3,"score":0.49218884110450745},{"id":"https://openalex.org/C179717631","wikidata":"https://www.wikidata.org/wiki/Q2991667","display_name":"Multilayer perceptron","level":3,"score":0.43948304653167725},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3680219054222107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.328804075717926}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2022.3192096","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2022.3192096","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7200000286102295,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1533861849","https://openalex.org/W1973996018","https://openalex.org/W1991139021","https://openalex.org/W1991579311","https://openalex.org/W1992019050","https://openalex.org/W1999864628","https://openalex.org/W1999885698","https://openalex.org/W2021736981","https://openalex.org/W2027468870","https://openalex.org/W2037752682","https://openalex.org/W2047306924","https://openalex.org/W2075774708","https://openalex.org/W2080639443","https://openalex.org/W2083514449","https://openalex.org/W2084598301","https://openalex.org/W2094962869","https://openalex.org/W2117671523","https://openalex.org/W2120113977","https://openalex.org/W2144345993","https://openalex.org/W2145617582","https://openalex.org/W2161851299","https://openalex.org/W2171061694","https://openalex.org/W2402146185","https://openalex.org/W2519091744","https://openalex.org/W2560479584","https://openalex.org/W2781404744","https://openalex.org/W2787124848","https://openalex.org/W2931364255","https://openalex.org/W3045751139","https://openalex.org/W3089738468","https://openalex.org/W3162806159","https://openalex.org/W3203726367","https://openalex.org/W3213355738","https://openalex.org/W4256399001","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W2028715205","https://openalex.org/W2344358524","https://openalex.org/W2060888333","https://openalex.org/W2053092242","https://openalex.org/W2028342517","https://openalex.org/W3042758298","https://openalex.org/W2050311283","https://openalex.org/W2942435052","https://openalex.org/W3169184738","https://openalex.org/W2007544974"],"abstract_inverted_index":{"The":[0,42,65,81,101,120,135,145,159,182,221],"difference":[1,35,89],"in":[2,109,154,216],"fundamental":[3],"frequency":[4],"(F0)":[5],"between":[6],"vowels":[7,30,75,114,151,210,233],"is":[8],"a":[9,46,51,86],"segregation":[10,111],"cue":[11],"for":[12],"identifying":[13],"concurrent":[14,62,74,113,209,232],"vowels.":[15,119],"Younger":[16],"listeners":[17],"with":[18,32,170,175],"normal":[19],"hearing":[20,248],"(YNH)":[21],"showed":[22],"that":[23,163,198],"the":[24,61,68,78,91,97,104,110,128,132,140,156,164,171,187,199,204,208,218,228],"percent":[25],"identification":[26,190],"score":[27,92,99],"of":[28,50,73,112,131,149,207],"both":[29,150],"improved":[31],"increasing":[33],"F0":[34,40,88,143,193,212],"and":[36,55,107,117,178,192,240,242,247],"asymptoted":[37],"at":[38,85],"higher":[39],"difference.":[41],"current":[43],"study":[44],"developed":[45],"deep-neural-network":[47],"model":[48,147,166],"consisting":[49],"time-delay":[52],"neural":[53],"network":[54],"multitask":[56],"learning":[57],"(TDNN-MTL)":[58],"to":[59,67,96,126,226],"predict":[60],"vowel":[63,189,238],"scores.":[64,134,158,220],"input":[66],"TDNN-MTL":[69,82,102,136,146,165,183,201,222],"were":[70,152],"temporal":[71],"responses":[72],"obtained":[76,234],"using":[77],"auditory-nerve":[79],"model.":[80],"was":[83,124,137],"trained":[84,200],"3-Hz":[87],"until":[90],"(80%)":[93],"became":[94],"closer":[95],"YNH":[98,133,157,172,219],"(85%).":[100],"learned":[103],"formant":[105,205],"coding":[106,206],"aided":[108,215],"into":[115],"dominant":[116],"recessive":[118],"total":[121],"weighted":[122],"loss":[123],"tailored":[125],"mimic":[127],"dominant-recessive":[129],"relationship":[130],"tested":[138],"against":[139],"other":[141,176],"five":[142],"differences.":[144],"scores":[148,167,173,191],"successful":[153],"predicting":[155],"chi-square":[160],"tests":[161],"revealed":[162],"correlated":[168],"well":[169],"compared":[174],"F0-segregation":[177],"multi-layer":[179],"perceptron":[180],"models.":[181],"also":[184],"correctly":[185],"predicted":[186],"one":[188],"benefit.":[194],"These":[195],"findings":[196],"suggest":[197],"accurately":[202],"predicts":[203],"across":[211,235],"differences,":[213],"which":[214],"capturing":[217],"can":[223],"be":[224],"extended":[225],"validate":[227],"behavioral":[229],"studies":[230],"on":[231],"acoustic":[236],"(e.g.,":[237,245],"duration":[239],"level)":[241],"auditory":[243],"changes":[244],"aging":[246],"loss).":[249]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}