{"id":"https://openalex.org/W4402352094","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649982","title":"Pre-training Encoder-Decoder for Minority Language Speech Recognition","display_name":"Pre-training Encoder-Decoder for Minority Language Speech Recognition","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402352094","doi":"https://doi.org/10.1109/ijcnn60899.2024.10649982"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10649982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10649982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","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/A5100408160","display_name":"Bo Wang","orcid":"https://orcid.org/0000-0002-9620-3413"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bo Wang","raw_affiliation_strings":["Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100537705","display_name":"Jin Xiaofeng","orcid":null},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Jin","raw_affiliation_strings":["Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100582065","display_name":"Mingdong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingdong Yu","raw_affiliation_strings":["Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100783079","display_name":"Guirong Wang","orcid":"https://orcid.org/0000-0002-2353-6241"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guirong Wang","raw_affiliation_strings":["Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100434198","display_name":"Jiaqi Chen","orcid":"https://orcid.org/0000-0002-6368-6164"},"institutions":[{"id":"https://openalex.org/I1793135","display_name":"Yanbian University","ror":"https://ror.org/039xnh269","country_code":"CN","type":"education","lineage":["https://openalex.org/I1793135"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Chen","raw_affiliation_strings":["Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002"],"affiliations":[{"raw_affiliation_string":"Yanbian University,Intelligent Information Processing Laboratory,Yanji,China,133002","institution_ids":["https://openalex.org/I1793135"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100408160"],"corresponding_institution_ids":["https://openalex.org/I1793135"],"apc_list":null,"apc_paid":null,"fwci":0.3637,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.66492681,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9902999997138977,"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":0.9818000197410583,"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":0.7873818278312683},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7613793015480042},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6964149475097656},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.576495885848999},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3851725161075592},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3811473548412323},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.04938516020774841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7873818278312683},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7613793015480042},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6964149475097656},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.576495885848999},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3851725161075592},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3811473548412323},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.04938516020774841},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10649982","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10649982","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","score":0.5,"id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320330447","display_name":"Yanbian University","ror":"https://ror.org/039xnh269"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1494198834","https://openalex.org/W1969121061","https://openalex.org/W2013426435","https://openalex.org/W2048804461","https://openalex.org/W2088386901","https://openalex.org/W2091746061","https://openalex.org/W2094393930","https://openalex.org/W2096672142","https://openalex.org/W2184343439","https://openalex.org/W2549401308","https://openalex.org/W2753709519","https://openalex.org/W2913340405","https://openalex.org/W2936774411","https://openalex.org/W2963088995","https://openalex.org/W2963522845","https://openalex.org/W2969430620","https://openalex.org/W2991309414","https://openalex.org/W3096338464","https://openalex.org/W3096655658","https://openalex.org/W3097580812","https://openalex.org/W3097777922","https://openalex.org/W3122295921","https://openalex.org/W3163605596","https://openalex.org/W3197771105","https://openalex.org/W3198608154","https://openalex.org/W3209059054","https://openalex.org/W4205775058","https://openalex.org/W4225274946","https://openalex.org/W4229456977","https://openalex.org/W4319862670","https://openalex.org/W4321510785","https://openalex.org/W4385245566","https://openalex.org/W4385484947","https://openalex.org/W6770205404"],"related_works":["https://openalex.org/W230091440","https://openalex.org/W2233261550","https://openalex.org/W2810751659","https://openalex.org/W258997015","https://openalex.org/W2997094352","https://openalex.org/W4390516098","https://openalex.org/W3216976533","https://openalex.org/W100620283","https://openalex.org/W2495260952","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Although":[0],"significant":[1],"progress":[2],"has":[3],"been":[4],"made":[5],"in":[6,71,80,93,100,128],"the":[7,33,46,72,78,89,94,97,101,113,123,134,144,148,164,169],"field":[8],"of":[9,23,35,48,107,136,147,171],"speech":[10,36,81,175],"recognition":[11,37,176],"for":[12,39],"widely":[13],"used":[14,110],"languages,":[15],"minority":[16,40,173],"languages":[17],"remain":[18],"constrained":[19],"by":[20,65],"a":[21,59,137,140],"shortage":[22],"high-quality":[24],"data":[25,84],"and":[26,50,125,155,179],"labels.":[27],"This":[28],"issue":[29],"not":[30],"only":[31],"limits":[32],"development":[34],"technology":[38],"language":[41,174],"communities":[42],"but":[43],"also":[44],"impacts":[45],"protection":[47],"linguistic":[49],"cultural":[51],"diversity.":[52],"To":[53],"address":[54],"this":[55],"issue,":[56],"we":[57,132],"propose":[58,133],"pre-training":[60,73,102,145],"encoder-decoder":[61],"model":[62,166,177],"Predformer.":[63],"Inspired":[64],"contrastive":[66],"learning":[67,153,182],"methods,":[68],"our":[69],"research":[70],"encoder":[74],"phase":[75,146],"involves":[76],"comparing":[77],"differences":[79],"across":[82],"various":[83],"representations":[85],"to":[86,111,121],"deeply":[87],"mine":[88],"implicit":[90],"representational":[91],"information":[92],"data.":[95],"At":[96],"same":[98],"time,":[99],"decoder":[103],"phase,":[104],"autoregressive":[105],"reconstruction":[106],"codes":[108],"is":[109],"capture":[112],"contextual":[114],"relationships":[115],"between":[116,183],"semantics.":[117],"Building":[118],"on":[119],"this,":[120],"alleviate":[122],"complexities":[124],"uncertainties":[126],"encountered":[127],"processing":[129],"long":[130],"sequences,":[131],"introduction":[135],"self-attention":[138],"with":[139],"memory":[141],"module":[142],"during":[143],"decoder,":[149],"aimed":[150],"at":[151],"enhancing":[152],"efficiency":[154],"effectively":[156],"overcoming":[157],"these":[158],"challenges.":[159],"Experimental":[160],"results":[161],"show":[162],"that":[163],"Predformer":[165],"significantly":[167],"improves":[168],"performance":[170],"nine":[172],"baselines":[178],"can":[180],"transfer":[181],"similar":[184],"speeches.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}