{"id":"https://openalex.org/W4225331914","doi":"https://doi.org/10.1109/icassp43922.2022.9747421","title":"Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemic Analysis","display_name":"Temporal Dynamic Convolutional Neural Network for Text-Independent Speaker Verification and Phonemic Analysis","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4225331914","doi":"https://doi.org/10.1109/icassp43922.2022.9747421"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747421","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5085633235","display_name":"Seong-Hu Kim","orcid":"https://orcid.org/0000-0003-3101-8732"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seong-Hu Kim","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Korea","Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068022654","display_name":"Hyeonuk Nam","orcid":"https://orcid.org/0000-0002-1169-5640"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyeonuk Nam","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Korea","Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044559850","display_name":"Yong\u2010Hwa Park","orcid":"https://orcid.org/0000-0003-3519-1321"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yong-Hwa Park","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Korea","Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology,Department of Mechanical Engineering,Korea","institution_ids":["https://openalex.org/I157485424"]},{"raw_affiliation_string":"Department of Mechanical Engineering, Korea Advanced Institute of Science and Technology, Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":2.8025,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":{"value":0.92175987,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6742","last_page":"6746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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/T11309","display_name":"Music and Audio Processing","score":0.9973999857902527,"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":0.8242700099945068},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7438770532608032},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.6141133308410645},{"id":"https://openalex.org/keywords/speaker-verification","display_name":"Speaker verification","score":0.5072960257530212},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.49100854992866516},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.48177096247673035},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.46385952830314636},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4544922709465027},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.43022215366363525},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4232422113418579},{"id":"https://openalex.org/keywords/speaker-recognition","display_name":"Speaker recognition","score":0.3255856931209564},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07710835337638855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8242700099945068},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7438770532608032},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.6141133308410645},{"id":"https://openalex.org/C2982762665","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker verification","level":3,"score":0.5072960257530212},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.49100854992866516},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.48177096247673035},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.46385952830314636},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4544922709465027},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.43022215366363525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4232422113418579},{"id":"https://openalex.org/C133892786","wikidata":"https://www.wikidata.org/wiki/Q1145189","display_name":"Speaker recognition","level":2,"score":0.3255856931209564},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07710835337638855},{"id":"https://openalex.org/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747421","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747421","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320335199","display_name":"Korea Institute of Energy Technology Evaluation and Planning","ror":"https://ror.org/02zq38y32"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1752971345","https://openalex.org/W2111978427","https://openalex.org/W2187089797","https://openalex.org/W2194775991","https://openalex.org/W2516764878","https://openalex.org/W2726515241","https://openalex.org/W2808631503","https://openalex.org/W2890704021","https://openalex.org/W2944388686","https://openalex.org/W2945244898","https://openalex.org/W2953133772","https://openalex.org/W2963870605","https://openalex.org/W2981087920","https://openalex.org/W2981609494","https://openalex.org/W2982101047","https://openalex.org/W3013020904","https://openalex.org/W3024869864","https://openalex.org/W3034421924","https://openalex.org/W3082779874","https://openalex.org/W3097298049","https://openalex.org/W3163505255","https://openalex.org/W3198041020","https://openalex.org/W3204647170","https://openalex.org/W4295312788","https://openalex.org/W6637373629","https://openalex.org/W6716109767","https://openalex.org/W6766978945","https://openalex.org/W6767312599","https://openalex.org/W6771223598","https://openalex.org/W6782351018","https://openalex.org/W6864424756"],"related_works":["https://openalex.org/W2372178361","https://openalex.org/W66821593","https://openalex.org/W2383388535","https://openalex.org/W1521299571","https://openalex.org/W1992908141","https://openalex.org/W3141593045","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W204267554","https://openalex.org/W3133710586"],"abstract_inverted_index":{"In":[0,39,117],"the":[1,12,20,105,113,153],"field":[2],"of":[3,23,29,52,73,80],"text-independent":[4,166],"speaker":[5,106,167],"recognition,":[6],"dynamic":[7,31,45,137],"models":[8,32],"that":[9,48,121],"adapt":[10,65],"along":[11],"time":[13,61,67],"axis":[14],"have":[15],"been":[16],"proposed":[17],"to":[18,59,66,112,141,155],"consider":[19,156],"phoneme-varying":[21],"characteristics":[22],"speech.":[24],"However,":[25],"a":[26],"detailed":[27],"analysis":[28,79],"how":[30,81],"work":[33,84],"depending":[34],"on":[35,85,125],"phonemes":[36,53,87,142],"is":[37,91],"insufficient.":[38],"this":[40],"paper,":[41],"we":[42,119],"propose":[43],"temporal":[44,50,136],"CNN":[46],"(TDY-CNN)":[47],"considers":[49],"variation":[51,158],"by":[54,69,109],"applying":[55,70],"kernels":[56,64,83,98,123],"optimally":[57],"adapting":[58],"each":[60],"bin.":[62],"These":[63],"bins":[68],"weighted":[71],"sum":[72],"trained":[74],"basis":[75,97],"kernels.":[76],"Then,":[77],"an":[78,100],"adaptive":[82,122],"different":[86],"in":[88],"various":[89],"layers":[90],"carried":[92],"out.":[93],"TDY-ResNet-38(\u00d70.5)":[94],"using":[95],"six":[96],"improved":[99],"equal":[101],"error":[102],"rate":[103],"(EER),":[104],"verification":[107],"performance,":[108],"17.3%":[110],"compared":[111],"baseline":[114],"model":[115,138],"ResNet-38(\u00d70.5).":[116],"addition,":[118],"showed":[120],"depend":[124],"phoneme":[126,146,157],"groups":[127],"and":[128,150,164],"are":[129],"more":[130,162],"phoneme-specific":[131],"at":[132],"early":[133],"layers.":[134],"The":[135],"adapts":[139],"itself":[140],"without":[143],"explicitly":[144],"given":[145],"information":[147],"during":[148],"training,":[149],"results":[151],"show":[152],"necessity":[154],"within":[159],"utterances":[160],"for":[161],"accurate":[163],"robust":[165],"verification.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}