{"id":"https://openalex.org/W4402353653","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651520","title":"Improving End-to-End Speech Recognition Through Conditional Cross-Modal Knowledge Distillation with Language Model","display_name":"Improving End-to-End Speech Recognition Through Conditional Cross-Modal Knowledge Distillation with Language Model","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402353653","doi":"https://doi.org/10.1109/ijcnn60899.2024.10651520"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10651520","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651520","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":"conference-paper","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/A5016886735","display_name":"Yuan Li","orcid":"https://orcid.org/0000-0001-9507-3007"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuan Li","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008226894","display_name":"Yonghe Wang","orcid":"https://orcid.org/0000-0003-1647-1539"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yonghe Wang","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014372166","display_name":"Feilong Bao","orcid":"https://orcid.org/0000-0001-7312-1629"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feilong Bao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113373769","display_name":"Zhenjie Gao","orcid":"https://orcid.org/0009-0002-6287-2472"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenjie Gao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076174513","display_name":"Guanglai Gao","orcid":"https://orcid.org/0009-0005-5513-1192"},"institutions":[{"id":"https://openalex.org/I2722730","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496","country_code":"CN","type":"education","lineage":["https://openalex.org/I2722730"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanglai Gao","raw_affiliation_strings":["Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia University,College of Computer Science,National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Mongolian Information Processing Technology,Huhot,China","institution_ids":["https://openalex.org/I2722730"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100447812","display_name":"Wenjun Zhang","orcid":"https://orcid.org/0000-0002-0449-0946"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wenjun Zhang","raw_affiliation_strings":["Inner Mongolia Personnel and Talent Public Service Center,Huhot,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inner Mongolia Personnel and Talent Public Service Center,Huhot,China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"35","issue":null,"first_page":"1","last_page":"7"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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/T10028","display_name":"Topic Modeling","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7790296077728271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7526270747184753},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.6161085367202759},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.549428403377533},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4911451041698456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.46143150329589844},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4407602548599243}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7790296077728271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7526270747184753},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.6161085367202759},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.549428403377533},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4911451041698456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46143150329589844},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4407602548599243},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10651520","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/ijcnn60899.2024.10651520","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":[{"score":0.4399999976158142,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322216","display_name":"Inner Mongolia University","ror":"https://ror.org/0106qb496"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W1915251500","https://openalex.org/W2293858598","https://openalex.org/W2402040300","https://openalex.org/W2526425061","https://openalex.org/W2577366047","https://openalex.org/W2627092829","https://openalex.org/W2888779557","https://openalex.org/W2889048668","https://openalex.org/W2936252403","https://openalex.org/W2936774411","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2963362078","https://openalex.org/W2963453233","https://openalex.org/W2964539095","https://openalex.org/W2972991710","https://openalex.org/W2973122799","https://openalex.org/W3096297644","https://openalex.org/W3097777922","https://openalex.org/W3151526698","https://openalex.org/W3156902660","https://openalex.org/W3164692279","https://openalex.org/W3196855257","https://openalex.org/W3197478142","https://openalex.org/W3211278025","https://openalex.org/W4221151577","https://openalex.org/W4224821750","https://openalex.org/W4225299129","https://openalex.org/W4226521565","https://openalex.org/W4281483168","https://openalex.org/W4372266905","https://openalex.org/W4385245566","https://openalex.org/W4385823005","https://openalex.org/W4391021438","https://openalex.org/W6638523607","https://openalex.org/W6640059789","https://openalex.org/W6687566353","https://openalex.org/W6754473786","https://openalex.org/W6794920533","https://openalex.org/W6839053282","https://openalex.org/W6847363464"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W2151749779","https://openalex.org/W3008587939","https://openalex.org/W3196421258","https://openalex.org/W4387301579","https://openalex.org/W3026162553","https://openalex.org/W2763956190","https://openalex.org/W4400488565"],"abstract_inverted_index":{"Recently,":[0],"cross-modal":[1,54],"knowledge":[2,55,88,96],"distillation":[3,56,97],"methods":[4],"for":[5,21,61,74],"end-to-end":[6],"automatic":[7],"speech":[8,152],"recognition":[9,23,77,132],"(E2E-ASR)":[10],"model":[11,69,73,93,108],"training":[12],"pointed":[13],"out":[14],"the":[15,48,71,76,87,91,115,125,131,135,150],"potential":[16],"help":[17],"of":[18,90,114,117,121,127,134],"text":[19,119],"data":[20,120],"improving":[22,75],"performance.":[24,78,159],"However,":[25],"conventional":[26],"optimization":[27],"strategies":[28],"can":[29],"mislead":[30],"student":[31,92],"models":[32],"to":[33,38,84,94],"produce":[34],"suboptimal":[35],"performance":[36,133],"due":[37],"erroneous":[39,99],"predictions":[40,100],"generated":[41,101],"by":[42,50,102],"teacher":[43,103],"models.":[44],"This":[45],"paper":[46],"addresses":[47],"issue":[49],"proposing":[51],"a":[52,58,81],"conditional":[53,82],"strategy,":[57],"novel":[59],"technique":[60],"selectively":[62],"incorporating":[63],"contextual":[64],"linguistic":[65],"information":[66],"from":[67,98],"language":[68,107],"into":[70],"E2E-ASR":[72,136],"We":[79],"introduce":[80],"selector":[83],"dynamically":[85],"adjust":[86],"source":[89],"avoid":[95],"model.":[104,137],"In":[105],"pre-trained":[106],"fine-tuning,":[109],"we":[110],"perform":[111],"an":[112],"analysis":[113],"impact":[116],"unsupervised":[118],"varying":[122],"scales":[123],"on":[124,149],"quality":[126],"soft":[128],"labels":[129],"and":[130,155],"Our":[138],"proposed":[139],"method":[140],"simultaneously":[141],"improve":[142],"two":[143],"different":[144],"non-autoregressive":[145],"decoding":[146],"approaches.":[147],"Experiments":[148],"Chinese":[151],"datasets":[153],"AISHELL-1":[154],"AISHELL-2":[156],"show":[157],"competitive":[158]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}