{"id":"https://openalex.org/W2944150351","doi":"https://doi.org/10.3390/sym11050644","title":"End-to-End Mandarin Speech Recognition Combining CNN and BLSTM","display_name":"End-to-End Mandarin Speech Recognition Combining CNN and BLSTM","publication_year":2019,"publication_date":"2019-05-07","ids":{"openalex":"https://openalex.org/W2944150351","doi":"https://doi.org/10.3390/sym11050644","mag":"2944150351"},"language":"en","primary_location":{"id":"doi:10.3390/sym11050644","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11050644","pdf_url":"https://www.mdpi.com/2073-8994/11/5/644/pdf?version=1558075526","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2073-8994/11/5/644/pdf?version=1558075526","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100391494","display_name":"Dong Wang","orcid":"https://orcid.org/0000-0002-6992-7950"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dong Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410073, China","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695468","display_name":"Xiaodong Wang","orcid":"https://orcid.org/0000-0001-8949-5967"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410073, China","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112298993","display_name":"Shaohe Lv","orcid":null},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaohe Lv","raw_affiliation_strings":["College of Computer, National University of Defense Technology, Changsha 410073, China","Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410073, China"],"affiliations":[{"raw_affiliation_string":"College of Computer, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]},{"raw_affiliation_string":"Science and Technology on Parallel and Distributed Processing Laboratory, National University of Defense Technology, Changsha 410073, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100391494","https://openalex.org/A5115695468"],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":{"value":2000,"currency":"CHF","value_usd":2165},"apc_paid":{"value":2000,"currency":"CHF","value_usd":2165},"fwci":3.7612,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.94638279,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"11","issue":"5","first_page":"644","last_page":"644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T11309","display_name":"Music and Audio Processing","score":0.9987000226974487,"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":0.8962676525115967},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7171753644943237},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7145256996154785},{"id":"https://openalex.org/keywords/mandarin-chinese","display_name":"Mandarin Chinese","score":0.685377836227417},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.607952356338501},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.5802561044692993},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5488281846046448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4435851275920868},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4420730769634247},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3403545618057251}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8962676525115967},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7171753644943237},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7145256996154785},{"id":"https://openalex.org/C138954614","wikidata":"https://www.wikidata.org/wiki/Q9192","display_name":"Mandarin Chinese","level":2,"score":0.685377836227417},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.607952356338501},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5802561044692993},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5488281846046448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4435851275920868},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4420730769634247},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3403545618057251},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3390/sym11050644","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11050644","pdf_url":"https://www.mdpi.com/2073-8994/11/5/644/pdf?version=1558075526","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:6080e59463a5441b9b6d1679b9d0b90e","is_oa":true,"landing_page_url":"https://doaj.org/article/6080e59463a5441b9b6d1679b9d0b90e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry, Vol 11, Iss 5, p 644 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/11/5/644/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/sym11050644","pdf_url":null,"source":{"id":"https://openalex.org/S4306400947","display_name":"MDPI (MDPI AG)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210097602","host_organization_name":"Multidisciplinary Digital Publishing Institute (Switzerland)","host_organization_lineage":["https://openalex.org/I4210097602"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Symmetry","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/sym11050644","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11050644","pdf_url":"https://www.mdpi.com/2073-8994/11/5/644/pdf?version=1558075526","source":{"id":"https://openalex.org/S190787756","display_name":"Symmetry","issn_l":"2073-8994","issn":["2073-8994"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Symmetry","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6200000047683716,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2944150351.pdf","grobid_xml":"https://content.openalex.org/works/W2944150351.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W108550785","https://openalex.org/W1494198834","https://openalex.org/W1710082047","https://openalex.org/W1836465849","https://openalex.org/W1922655562","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2250357346","https://openalex.org/W2284628133","https://openalex.org/W2293858598","https://openalex.org/W2524185514","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2739427748","https://openalex.org/W2755682845","https://openalex.org/W2773389940","https://openalex.org/W2810104656","https://openalex.org/W2889205932","https://openalex.org/W2889552651","https://openalex.org/W2900525210","https://openalex.org/W2901368553","https://openalex.org/W2949975180","https://openalex.org/W2950990740","https://openalex.org/W2951171832","https://openalex.org/W2953291251","https://openalex.org/W2962825331","https://openalex.org/W2963242190","https://openalex.org/W2963403664","https://openalex.org/W2963437406","https://openalex.org/W2963448630","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W2964190464","https://openalex.org/W6682889407"],"related_works":["https://openalex.org/W2990005675","https://openalex.org/W2374317326","https://openalex.org/W1603321096","https://openalex.org/W2394766824","https://openalex.org/W2078713291","https://openalex.org/W2361574037","https://openalex.org/W2386292991","https://openalex.org/W2364440891","https://openalex.org/W2393726922","https://openalex.org/W2916997151"],"abstract_inverted_index":{"Since":[0],"conventional":[1,43],"Automatic":[2],"Speech":[3],"Recognition":[4],"(ASR)":[5],"systems":[6,49],"often":[7],"contain":[8],"many":[9],"modules":[10],"and":[11,21,38,61,110,114,174],"use":[12,57],"varieties":[13],"of":[14,153],"expertise,":[15],"it":[16],"is":[17,71,124,172],"hard":[18],"to":[19,96,107],"build":[20],"train":[22],"such":[23],"models.":[24,143],"Recent":[25],"research":[26],"show":[27,145],"that":[28,146],"end-to-end":[29,47,85],"ASRs":[30],"can":[31],"significantly":[32],"simplify":[33],"the":[34,128,156,162],"speech":[35,76,99,132],"recognition":[36],"pipelines":[37],"achieve":[39],"competitive":[40],"performance":[41],"with":[42],"systems.":[44],"However,":[45],"most":[46],"ASR":[48,90,183],"are":[50,66,167],"neither":[51,136],"reproducible":[52,173],"nor":[53,140],"comparable":[54],"because":[55],"they":[56],"specific":[58],"language":[59,142],"models":[60],"in-house":[62,138],"training":[63],"databases":[64,139],"which":[65],"not":[67],"freely":[68,168],"available.":[69],"This":[70,88],"especially":[72],"common":[73],"for":[74,120,180],"Mandarin":[75,86,131,182],"recognition.":[77],"In":[78],"this":[79],"paper,":[80],"we":[81,165],"propose":[82],"a":[83,151,177],"CNN+BLSTM+CTC":[84,89,148],"ASR.":[87],"uses":[91,101,115],"Convolutional":[92],"Neural":[93],"Net":[94],"(CNN)":[95],"learn":[97,108],"local":[98],"features,":[100],"Bidirectional":[102],"Long-Short":[103],"Time":[104],"Memory":[105],"(BLSTM)":[106],"history":[109],"future":[111],"contextual":[112],"information,":[113],"Connectionist":[116],"Temporal":[117],"Classification":[118],"(CTC)":[119],"decoding.":[121],"Our":[122],"model":[123,149,171],"completely":[125],"trained":[126],"on":[127],"by-far-largest":[129],"open-source":[130],"corpus":[133],"AISHELL-1,":[134],"using":[135],"any":[137],"external":[141],"Experiments":[144],"our":[147,170],"achieves":[150],"WER":[152],"19.2%,":[154],"outperforming":[155],"exiting":[157],"best":[158],"work.":[159],"Because":[160],"all":[161],"data":[163],"corpora":[164],"used":[166],"available,":[169],"comparable,":[175],"providing":[176],"new":[178],"baseline":[179],"further":[181],"research.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}