{"id":"https://openalex.org/W4403182924","doi":"https://doi.org/10.1109/taslp.2024.3473316","title":"Audio-Only Phonetic Segment Classification Using Embeddings Learned From Audio and Ultrasound Tongue Imaging Data","display_name":"Audio-Only Phonetic Segment Classification Using Embeddings Learned From Audio and Ultrasound Tongue Imaging Data","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403182924","doi":"https://doi.org/10.1109/taslp.2024.3473316"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3473316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3473316","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/A5104971371","display_name":"Ilhan Aytutuldu","orcid":null},"institutions":[{"id":"https://openalex.org/I109297418","display_name":"Gebze Technical University","ror":"https://ror.org/01sdnnq10","country_code":"TR","type":"education","lineage":["https://openalex.org/I109297418"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Ilhan Aytutuldu","raw_affiliation_strings":["Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye","Department of Computer Engineering, Gebze Technical University 41400 Gebze/KOCAELI, Turkey"],"raw_orcid":"https://orcid.org/0000-0003-4237-8442","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye","institution_ids":["https://openalex.org/I109297418"]},{"raw_affiliation_string":"Department of Computer Engineering, Gebze Technical University 41400 Gebze/KOCAELI, Turkey","institution_ids":["https://openalex.org/I109297418"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010447124","display_name":"Yakup Gen\u00e7","orcid":"https://orcid.org/0000-0002-6952-6735"},"institutions":[{"id":"https://openalex.org/I109297418","display_name":"Gebze Technical University","ror":"https://ror.org/01sdnnq10","country_code":"TR","type":"education","lineage":["https://openalex.org/I109297418"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Yakup Genc","raw_affiliation_strings":["Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye","Department of Computer Engineering, Gebze Technical University 41400 Gebze/KOCAELI, Turkey"],"raw_orcid":"https://orcid.org/0000-0002-6952-6735","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye","institution_ids":["https://openalex.org/I109297418"]},{"raw_affiliation_string":"Department of Computer Engineering, Gebze Technical University 41400 Gebze/KOCAELI, Turkey","institution_ids":["https://openalex.org/I109297418"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076768060","display_name":"Yusuf Sinan Akg\u00fcl","orcid":"https://orcid.org/0000-0001-8501-4812"},"institutions":[{"id":"https://openalex.org/I109297418","display_name":"Gebze Technical University","ror":"https://ror.org/01sdnnq10","country_code":"TR","type":"education","lineage":["https://openalex.org/I109297418"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Yusuf Sinan Akgul","raw_affiliation_strings":["Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye","Department of Computer Engineering, Gebze Technical University 41400 Gebze/KOCAELI, Turkey"],"raw_orcid":"https://orcid.org/0000-0001-8501-4812","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Gebze Technical University, Gebze, Türkiye","institution_ids":["https://openalex.org/I109297418"]},{"raw_affiliation_string":"Department of Computer Engineering, Gebze Technical University 41400 Gebze/KOCAELI, Turkey","institution_ids":["https://openalex.org/I109297418"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I109297418"],"apc_list":null,"apc_paid":null,"fwci":0.5972,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.74108531,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"4501","last_page":"4510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9437000155448914,"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":0.9437000155448914,"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/tongue","display_name":"Tongue","score":0.5750246047973633},{"id":"https://openalex.org/keywords/audio-visual","display_name":"Audio visual","score":0.5458186268806458},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5098468661308289},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49999070167541504},{"id":"https://openalex.org/keywords/ultrasound-imaging","display_name":"Ultrasound imaging","score":0.4738776385784149},{"id":"https://openalex.org/keywords/audio-analyzer","display_name":"Audio analyzer","score":0.44220057129859924},{"id":"https://openalex.org/keywords/ultrasound","display_name":"Ultrasound","score":0.43782421946525574},{"id":"https://openalex.org/keywords/audio-signal","display_name":"Audio signal","score":0.3076915144920349},{"id":"https://openalex.org/keywords/acoustics","display_name":"Acoustics","score":0.2396564781665802},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.23698893189430237},{"id":"https://openalex.org/keywords/audio-signal-processing","display_name":"Audio signal processing","score":0.21498051285743713},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.1907849907875061},{"id":"https://openalex.org/keywords/speech-coding","display_name":"Speech coding","score":0.12993144989013672},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.06319034099578857}],"concepts":[{"id":"https://openalex.org/C2779744641","wikidata":"https://www.wikidata.org/wiki/Q9614","display_name":"Tongue","level":2,"score":0.5750246047973633},{"id":"https://openalex.org/C3017588708","wikidata":"https://www.wikidata.org/wiki/Q758901","display_name":"Audio visual","level":2,"score":0.5458186268806458},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5098468661308289},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49999070167541504},{"id":"https://openalex.org/C2986892559","wikidata":"https://www.wikidata.org/wiki/Q234904","display_name":"Ultrasound imaging","level":3,"score":0.4738776385784149},{"id":"https://openalex.org/C160372630","wikidata":"https://www.wikidata.org/wiki/Q4819855","display_name":"Audio analyzer","level":5,"score":0.44220057129859924},{"id":"https://openalex.org/C143753070","wikidata":"https://www.wikidata.org/wiki/Q162564","display_name":"Ultrasound","level":2,"score":0.43782421946525574},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.3076915144920349},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.2396564781665802},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.23698893189430237},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.21498051285743713},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.1907849907875061},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.12993144989013672},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.06319034099578857},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3473316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3473316","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":0.7099999785423279,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":54,"referenced_works":["https://openalex.org/W1536341998","https://openalex.org/W1595584206","https://openalex.org/W1981207086","https://openalex.org/W1985579076","https://openalex.org/W1995440941","https://openalex.org/W2022423195","https://openalex.org/W2028687274","https://openalex.org/W2053421158","https://openalex.org/W2089207444","https://openalex.org/W2104095591","https://openalex.org/W2126468446","https://openalex.org/W2136223099","https://openalex.org/W2145056192","https://openalex.org/W2152262131","https://openalex.org/W2163164853","https://openalex.org/W2265744734","https://openalex.org/W2291710599","https://openalex.org/W2329227418","https://openalex.org/W2404317780","https://openalex.org/W2406959878","https://openalex.org/W2490959726","https://openalex.org/W2501279594","https://openalex.org/W2502847729","https://openalex.org/W2565110584","https://openalex.org/W2619383789","https://openalex.org/W2746999397","https://openalex.org/W2772633765","https://openalex.org/W2775432161","https://openalex.org/W2887522866","https://openalex.org/W2888336199","https://openalex.org/W2889418448","https://openalex.org/W2896599145","https://openalex.org/W2896950961","https://openalex.org/W2901322269","https://openalex.org/W2939800755","https://openalex.org/W2951841298","https://openalex.org/W2981643801","https://openalex.org/W2981842355","https://openalex.org/W3005329674","https://openalex.org/W3015480556","https://openalex.org/W3085051942","https://openalex.org/W3110147986","https://openalex.org/W3143787022","https://openalex.org/W3180179387","https://openalex.org/W4225406964","https://openalex.org/W4252648610","https://openalex.org/W4286278015","https://openalex.org/W4377240112","https://openalex.org/W6686207219","https://openalex.org/W6688268161","https://openalex.org/W6725830792","https://openalex.org/W6753585016","https://openalex.org/W6756285404","https://openalex.org/W6776139684"],"related_works":["https://openalex.org/W2098934641","https://openalex.org/W4402262758","https://openalex.org/W1996547972","https://openalex.org/W3096250625","https://openalex.org/W3011716530","https://openalex.org/W2139941521","https://openalex.org/W2794811190","https://openalex.org/W4308222513","https://openalex.org/W2363866404","https://openalex.org/W9205999"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3],"phonetic":[4],"segment":[5],"classification":[6],"method":[7,77],"based":[8],"on":[9,50],"joint":[10],"embeddings":[11,41],"learned":[12],"from":[13,44],"processing":[14],"Ultrasound":[15],"Tongue":[16],"Imaging":[17],"(UTI)":[18],"and":[19,89],"audio":[20,34,59,88,99],"data.":[21,91],"For":[22],"constructing":[23],"the":[24,95],"embeddings,":[25],"we":[26],"compiled":[27],"an":[28],"ultrasound":[29,69],"image":[30],"dataset":[31],"synchronized":[32],"with":[33],"that":[35,75,84],"encompasses":[36],"common":[37],"speech":[38,65],"scenarios.":[39],"The":[40],"are":[42],"obtained":[43],"artificial":[45],"neural":[46],"network":[47],"models":[48],"trained":[49],"this":[51],"dataset.":[52],"During":[53],"testing,":[54],"our":[55,76],"model":[56],"processes":[57],"only":[58],"data,":[60],"making":[61],"it":[62,93],"practical":[63],"for":[64],"therapy":[66],"as":[67],"no":[68],"imaging":[70],"is":[71],"required.":[72],"Experiments":[73],"show":[74],"yields":[78],"similar":[79],"performance":[80],"compared":[81],"to":[82],"methods":[83,96],"simultaneously":[85],"use":[86],"both":[87],"UTI":[90,101],"However,":[92],"outperforms":[94],"utilizing":[97],"solely":[98],"or":[100],"data":[102],"in":[103],"real-time":[104],"classification.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}