乐胖代购免代理版

{"id":"https://openalex.org/W4392902938","doi":"https://doi.org/10.1109/icassp48485.2024.10448480","title":"L1-Aware Multilingual Mispronunciation Detection Framework","display_name":"L1-Aware Multilingual Mispronunciation Detection Framework","publication_year":2024,"publication_date":"2024-03-18","ids":{"openalex":"https://openalex.org/W4392902938","doi":"https://doi.org/10.1109/icassp48485.2024.10448480"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448480","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_indexed_in_scopus":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},"type":"article","type_crossref":"proceedings-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1109/icassp48485.2024.10448480","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072129532","display_name":"Yassine El Kheir","orcid":null},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Yassine El Kheir","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022279488","display_name":"Shammur Absar Chowdhury","orcid":"https://orcid.org/0000-0002-1331-2543"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Shammur Absar Chowdhury","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5104175595","display_name":"Ahmed Ali","orcid":"https://orcid.org/0009-0004-8477-4376"},"institutions":[{"id":"https://openalex.org/I1301390666","display_name":"Qatar Airways (Qatar)","ror":"https://ror.org/01hx00y13","country_code":"QA","type":"company","lineage":["https://openalex.org/I1301390666"]}],"countries":["QA"],"is_corresponding":false,"raw_author_name":"Ahmed Ali","raw_affiliation_strings":["Qatar Computing Research Institute, HBKU, Doha, Qatar"],"affiliations":[{"raw_affiliation_string":"Qatar Computing Research Institute, HBKU, Doha, Qatar","institution_ids":["https://openalex.org/I1301390666"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.866,"has_fulltext":true,"fulltext_origin":"pdf","cited_by_count":2,"citation_normalized_percentile":{"value":0.795225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":92,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"12752","last_page":"12756"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9999,"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":0.9999,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9983,"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/T10403","display_name":"Phonetics and Phonology Research","score":0.997,"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/robustness","display_name":"Robustness","score":0.52268827},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.43452153},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.43336102}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8324938},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7012284},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.61329854},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.52268827},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.51540244},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4751394},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4616633},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4598561},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.43452153},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.43336102},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11573744},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448480","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_indexed_in_scopus":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},{"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2309.07719","pdf_url":"https://arxiv.org/pdf/2309.07719","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_indexed_in_scopus":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":["Cornell University"],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1109/icassp48485.2024.10448480","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_indexed_in_scopus":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},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7}],"grants":[],"datasets":[],"versions":[],"referenced_works_count":21,"referenced_works":["https://openalex.org/W2054441760","https://openalex.org/W2070233361","https://openalex.org/W2139008940","https://openalex.org/W2888954148","https://openalex.org/W2938359332","https://openalex.org/W2972347929","https://openalex.org/W2973136824","https://openalex.org/W3015231007","https://openalex.org/W3035390927","https://openalex.org/W3096674206","https://openalex.org/W3156081754","https://openalex.org/W3196525293","https://openalex.org/W3196891430","https://openalex.org/W3197816268","https://openalex.org/W4224928163","https://openalex.org/W4312069033","https://openalex.org/W4372270124","https://openalex.org/W4378105483","https://openalex.org/W4385823114","https://openalex.org/W4385987097","https://openalex.org/W4385987657"],"related_works":["https://openalex.org/W4225593417","https://openalex.org/W410723623","https://openalex.org/W3160494304","https://openalex.org/W3022298670","https://openalex.org/W2990005675","https://openalex.org/W2573498121","https://openalex.org/W2413243053","https://openalex.org/W2118717649","https://openalex.org/W2035068594","https://openalex.org/W2015341305"],"abstract_inverted_index":{"The":[0,149],"phonological":[1],"discrepancies":[2],"between":[3],"a":[4,15,23,82,104],"speaker's":[5],"native":[6],"(L1)":[7],"and":[8,28,48,87,90,122,140,142,146,154,168],"the":[9,45,62,66,71,94,98,117,127,130],"non-native":[10],"language":[11],"(L2)":[12],"serves":[13],"as":[14],"major":[16],"factor":[17],"for":[18,103,116],"mispronunciation.":[19],"This":[20],"paper":[21],"introduces":[22],"novel":[24],"multilingual":[25,106],"Mispronunciation":[26],"Detection":[27],"Diagnosis":[29],"(MDD)":[30],"architecture,":[31],"L1-MultiMDD,":[32],"enriched":[33],"with":[34,65,93],"L1-aware":[35],"speech":[36,40],"representation.":[37],"An":[38],"end-to-end":[39],"encoder":[41],"is":[42,58,100],"trained":[43],"on":[44,134],"input":[46,63],"signal":[47],"its":[49],"corresponding":[50],"reference":[51,67],"phoneme":[52,68,107],"sequence.":[53,69],"First,":[54],"an":[55,77],"attention":[56],"mechanism":[57],"deployed":[59],"to":[60],"align":[61],"audio":[64],"Afterwards,":[70],"L1-L2-speech":[72],"embedding":[73],"are":[74,91],"extracted":[75],"from":[76],"auxiliary":[78],"model,":[79],"pretrained":[80],"in":[81,152],"multi-task":[83],"setup":[84],"identifying":[85],"L1":[86],"L2":[88],"language,":[89],"infused":[92],"primary":[95],"network.":[96],"Finally,":[97],"L1-MultiMDD":[99,132],"then":[101],"optimized":[102],"unified":[105],"recognition":[108],"task":[109],"using":[110],"connectionist":[111],"temporal":[112],"classification":[113],"(CTC)":[114],"loss":[115],"target":[118,161],"languages:":[119],"English,":[120],"Arabic,":[121],"Mandarin.":[123],"Our":[124],"experiments":[125],"demonstrate":[126],"effectiveness":[128],"of":[129],"proposed":[131],"framework":[133],"both":[135],"seen":[136],"\u2013":[137,144],"L2-ARTIC,":[138],"LATIC,":[139],"AraVoiceL2v2;":[141],"unseen":[143],"EpaDB":[145],"Speechocean762":[147],"datasets.":[148],"consistent":[150],"gains":[151],"PER,":[153],"false":[155],"rejection":[156],"rate":[157],"(FRR)":[158],"across":[159],"all":[160],"languages":[162],"confirm":[163],"our":[164],"approach's":[165],"robustness,":[166],"efficacy,":[167],"generalizability.":[169]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W4392902938","counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-01-17T13:38:57.974671","created_date":"2024-03-19"}