{"id":"https://openalex.org/W2766219058","doi":"https://doi.org/10.1109/jstsp.2017.2763455","title":"Hybrid CTC/Attention Architecture for End-to-End Speech Recognition","display_name":"Hybrid CTC/Attention Architecture for End-to-End Speech Recognition","publication_year":2017,"publication_date":"2017-10-25","ids":{"openalex":"https://openalex.org/W2766219058","doi":"https://doi.org/10.1109/jstsp.2017.2763455","mag":"2766219058"},"language":"en","primary_location":{"id":"doi:10.1109/jstsp.2017.2763455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2763455","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-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/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-5970-8631","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-4560-8039","affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062940343","display_name":"Suyoun Kim","orcid":"https://orcid.org/0000-0002-6822-337X"},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Suyoun Kim","raw_affiliation_strings":["Carnegie Mellon University, Pittsburgh, PA, USA"],"raw_orcid":"https://orcid.org/0000-0002-6822-337X","affiliations":[{"raw_affiliation_string":"Carnegie Mellon University, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078778981","display_name":"Tomoki Hayashi","orcid":"https://orcid.org/0000-0001-8782-4093"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University, Nagoya, Japan"],"raw_orcid":"https://orcid.org/0000-0001-8782-4093","affiliations":[{"raw_affiliation_string":"Nagoya University, Nagoya, Japan","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":53.8454,"has_fulltext":false,"cited_by_count":832,"citation_normalized_percentile":{"value":0.9988091,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"11","issue":"8","first_page":"1240","last_page":"1253"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.8586609363555908},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6279496550559998},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6189779043197632},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5878668427467346},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5251731276512146},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5039548277854919},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4621259868144989}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8586609363555908},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6279496550559998},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6189779043197632},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5878668427467346},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5251731276512146},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5039548277854919},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4621259868144989},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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/jstsp.2017.2763455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jstsp.2017.2763455","pdf_url":null,"source":{"id":"https://openalex.org/S42167783","display_name":"IEEE Journal of Selected Topics in Signal Processing","issn_l":"1932-4553","issn":["1932-4553","1941-0484"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Selected Topics in Signal Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W165283731","https://openalex.org/W179875071","https://openalex.org/W811578723","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1553004968","https://openalex.org/W1586532344","https://openalex.org/W1855892484","https://openalex.org/W1990005915","https://openalex.org/W2005708641","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2125529971","https://openalex.org/W2127141656","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2143017621","https://openalex.org/W2144499799","https://openalex.org/W2160815625","https://openalex.org/W2163377725","https://openalex.org/W2193413348","https://openalex.org/W2395416438","https://openalex.org/W2514741789","https://openalex.org/W2515801922","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2530486890","https://openalex.org/W2545177271","https://openalex.org/W2559260703","https://openalex.org/W2577366047","https://openalex.org/W2608712415","https://openalex.org/W2627092829","https://openalex.org/W2739883972","https://openalex.org/W2952288254","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963447639","https://openalex.org/W2964308564","https://openalex.org/W3145501851","https://openalex.org/W4251372957","https://openalex.org/W4299649720","https://openalex.org/W6601563604","https://openalex.org/W6606787761","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6639156005","https://openalex.org/W6675365184","https://openalex.org/W6678720029","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6681794868","https://openalex.org/W6683955732","https://openalex.org/W6687566353","https://openalex.org/W6727690538","https://openalex.org/W6728811460","https://openalex.org/W6728910023"],"related_works":["https://openalex.org/W2364370872","https://openalex.org/W2053269318","https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"Conventional":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"based":[5,239],"on":[6,240],"a":[7,16,38,54,72,86,179],"hidden":[8],"Markov":[9,121],"model":[10],"(HMM)/deep":[11],"neural":[12],"network":[13,75],"(DNN)":[14],"is":[15,216,232],"very":[17],"complicated":[18,69],"system":[19],"consisting":[20],"of":[21,63,82,95,143,199,243],"various":[22],"modules":[23,70],"such":[24,36],"as":[25,37],"acoustic,":[26],"lexicon,":[27],"and":[28,42,77,112,115,148,161,175,193,208,225,228,247],"language":[29],"models.":[30],"It":[31],"also":[32],"requires":[33],"linguistic":[34,83,251],"resources,":[35],"pronunciation":[39],"dictionary,":[40],"tokenization,":[41],"phonetic":[43],"context-dependency":[44],"trees.":[45],"On":[46],"the":[47,60,80,141,154,197,200,206,213,241],"other":[48],"hand,":[49],"end-to-end":[50,96,136],"ASR":[51,65,221,237],"has":[52],"become":[53],"popular":[55],"alternative":[56],"to":[57,106,123,158,184,218,234],"greatly":[58],"simplify":[59],"model-building":[61],"process":[62],"conventional":[64,235],"systems":[66,238],"by":[67,78,128,171],"representing":[68],"with":[71,85,190],"single":[73],"deep":[74],"architecture,":[76],"replacing":[79],"use":[81,102],"resources":[84],"data-driven":[87],"learning":[88,156,203,246],"method.":[89],"There":[90],"are":[91],"two":[92,219],"major":[93],"types":[94],"architectures":[97,145],"for":[98],"ASR;":[99],"attention-based":[100,174,209],"methods":[101],"an":[103],"attention":[104],"mechanism":[105],"perform":[107,168],"alignment":[108],"between":[109],"acoustic":[110],"frames":[111],"recognized":[113],"symbols,":[114],"connectionist":[116],"temporal":[117],"classification":[118],"(CTC)":[119],"uses":[120],"assumptions":[122],"efficiently":[124],"solve":[125],"sequential":[126],"problems":[127],"dynamic":[129],"programming.":[130],"This":[131],"paper":[132],"proposes":[133],"hybrid":[134],"CTC/attention":[135],"ASR,":[137],"which":[138],"effectively":[139],"utilizes":[140],"advantages":[142,242],"both":[144,173,205,244],"in":[146,178],"training":[147],"decoding.":[149],"During":[150,165],"training,":[151],"we":[152,167],"employ":[153],"multiobjective":[155,202,245],"framework":[157],"improve":[159],"robustness":[160],"achieve":[162],"fast":[163],"convergence.":[164],"decoding,":[166],"joint":[169,248],"decoding":[170,249],"combining":[172],"CTC":[176,207],"scores":[177],"one-pass":[180],"beam":[181],"search":[182],"algorithm":[183],"further":[185],"eliminate":[186],"irregular":[187],"alignments.":[188],"Experiments":[189],"English":[191],"(WSJ":[192],"CHiME-4)":[194],"tasks":[195],"demonstrate":[196],"effectiveness":[198],"proposed":[201,214],"over":[204],"encoder-decoder":[210],"baselines.":[211],"Moreover,":[212],"method":[215],"applied":[217],"large-scale":[220],"benchmarks":[222],"(spontaneous":[223],"Japanese":[224],"Mandarin":[226],"Chinese),":[227],"exhibits":[229],"performance":[230],"that":[231],"comparable":[233],"DNN/HMM":[236],"without":[250],"resources.":[252]},"counts_by_year":[{"year":2026,"cited_by_count":26},{"year":2025,"cited_by_count":88},{"year":2024,"cited_by_count":103},{"year":2023,"cited_by_count":122},{"year":2022,"cited_by_count":111},{"year":2021,"cited_by_count":148},{"year":2020,"cited_by_count":129},{"year":2019,"cited_by_count":75},{"year":2018,"cited_by_count":30}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}