{"id":"https://openalex.org/W4391307639","doi":"https://doi.org/10.1109/icspcc59353.2023.10400369","title":"Improving End-to-End Automatic Speech Recognition with Multi-Layer-Enriched Supervised Learning","display_name":"Improving End-to-End Automatic Speech Recognition with Multi-Layer-Enriched Supervised Learning","publication_year":2023,"publication_date":"2023-11-14","ids":{"openalex":"https://openalex.org/W4391307639","doi":"https://doi.org/10.1109/icspcc59353.2023.10400369"},"language":"en","primary_location":{"id":"doi:10.1109/icspcc59353.2023.10400369","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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/A5103224748","display_name":"Jingyu Zhao","orcid":"https://orcid.org/0000-0001-8214-0469"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jingyu Zhao","raw_affiliation_strings":["Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China","Department of Information and Communication Engineering, Facult of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Facult of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040147385","display_name":"Ruwei Li","orcid":"https://orcid.org/0000-0002-7828-2242"},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruwei Li","raw_affiliation_strings":["Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China","Department of Information and Communication Engineering, Facult of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Facult of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101350174","display_name":"Weidong An","orcid":null},"institutions":[{"id":"https://openalex.org/I37796252","display_name":"Beijing University of Technology","ror":"https://ror.org/037b1pp87","country_code":"CN","type":"education","lineage":["https://openalex.org/I37796252"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weidong An","raw_affiliation_strings":["Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China","Department of Information and Communication Engineering, Facult of Information Technology, Beijing University of Technology, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beijing University of Technology,Facult of Information Technology,Department of Information and Communication Engineering,Beijing,China","institution_ids":["https://openalex.org/I37796252"]},{"raw_affiliation_string":"Department of Information and Communication Engineering, Facult of Information Technology, Beijing University of Technology, Beijing, China","institution_ids":["https://openalex.org/I37796252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5103224748"],"corresponding_institution_ids":["https://openalex.org/I37796252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.19694007,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs/2012.05481","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9782000184059143,"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":0.9782000184059143,"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":0.90420001745224,"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/end-to-end-principle","display_name":"End-to-end principle","score":0.7920433282852173},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7459855675697327},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.632444441318512},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.5972315073013306},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4833933413028717},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38680484890937805},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.05443686246871948}],"concepts":[{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7920433282852173},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7459855675697327},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.632444441318512},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.5972315073013306},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4833933413028717},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38680484890937805},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.05443686246871948},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icspcc59353.2023.10400369","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icspcc59353.2023.10400369","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)","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":34,"referenced_works":["https://openalex.org/W1586532344","https://openalex.org/W2095705004","https://openalex.org/W2127141656","https://openalex.org/W2194775991","https://openalex.org/W2327501763","https://openalex.org/W2520160253","https://openalex.org/W2526425061","https://openalex.org/W2750499125","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963242190","https://openalex.org/W2964539095","https://openalex.org/W2972818416","https://openalex.org/W3007328579","https://openalex.org/W3015995734","https://openalex.org/W3096396467","https://openalex.org/W3111562797","https://openalex.org/W3197478142","https://openalex.org/W3197580070","https://openalex.org/W3209059054","https://openalex.org/W3211278025","https://openalex.org/W4221167707","https://openalex.org/W4287173589","https://openalex.org/W4302028822","https://openalex.org/W6635078382","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6687566353","https://openalex.org/W6727336983","https://openalex.org/W6745057489","https://openalex.org/W6787040858","https://openalex.org/W6795952400"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W2151749779","https://openalex.org/W1999612375","https://openalex.org/W2938107654","https://openalex.org/W3008587939","https://openalex.org/W4387301579","https://openalex.org/W2951281592","https://openalex.org/W2166381389","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"To":[0],"enhance":[1],"speech":[2,11,131],"recognition":[3,12,75,132],"performance":[4],"with":[5],"limited":[6],"network":[7,63],"capacity,":[8],"an":[9,49,128],"end-to-end":[10],"algorithm":[13],"based":[14],"on":[15,66,107],"multi-layer-enriched":[16],"supervision":[17,43,51],"(MES-ASR)":[18],"is":[19,45,105],"proposed":[20,103],"in":[21,85,123,130],"this":[22,78],"paper.":[23],"This":[24,56],"approach":[25,104],"allows":[26],"the":[27,36,40,58,62,81,86,108,114],"model":[28],"to":[29,64,73],"learn":[30],"more":[31,68],"speaking":[32,69],"content":[33,70],"information":[34],"despite":[35],"capacity":[37],"constraints.":[38],"Specifically,":[39],"intermediate":[41],"layer":[42],"loss":[44,52,83],"optimized":[46],"by":[47],"introducing":[48],"additional":[50,95],"at":[53],"that":[54],"layer.":[55],"forces":[57],"lower":[59],"layers":[60],"of":[61],"focus":[65],"acquiring":[67],"information,":[71],"leading":[72],"improved":[74],"performance.":[76,133],"Notably,":[77],"method":[79],"adds":[80],"supervisory":[82],"solely":[84],"middle":[87],"layer,":[88],"ensuring":[89],"simplicity":[90],"during":[91,100],"training":[92],"and":[93,127],"no":[94],"memory":[96],"or":[97],"computational":[98],"overhead":[99],"testing.":[101],"The":[102,117],"evaluated":[106],"Aishell-1":[109],"dataset,":[110],"employing":[111],"WeNet":[112],"as":[113],"baseline":[115],"model.":[116],"experimental":[118],"results":[119],"demonstrate":[120],"a":[121],"reduction":[122],"character":[124],"error":[125],"rate":[126],"enhancement":[129]},"counts_by_year":[],"updated_date":"2025-12-23T23:11:35.936235","created_date":"2025-10-10T00:00:00"}