{"id":"https://openalex.org/W4296070464","doi":"https://doi.org/10.21437/interspeech.2022-11155","title":"CoCA-MDD: A Coupled Cross-Attention based Framework for Streaming Mispronunciation Detection and Diagnosis","display_name":"CoCA-MDD: A Coupled Cross-Attention based Framework for Streaming Mispronunciation Detection and Diagnosis","publication_year":2022,"publication_date":"2022-09-16","ids":{"openalex":"https://openalex.org/W4296070464","doi":"https://doi.org/10.21437/interspeech.2022-11155"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2022-11155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11155","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","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/A5046186949","display_name":"Nianzu Zheng","orcid":"https://orcid.org/0000-0001-6300-9684"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Nianzu Zheng","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113782870","display_name":"Liqun Deng","orcid":"https://orcid.org/0000-0002-7594-0414"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqun Deng","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002206405","display_name":"Wenyong Huang","orcid":"https://orcid.org/0000-0003-3167-0851"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenyong Huang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083831776","display_name":"Yu Ting Yeung","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Ting Yeung","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102033255","display_name":"Baohua Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baohua Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047568480","display_name":"Yuanyuan Guo","orcid":"https://orcid.org/0000-0002-0618-1709"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyuan Guo","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115592503","display_name":"Yasheng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yasheng Wang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100373723","display_name":"Xiao Chen","orcid":"https://orcid.org/0000-0002-4224-6450"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Chen","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100650977","display_name":"Xin Jiang","orcid":"https://orcid.org/0009-0005-5164-306X"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xin Jiang","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100426170","display_name":"Qun Liu","orcid":"https://orcid.org/0000-0002-7000-1792"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qun Liu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5046186949"],"corresponding_institution_ids":["https://openalex.org/I2250955327"],"apc_list":null,"apc_paid":null,"fwci":0.3137,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.51200509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4352","last_page":"4356"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7621999979019165,"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/T10028","display_name":"Topic Modeling","score":0.7621999979019165,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.6906999945640564,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6557081341743469},{"id":"https://openalex.org/keywords/coca","display_name":"Coca","score":0.5363897681236267},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3632098436355591},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3406029939651489},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.1710553765296936}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557081341743469},{"id":"https://openalex.org/C2781313679","wikidata":"https://www.wikidata.org/wiki/Q66793593","display_name":"Coca","level":2,"score":0.5363897681236267},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3632098436355591},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3406029939651489},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.1710553765296936},{"id":"https://openalex.org/C118552586","wikidata":"https://www.wikidata.org/wiki/Q7867","display_name":"Psychiatry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2022-11155","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2022-11155","pdf_url":null,"source":{"id":"https://openalex.org/S4363604309","display_name":"Interspeech 2022","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":"Interspeech 2022","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W2074231493","https://openalex.org/W2091856355","https://openalex.org/W2139008940","https://openalex.org/W2733417325","https://openalex.org/W2768986418","https://openalex.org/W2888954148","https://openalex.org/W2962760690","https://openalex.org/W3012193086","https://openalex.org/W3015231007","https://openalex.org/W3015927303","https://openalex.org/W3081817774","https://openalex.org/W3096686110","https://openalex.org/W3097395819","https://openalex.org/W3097515180","https://openalex.org/W3123665557","https://openalex.org/W3156081754","https://openalex.org/W3162227798","https://openalex.org/W3197816268","https://openalex.org/W3198712976","https://openalex.org/W4287241492","https://openalex.org/W4297726970"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2062961690","https://openalex.org/W2738862710","https://openalex.org/W2419950109","https://openalex.org/W2368779261","https://openalex.org/W2794438528","https://openalex.org/W2778699561","https://openalex.org/W3128571556","https://openalex.org/W2374918184"],"abstract_inverted_index":{"Mispronunciation":[0],"detection":[1],"and":[2,100,119,123],"diagnosis":[3],"(MDD)":[4],"is":[5,68],"a":[6,46,61],"popular":[7],"research":[8],"focus":[9],"in":[10,21,60],"computer-aided":[11],"pronunciation":[12,130],"training":[13],"(CAPT)":[14],"systems.End-to-end":[15],"(e2e)":[16],"approaches":[17],"are":[18],"becoming":[19],"dominant":[20],"MDD.However":[22],"an":[23],"e2e":[24,48],"MDD":[25,49],"model":[26,50,83,92],"usually":[27],"requires":[28],"entire":[29],"speech":[30,59],"utterances":[31],"as":[32],"input":[33,58],"context,":[34],"which":[35],"leads":[36],"to":[37,56,70,84],"significant":[38],"time":[39],"latency":[40],"especially":[41],"for":[42,104,121],"long":[43],"paragraphs.We":[44],"propose":[45],"streaming":[47,62,98,122],"called":[51],"CoCA-MDD.We":[52],"utilize":[53],"conv-transformer":[54],"structure":[55],"encode":[57],"manner.A":[63],"coupled":[64],"cross-attention":[65],"(CoCA)":[66],"mechanism":[67],"proposed":[69,91],"integrate":[71],"frame-level":[72],"acoustic":[73],"features":[74],"with":[75,88],"encoded":[76],"reference":[77],"linguistic":[78],"features.CoCA":[79],"also":[80],"enables":[81],"our":[82],"perform":[85],"mispronunciation":[86,101],"classification":[87,102],"whole":[89],"utterances.The":[90],"allows":[93],"system":[94],"fusion":[95,124],"between":[96],"the":[97],"output":[99,103],"further":[105],"performance":[106],"enhancement.We":[107],"evaluate":[108],"CoCA-MDD":[109,132],"on":[110,127,140],"publicly":[111],"available":[112],"corpora.CoCA-MDD":[113],"achieves":[114,133],"F1":[115],"scores":[116],"of":[117],"57.03%":[118],"60.78%":[120],"modes":[125],"respectively":[126],"L2-ARCTIC.For":[128],"phone-level":[129],"scoring,":[131],"0.58":[134],"Pearson":[135],"correlation":[136],"coefficient":[137],"(PCC)":[138],"value":[139],"SpeechOcean762.":[141]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-31T07:56:22.981413","created_date":"2025-10-10T00:00:00"}