{"id":"https://openalex.org/W3134482008","doi":"https://doi.org/10.23919/eusipco54536.2021.9615987","title":"End-to-End Mispronunciation Detection and Diagnosis From Raw Waveforms","display_name":"End-to-End Mispronunciation Detection and Diagnosis From Raw Waveforms","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3134482008","doi":"https://doi.org/10.23919/eusipco54536.2021.9615987","mag":"3134482008"},"language":"en","primary_location":{"id":"doi:10.23919/eusipco54536.2021.9615987","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9615987","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","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/A5081032657","display_name":"Bicheng Yan","orcid":"https://orcid.org/0000-0002-3356-7594"},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Bi-Cheng Yan","raw_affiliation_strings":["Dept. of Computer Science and Information Engineering, National Normal Taiwan University"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Information Engineering, National Normal Taiwan University","institution_ids":["https://openalex.org/I134161618"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115595070","display_name":"Berlin Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I134161618","display_name":"National Taiwan Normal University","ror":"https://ror.org/059dkdx38","country_code":"TW","type":"education","lineage":["https://openalex.org/I134161618"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Berlin Chen","raw_affiliation_strings":["Dept. of Computer Science and Information Engineering, National Normal Taiwan University"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Information Engineering, National Normal Taiwan University","institution_ids":["https://openalex.org/I134161618"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081032657"],"corresponding_institution_ids":["https://openalex.org/I134161618"],"apc_list":null,"apc_paid":null,"fwci":1.7763,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.87606285,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"61","last_page":"65"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9976000189781189,"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":0.9955999851226807,"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/computer-science","display_name":"Computer science","score":0.7848813533782959},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.6978896856307983},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5969938039779663},{"id":"https://openalex.org/keywords/sinc-function","display_name":"Sinc function","score":0.49504366517066956},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.4836024343967438},{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.47952035069465637},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4655070900917053},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.43511539697647095},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4187331199645996},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.08992999792098999}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7848813533782959},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.6978896856307983},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5969938039779663},{"id":"https://openalex.org/C152303783","wikidata":"https://www.wikidata.org/wiki/Q855949","display_name":"Sinc function","level":2,"score":0.49504366517066956},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.4836024343967438},{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.47952035069465637},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4655070900917053},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.43511539697647095},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4187331199645996},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.08992999792098999},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.23919/eusipco54536.2021.9615987","is_oa":false,"landing_page_url":"https://doi.org/10.23919/eusipco54536.2021.9615987","pdf_url":null,"source":{"id":"https://openalex.org/S4363607854","display_name":"2021 29th European Signal Processing Conference (EUSIPCO)","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":"2021 29th European Signal Processing Conference (EUSIPCO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G6568675257","display_name":null,"funder_award_id":"TL-110-D301,110-2634-F-008-004","funder_id":"https://openalex.org/F4320322795","funder_display_name":"Ministry of Science and Technology, Taiwan"}],"funders":[{"id":"https://openalex.org/F4320321559","display_name":"Chunghwa Telecom Laboratories","ror":"https://ror.org/04f786589"},{"id":"https://openalex.org/F4320322795","display_name":"Ministry of Science and Technology, Taiwan","ror":"https://ror.org/02kv4zf79"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W290344559","https://openalex.org/W1635512741","https://openalex.org/W2049905800","https://openalex.org/W2091856355","https://openalex.org/W2127141656","https://openalex.org/W2139008940","https://openalex.org/W2401896499","https://openalex.org/W2552635739","https://openalex.org/W2766219058","https://openalex.org/W2888954148","https://openalex.org/W2901616798","https://openalex.org/W2938359332","https://openalex.org/W2963175699","https://openalex.org/W2972347929","https://openalex.org/W2990413709","https://openalex.org/W3015231007","https://openalex.org/W3095326192","https://openalex.org/W3095473841","https://openalex.org/W3095669552","https://openalex.org/W3097069417","https://openalex.org/W3097395819","https://openalex.org/W3097515180","https://openalex.org/W6712949300","https://openalex.org/W6756859573","https://openalex.org/W6784237427","https://openalex.org/W6784749589","https://openalex.org/W6785072242"],"related_works":["https://openalex.org/W1979693299","https://openalex.org/W2184738069","https://openalex.org/W3107204728","https://openalex.org/W4287591324","https://openalex.org/W2385915439","https://openalex.org/W4226420367","https://openalex.org/W2980176872","https://openalex.org/W2962876041","https://openalex.org/W1531285554","https://openalex.org/W2899027234"],"abstract_inverted_index":{"Mispronunciation":[0],"detection":[1,208],"and":[2,11,45,51,88,96,117,154,238],"diagnosis":[3,239],"(MDD)":[4],"is":[5,21,49,155,170],"designed":[6],"to":[7,15,40,77,111,120,133,148,158,212],"identify":[8],"pronunciation":[9,27],"errors":[10],"provide":[12],"instructive":[13],"feedback":[14],"guide":[16],"non-native":[17,43,173,195],"language":[18,196],"learners,":[19],"which":[20,67,169],"a":[22,59,107,114,121,171],"core":[23],"component":[24],"in":[25,210],"computer-assisted":[26],"training":[28],"(CAPT)":[29],"systems.":[30],"However,":[31],"MDD":[32,104,215],"often":[33],"suffers":[34],"from":[35,140],"the":[36,46,128,141,166,185,220],"data-sparsity":[37],"problem":[38],"due":[39],"that":[41,184,217],"collecting":[42],"data":[44],"associated":[47],"annotations":[48],"time-consuming":[50],"labor-intensive.":[52],"To":[53,100],"address":[54],"this":[55,101],"issue,":[56],"we":[57],"explore":[58],"fully":[60],"end-to-end":[61],"(E2E)":[62],"neural":[63,92,143],"model":[64,105,203,228],"for":[65,178,194],"MDD,":[66],"processes":[68],"learners'":[69],"speech":[70,175],"directly":[71],"based":[72],"on":[73,165,180,233],"raw":[74,82,115],"waveforms.":[75],"Compared":[76],"conventional":[78],"hand-crafted":[79],"acoustic":[80,86,223],"features,":[81],"waveforms":[83],"retain":[84],"more":[85,97,156],"phenomena":[87],"potentially":[89],"can":[90,190,204],"help":[91],"networks":[93],"discover":[94],"better":[95],"customized":[98],"representations.":[99],"end,":[102],"our":[103,202,227],"adopts":[106],"co-called":[108],"SincNet":[109,126,150,189],"module":[110],"take":[112,218],"input":[113,219],"waveform":[116],"covert":[118],"it":[119],"suitable":[122],"vector":[123],"representation":[124],"sequence.":[125],"employs":[127],"cardinal":[129],"sine":[130],"(sinc)":[131],"function":[132],"implement":[134],"learnable":[135],"bandpass":[136],"filters,":[137],"drawing":[138],"inspiration":[139],"convolutional":[142],"network":[144],"(CNN).":[145],"By":[146],"comparison":[147],"CNN,":[149],"has":[151],"fewer":[152],"parameters":[153],"amenable":[157],"human":[159],"interpretation.":[160],"Extensive":[161],"experiments":[162],"are":[163],"conducted":[164],"L2-ARCTIC":[167],"dataset,":[168],"publicly-available":[172],"English":[174],"corpus":[176],"compiled":[177],"research":[179],"CAPT.":[181],"We":[182],"find":[183],"sinc":[186],"filters":[187],"of":[188,198],"be":[191],"adapted":[192],"quickly":[193],"learners":[197],"different":[199],"nationalities.":[200],"Furthermore,":[201],"achieve":[205],"comparable":[206],"mispronunciation":[207],"performance":[209],"relation":[211],"state-of-the-art":[213],"E2E":[214],"models":[216],"standard":[221],"handcrafted":[222],"features.":[224],"Besides":[225],"that,":[226],"also":[229],"provides":[230],"considerable":[231],"improvements":[232],"phone":[234],"error":[235],"rate":[236],"(PER)":[237],"accuracy.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}