{"id":"https://openalex.org/W4224919343","doi":"https://doi.org/10.1109/icassp43922.2022.9746804","title":"Improving the Classification of Phonetic Segments from Raw Ultrasound Using Self-Supervised Learning and Hard Example Mining","display_name":"Improving the Classification of Phonetic Segments from Raw Ultrasound Using Self-Supervised Learning and Hard Example Mining","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4224919343","doi":"https://doi.org/10.1109/icassp43922.2022.9746804"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9746804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746804","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/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 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/A5100670646","display_name":"Meng Jiang","orcid":"https://orcid.org/0000-0003-0509-8927"},"institutions":[{"id":"https://openalex.org/I165911609","display_name":"Changsha Medical University","ror":"https://ror.org/05dt7z971","country_code":"CN","type":"education","lineage":["https://openalex.org/I165911609"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meng Jiang","raw_affiliation_strings":["Changsha Medical University,Changsha,China","Changsha Medical University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Changsha Medical University,Changsha,China","institution_ids":["https://openalex.org/I165911609"]},{"raw_affiliation_string":"Changsha Medical University, Changsha, China","institution_ids":["https://openalex.org/I165911609"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003123879","display_name":"Liang Cheng","orcid":null},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]},{"id":"https://openalex.org/I4210159865","display_name":"Xiangya Hospital Central South University","ror":"https://ror.org/05c1yfj14","country_code":"CN","type":"healthcare","lineage":["https://openalex.org/I4210159865"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Cheng","raw_affiliation_strings":["Central South University,Xiangya Hospital,Changsha,China","Xiangya Hospital, Central South University, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University,Xiangya Hospital,Changsha,China","institution_ids":["https://openalex.org/I4210159865","https://openalex.org/I139660479"]},{"raw_affiliation_string":"Xiangya Hospital, Central South University, Changsha, China","institution_ids":["https://openalex.org/I4210159865","https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051680867","display_name":"Yong Dou","orcid":"https://orcid.org/0000-0002-1256-8934"},"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":"Yong Dou","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":"last","author":{"id":"https://openalex.org/A5050791552","display_name":"Jinjia Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I39333907","display_name":"Yanshan University","ror":"https://ror.org/02txfnf15","country_code":"CN","type":"education","lineage":["https://openalex.org/I39333907"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinjia Wang","raw_affiliation_strings":["Yanshan University,Qinhuangdao,China","Yanshan University, Qinhuangdao, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Yanshan University,Qinhuangdao,China","institution_ids":["https://openalex.org/I39333907"]},{"raw_affiliation_string":"Yanshan University, Qinhuangdao, China","institution_ids":["https://openalex.org/I39333907"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.0382,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.77768354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8262","last_page":"8266"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9973999857902527,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9950000047683716,"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":0.8110916614532471},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6050021052360535},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5405375957489014},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.52577805519104},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.520735502243042},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.48610734939575195},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.48177024722099304},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.44567960500717163},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.4289235472679138},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4111087918281555},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3992927372455597},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3786017894744873},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3728017508983612},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.32973477244377136},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.12098437547683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8110916614532471},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6050021052360535},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5405375957489014},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.52577805519104},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.520735502243042},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.48610734939575195},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.48177024722099304},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.44567960500717163},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.4289235472679138},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4111087918281555},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3992927372455597},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3786017894744873},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3728017508983612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32973477244377136},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.12098437547683716},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9746804","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9746804","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.8199999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1995440941","https://openalex.org/W2129160496","https://openalex.org/W2152262131","https://openalex.org/W2160537405","https://openalex.org/W2397670449","https://openalex.org/W2603597171","https://openalex.org/W2623570296","https://openalex.org/W2723896375","https://openalex.org/W2889418448","https://openalex.org/W2901322269","https://openalex.org/W2939800755","https://openalex.org/W2963272864","https://openalex.org/W2963351448","https://openalex.org/W2984833982","https://openalex.org/W3005680577","https://openalex.org/W3035060554","https://openalex.org/W3171007011","https://openalex.org/W4288279674","https://openalex.org/W6638667902","https://openalex.org/W6740755497","https://openalex.org/W6766188099","https://openalex.org/W6770003738","https://openalex.org/W6774314701","https://openalex.org/W6779326418"],"related_works":["https://openalex.org/W4206357785","https://openalex.org/W3192840557","https://openalex.org/W4281381188","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3023427754","https://openalex.org/W4375928479","https://openalex.org/W3131673289","https://openalex.org/W3198847674","https://openalex.org/W3096913503"],"abstract_inverted_index":{"Ultrasound":[0],"tongue":[1],"imaging":[2],"is":[3,32,58,97,116],"an":[4,14],"attractive":[5],"way":[6],"for":[7,17,34,53,75],"speech":[8],"production":[9],"study":[10,167],"as":[11],"it":[12,57],"provides":[13],"effective":[15],"visualization":[16],"the":[18,54,68,76,101,106,120,124,130,136,139,152,156,166],"vocal":[19],"tract.":[20],"Automatic":[21],"classification":[22,77],"of":[23,82,123],"phonetic":[24],"segments":[25],"(tongue":[26],"shapes)":[27],"from":[28],"raw":[29],"ultrasound":[30],"data":[31,69],"vital":[33],"further":[35],"interpretation.":[36],"Recently,":[37],"deep":[38],"learning-based":[39],"approaches":[40],"have":[41],"been":[42],"adopted":[43,98],"in":[44,64,168],"this":[45,86,169],"task,":[46,78],"which":[47],"required":[48],"a":[49],"large-scale":[50],"annotated":[51],"dataset":[52,143],"training,":[55],"and":[56,104,159],"not":[59],"easy":[60],"to":[61,80,90,99,118],"be":[62],"obtained":[63],"practical":[65],"settings.":[66],"Moreover,":[67],"may":[70],"contain":[71],"many":[72],"hard":[73,113],"examples":[74],"due":[79],"contamination":[81],"speckle":[83],"noise.":[84],"In":[85],"paper,":[87],"we":[88,134,171],"aim":[89],"address":[91],"these":[92],"issues:":[93],"firstly,":[94],"self-supervised":[95],"learning":[96,121],"utilize":[100],"unlabeled":[102],"datasets":[103],"extract":[105],"features":[107],"without":[108],"any":[109],"human":[110],"annotations;":[111],"secondly,":[112],"example":[114],"mining":[115],"applied":[117],"imitate":[119],"path":[122],"clinical":[125],"linguists.":[126],"To":[127,163],"empirically":[128],"demonstrate":[129],"proposed":[131,153],"method\u2019s":[132],"effectiveness,":[133],"evaluate":[135],"method":[137,154],"on":[138],"Ultrax":[140],"Typically":[141],"Developing":[142],"(UXTD)":[144],"under":[145],"different":[146],"scenarios.":[147],"The":[148],"results":[149],"show":[150],"that":[151],"outperforms":[155],"other":[157],"methods":[158],"achieves":[160],"superior":[161],"performance.":[162],"better":[164],"promote":[165],"field,":[170],"release":[172],"our":[173],"code":[174],"publicly":[175],"at":[176],"<sup":[177],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[178],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>":[179],".":[180]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}