{"id":"https://openalex.org/W4372348302","doi":"https://doi.org/10.1109/icassp49357.2023.10095156","title":"Raw Ultrasound-Based Phonetic Segments Classification Via Mask Modeling","display_name":"Raw Ultrasound-Based Phonetic Segments Classification Via Mask Modeling","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4372348302","doi":"https://doi.org/10.1109/icassp49357.2023.10095156"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10095156","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5005516309","display_name":"Kang Soo You","orcid":"https://orcid.org/0009-0009-5685-2521"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang You","raw_affiliation_strings":["Tongji University,Shanghai,China","Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461621","display_name":"Bo Liu","orcid":"https://orcid.org/0000-0002-0894-1054"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Liu","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National Key Lab of Parallel and Distributed Processing, Changsha, China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Lab of Parallel and Distributed Processing, Changsha, China","institution_ids":[]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013340793","display_name":"Kele Xu","orcid":"https://orcid.org/0000-0001-5997-5169"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kele Xu","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National Key Lab of Parallel and Distributed Processing, Changsha, China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Lab of Parallel and Distributed Processing, Changsha, China","institution_ids":[]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027048094","display_name":"Yunsheng Xiong","orcid":"https://orcid.org/0000-0002-1360-575X"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsheng Xiong","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China","National Key Lab of Parallel and Distributed Processing, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Lab of Parallel and Distributed Processing, Changsha, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047948744","display_name":"Qisheng Xu","orcid":"https://orcid.org/0000-0003-4141-5950"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qisheng Xu","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National University of Defense Technology, Changsha, China","National Key Lab of Parallel and Distributed Processing, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Lab of Parallel and Distributed Processing, Changsha, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026070862","display_name":"Ming Feng","orcid":"https://orcid.org/0000-0001-9943-5941"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming Feng","raw_affiliation_strings":["Tongji University,Shanghai,China","Tongji University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tongji University,Shanghai,China","institution_ids":["https://openalex.org/I116953780"]},{"raw_affiliation_string":"Tongji University, Shanghai, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016031960","display_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","orcid":"https://orcid.org/0000-0003-4375-7524"},"institutions":[{"id":"https://openalex.org/I29770179","display_name":"Budapest University of Technology and Economics","ror":"https://ror.org/02w42ss30","country_code":"HU","type":"education","lineage":["https://openalex.org/I29770179"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tam\u00e1s G\u00e1bor Csap\u00f3","raw_affiliation_strings":["Budapest University of Technology and Economics,Budapest,Hungary","Budapest University of Technology and Economics, Budapest, Hungary"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Budapest University of Technology and Economics,Budapest,Hungary","institution_ids":["https://openalex.org/I29770179"]},{"raw_affiliation_string":"Budapest University of Technology and Economics, Budapest, Hungary","institution_ids":["https://openalex.org/I29770179"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018669598","display_name":"Boqing Zhu","orcid":"https://orcid.org/0000-0001-7867-2112"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boqing Zhu","raw_affiliation_strings":["National University of Defense Technology,Changsha,China","National Key Lab of Parallel and Distributed Processing, Changsha, China","National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Defense Technology,Changsha,China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"National Key Lab of Parallel and Distributed Processing, Changsha, China","institution_ids":[]},{"raw_affiliation_string":"National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"abs 1907 835","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9965999722480774,"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":0.9965999722480774,"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/T10863","display_name":"Voice and Speech Disorders","score":0.9925000071525574,"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/T10860","display_name":"Speech and Audio Processing","score":0.987500011920929,"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":0.8267802000045776},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6920616030693054},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6580265760421753},{"id":"https://openalex.org/keywords/masking","display_name":"Masking (illustration)","score":0.577722430229187},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5299804210662842},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5174058675765991},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4613819718360901},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4582478404045105},{"id":"https://openalex.org/keywords/task-analysis","display_name":"Task analysis","score":0.42082875967025757},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.41299107670783997},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40691837668418884},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4065319895744324},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.40382492542266846},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.39124807715415955},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3820876479148865}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8267802000045776},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6920616030693054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6580265760421753},{"id":"https://openalex.org/C2777402240","wikidata":"https://www.wikidata.org/wiki/Q6783436","display_name":"Masking (illustration)","level":2,"score":0.577722430229187},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5299804210662842},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5174058675765991},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4613819718360901},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4582478404045105},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.42082875967025757},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.41299107670783997},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40691837668418884},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4065319895744324},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.40382492542266846},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.39124807715415955},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3820876479148865},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10095156","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10095156","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.8500000238418579}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1964413222","https://openalex.org/W1995440941","https://openalex.org/W2008120082","https://openalex.org/W2129160496","https://openalex.org/W2397670449","https://openalex.org/W2603597171","https://openalex.org/W2623570296","https://openalex.org/W2802863253","https://openalex.org/W2889418448","https://openalex.org/W2939800755","https://openalex.org/W2963272864","https://openalex.org/W2981351925","https://openalex.org/W3094502228","https://openalex.org/W3171007011","https://openalex.org/W4224919343","https://openalex.org/W4312804044","https://openalex.org/W4313156423","https://openalex.org/W4386065386","https://openalex.org/W6679032535","https://openalex.org/W6754361310","https://openalex.org/W6784333009","https://openalex.org/W6838376339"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W4321369474","https://openalex.org/W2731899572","https://openalex.org/W3133861977","https://openalex.org/W2915754718","https://openalex.org/W4299822940","https://openalex.org/W2279398222","https://openalex.org/W4246751904","https://openalex.org/W3000866861","https://openalex.org/W2955560448"],"abstract_inverted_index":{"Ultrasound":[0],"tongue":[1,30],"imaging":[2],"is":[3,49],"widely":[4,21],"used":[5,22],"in":[6,23,54,139],"clinical":[7],"linguistics":[8],"and":[9,26],"phonetics.":[10],"Recently,":[11],"deep":[12,37],"neural":[13,17,102],"networks,":[14,18],"especially":[15],"convolutional":[16],"have":[19],"been":[20],"the":[24,77,94,101,111,123,131],"interpretation":[25],"analysis":[27],"of":[28,44,71,79,118,137],"ultrasound":[29],"images":[31],"(UTI).":[32],"Despite":[33],"achieving":[34],"satisfactory":[35],"performance,":[36],"models":[38],"rely":[39],"on":[40,64],"a":[41,68,115],"large":[42,69],"amount":[43,70,117],"manually":[45],"labeled":[46,119],"data,":[47],"which":[48],"often":[50],"difficult":[51],"to":[52,66,75,104],"obtain":[53],"practical":[55],"settings.":[56],"To":[57],"address":[58],"this":[59,61],"issue,":[60],"paper":[62],"focuses":[63],"how":[65],"utilize":[67],"unlabeled":[72],"UTI":[73,80],"data":[74],"improve":[76,130],"performance":[78],"classification":[81,132],"task.":[82],"Specifically,":[83],"we":[84,109],"explore":[85],"self-supervised":[86],"learning":[87],"with":[88,114,122],"masking":[89],"modeling":[90],"strategy.":[91],"By":[92],"predicting":[93],"masked":[95],"part,":[96],"our":[97,127],"pre-trained":[98,112],"model":[99,113],"enables":[100],"network":[103],"infer":[105],"contextual":[106],"information.":[107],"Then,":[108],"fine-tune":[110],"small":[116],"data.":[120],"Compared":[121],"previous":[124],"competing":[125],"algorithms,":[126],"method":[128],"can":[129],"accuracy":[133],"by":[134],"an":[135],"average":[136],"13.33%":[138],"four":[140],"different":[141],"scenarios.":[142]},"counts_by_year":[{"year":2024,"cited_by_count":4}],"updated_date":"2026-07-25T09:21:30.201066","created_date":"2025-10-10T00:00:00"}