{"id":"https://openalex.org/W2964539095","doi":"https://doi.org/10.3390/sym11081018","title":"An Overview of End-to-End Automatic Speech Recognition","display_name":"An Overview of End-to-End Automatic Speech Recognition","publication_year":2019,"publication_date":"2019-08-07","ids":{"openalex":"https://openalex.org/W2964539095","doi":"https://doi.org/10.3390/sym11081018","mag":"2964539095"},"language":"en","primary_location":{"id":"doi:10.3390/sym11081018","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11081018","pdf_url":"https://www.mdpi.com/2073-8994/11/8/1018/pdf?version=1566214558","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/2073-8994/11/8/1018/pdf?version=1566214558","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"],"raw_orcid":"https://orcid.org/0000-0002-6992-7950","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"],"raw_orcid":null,"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"],"raw_orcid":null,"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":1,"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":13.1306,"has_fulltext":true,"cited_by_count":250,"citation_normalized_percentile":{"value":0.98987432,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"11","issue":"8","first_page":"1018","last_page":"1018"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9955000281333923,"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":0.9907000064849854,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8186637163162231},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7999829053878784},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.7129435539245605},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6358495950698853},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5918287634849548},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5537899732589722},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.48667770624160767},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.4661741256713867},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.41889098286628723},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.41805756092071533},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40871989727020264},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.331855833530426},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.23715490102767944}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8186637163162231},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7999829053878784},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.7129435539245605},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6358495950698853},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5918287634849548},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5537899732589722},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.48667770624160767},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.4661741256713867},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41889098286628723},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.41805756092071533},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40871989727020264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.331855833530426},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.23715490102767944},{"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/sym11081018","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11081018","pdf_url":"https://www.mdpi.com/2073-8994/11/8/1018/pdf?version=1566214558","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:5188709e0281434a96003e3ed572243b","is_oa":true,"landing_page_url":"https://doaj.org/article/5188709e0281434a96003e3ed572243b","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"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 8, p 1018 (2019)","raw_type":"article"},{"id":"pmh:oai:mdpi.com:/2073-8994/11/8/1018/","is_oa":true,"landing_page_url":"http://dx.doi.org/10.3390/sym11081018","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/sym11081018","is_oa":true,"landing_page_url":"https://doi.org/10.3390/sym11081018","pdf_url":"https://www.mdpi.com/2073-8994/11/8/1018/pdf?version=1566214558","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":[{"score":0.6499999761581421,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":74,"referenced_works":["https://openalex.org/W187290754","https://openalex.org/W854541894","https://openalex.org/W1542537254","https://openalex.org/W1586532344","https://openalex.org/W1710082047","https://openalex.org/W1777419623","https://openalex.org/W1828163288","https://openalex.org/W1922655562","https://openalex.org/W1942035323","https://openalex.org/W1977286842","https://openalex.org/W2045009386","https://openalex.org/W2045956438","https://openalex.org/W2063223471","https://openalex.org/W2064675550","https://openalex.org/W2078993594","https://openalex.org/W2097645910","https://openalex.org/W2102113734","https://openalex.org/W2114016253","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2157331557","https://openalex.org/W2158373110","https://openalex.org/W2193413348","https://openalex.org/W2263232528","https://openalex.org/W2293858598","https://openalex.org/W2327501763","https://openalex.org/W2407648438","https://openalex.org/W2514969556","https://openalex.org/W2521999726","https://openalex.org/W2526425061","https://openalex.org/W2530486890","https://openalex.org/W2530876040","https://openalex.org/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2619820632","https://openalex.org/W2627092829","https://openalex.org/W2739427748","https://openalex.org/W2745439869","https://openalex.org/W2746192915","https://openalex.org/W2750499125","https://openalex.org/W2766219058","https://openalex.org/W2798853776","https://openalex.org/W2808347441","https://openalex.org/W2889163603","https://openalex.org/W2901152136","https://openalex.org/W2950903920","https://openalex.org/W2951171832","https://openalex.org/W2953022181","https://openalex.org/W2953291251","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2962988733","https://openalex.org/W2963070863","https://openalex.org/W2963211739","https://openalex.org/W2963236196","https://openalex.org/W2963403664","https://openalex.org/W2963414781","https://openalex.org/W2963483399","https://openalex.org/W2963590118","https://openalex.org/W2963747784","https://openalex.org/W2963827914","https://openalex.org/W2963920996","https://openalex.org/W3035139526","https://openalex.org/W4232478747","https://openalex.org/W4238651617","https://openalex.org/W6632300202","https://openalex.org/W6638196096","https://openalex.org/W6638749077","https://openalex.org/W6728811460","https://openalex.org/W6779487094"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W2121652828","https://openalex.org/W2916997151","https://openalex.org/W3198455051"],"abstract_inverted_index":{"Automatic":[0,219],"speech":[1,7,35,125,164,220],"recognition,":[2,8],"especially":[3],"large":[4],"vocabulary":[5],"continuous":[6],"is":[9,73,119,159,222,234],"an":[10,120],"important":[11,121],"issue":[12],"in":[13,227],"the":[14,23,33,46,69,95,116,132,141,160,167,171,207,212,228],"field":[15,229],"of":[16,124,134,147,163,177,211,230,238],"machine":[17],"learning.":[18],"For":[19],"a":[20,99,223,235],"long":[21],"time,":[22],"hidden":[24],"Markov":[25],"model":[26,29,44,48,71,97,118,149,158,214],"(HMM)-Gaussian":[27],"mixed":[28],"(GMM)":[30],"has":[31,52,98],"been":[32],"mainstream":[34],"recognition":[36,221,225],"framework.":[37],"But":[38],"recently,":[39],"HMM-deep":[40],"neural":[41,189],"network":[42,190],"(DNN)":[43],"and":[45,87,112,145,150,153,174,192,194,197,204,206],"end-to-end":[47,96,117,135,151,157,180,213],"using":[49,58],"deep":[50,59],"learning":[51,60],"achieved":[53],"performance":[54],"beyond":[55],"HMM-GMM.":[56],"Both":[57],"techniques,":[61],"these":[62],"two":[63],"models":[64],"have":[65],"comparable":[66],"performances.":[67],"However,":[68],"HMM-DNN":[70],"itself":[72],"limited":[74],"by":[75],"various":[76],"unfavorable":[77],"factors":[78],"such":[79],"as":[80],"data":[81,110],"forced":[82],"segmentation":[83],"alignment,":[84],"independent":[85],"hypothesis,":[86],"multi-module":[88],"individual":[89],"training":[90],"inherited":[91],"from":[92],"HMM,":[93],"while":[94],"simplified":[100],"model,":[101],"joint":[102],"training,":[103],"direct":[104],"output,":[105],"no":[106],"need":[107],"to":[108],"force":[109],"alignment":[111],"other":[113],"advantages.":[114],"Therefore,":[115],"research":[122,175],"direction":[123,162],"recognition.":[126,165],"In":[127],"this":[128],"paper":[129,138],"we":[130],"review":[131],"development":[133,161,210],"model.":[136],"This":[137],"first":[139],"introduces":[140],"basic":[142],"ideas,":[143],"advantages":[144,203],"disadvantages":[146,205],"HMM-based":[148],"models,":[152,181],"points":[154],"out":[155],"that":[156],"Then":[166],"article":[168],"focuses":[169],"on":[170],"principles,":[172],"progress":[173],"hotspots":[176],"three":[178],"different":[179],"which":[182,233],"are":[183,215],"connectionist":[184],"temporal":[185],"classification":[186],"(CTC)-based,":[187],"recurrent":[188],"(RNN)-transducer":[191],"attention-based,":[193],"makes":[195],"theoretically":[196],"experimentally":[198],"detailed":[199],"comparisons.":[200],"Their":[201],"respective":[202],"possible":[208],"future":[209],"finally":[216],"pointed":[217],"out.":[218],"pattern":[224],"task":[226],"computer":[231],"science,":[232],"subject":[236],"area":[237],"Symmetry.":[239]},"counts_by_year":[{"year":2026,"cited_by_count":9},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":59},{"year":2023,"cited_by_count":56},{"year":2022,"cited_by_count":44},{"year":2021,"cited_by_count":30},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}