{"id":"https://openalex.org/W2739883972","doi":"https://doi.org/10.18653/v1/p17-1048","title":"Joint CTC/attention decoding for end-to-end speech recognition","display_name":"Joint CTC/attention decoding for end-to-end speech recognition","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2739883972","doi":"https://doi.org/10.18653/v1/p17-1048","mag":"2739883972"},"language":"en","primary_location":{"id":"doi:10.18653/v1/p17-1048","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1048","pdf_url":"https://www.aclweb.org/anthology/P17-1048.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.aclweb.org/anthology/P17-1048.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001291873","display_name":"Shinji Watanabe","orcid":"https://orcid.org/0000-0002-5970-8631"},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210133125","display_name":"Mitsubishi Electric (Japan)","ror":"https://ror.org/033y26782","country_code":"JP","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"John Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL)","institution_ids":["https://openalex.org/I4210133125"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210133125"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":137,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"518","last_page":"529"},"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":0.9969000220298767,"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/T10901","display_name":"Advanced Data Compression Techniques","score":0.9940000176429749,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8444039821624756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7192948460578918},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7100238800048828},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6882896423339844},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5732064843177795},{"id":"https://openalex.org/keywords/pronunciation","display_name":"Pronunciation","score":0.532646656036377},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5119396448135376},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.49935197830200195},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4508976936340332},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.43096667528152466},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4294581413269043},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2533248960971832},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11756694316864014},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08784541487693787},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08696645498275757},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0812612771987915}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8444039821624756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7192948460578918},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7100238800048828},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6882896423339844},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5732064843177795},{"id":"https://openalex.org/C2780844864","wikidata":"https://www.wikidata.org/wiki/Q184377","display_name":"Pronunciation","level":2,"score":0.532646656036377},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5119396448135376},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.49935197830200195},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4508976936340332},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.43096667528152466},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4294581413269043},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2533248960971832},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11756694316864014},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08784541487693787},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08696645498275757},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0812612771987915},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/p17-1048","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1048","pdf_url":"https://www.aclweb.org/anthology/P17-1048.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/p17-1048","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/p17-1048","pdf_url":"https://www.aclweb.org/anthology/P17-1048.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.5600000023841858,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2739883972.pdf","grobid_xml":"https://content.openalex.org/works/W2739883972.grobid-xml"},"referenced_works_count":32,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W37526647","https://openalex.org/W165283731","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1526236009","https://openalex.org/W1553004968","https://openalex.org/W1586532344","https://openalex.org/W1815076433","https://openalex.org/W1855892484","https://openalex.org/W1990005915","https://openalex.org/W2127141656","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/W2545177271","https://openalex.org/W2577366047","https://openalex.org/W2608712415","https://openalex.org/W2949640717","https://openalex.org/W2953320089","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2964308564","https://openalex.org/W3145501851"],"related_works":["https://openalex.org/W2235458433","https://openalex.org/W1953068910","https://openalex.org/W2150890698","https://openalex.org/W1592822300","https://openalex.org/W2137953178","https://openalex.org/W2974142481","https://openalex.org/W2442093297","https://openalex.org/W2058877998","https://openalex.org/W60887625","https://openalex.org/W3193318782"],"abstract_inverted_index":{"End-to-end":[0],"automatic":[1],"speech":[2],"recognition":[3],"(ASR)":[4],"has":[5],"become":[6],"a":[7,32,81,89],"popular":[8],"alternative":[9],"to":[10,31,53,70,106,120],"conventional":[11,121],"DNN/HMM":[12,123],"systems":[13,125],"because":[14],"it":[15],"avoids":[16],"the":[17,103,117],"need":[18],"for":[19,45,85],"linguistic":[20,127],"resources":[21],"such":[22],"as":[23],"pronunciation":[24],"dictionary,":[25],"tokenization,":[26],"and":[27,59,62,112,115],"contextdependency":[28],"trees,":[29],"leading":[30],"greatly":[33],"simplified":[34],"model-building":[35],"process.":[36],"There":[37],"are":[38],"two":[39,107],"major":[40],"types":[41],"of":[42],"end-to-end":[43,86],"architectures":[44],"ASR:":[46],"attention-based":[47],"methods":[48],"use":[49],"an":[50],"attention":[51],"mechanism":[52],"perform":[54],"alignment":[55],"between":[56],"acoustic":[57],"frames":[58],"recognized":[60],"symbols,":[61],"connectionist":[63],"temporal":[64],"classification":[65],"(CTC),":[66],"uses":[67],"Markov":[68],"assumptions":[69],"efficiently":[71],"solve":[72],"sequential":[73],"problems":[74],"by":[75],"dynamic":[76],"programming.":[77],"This":[78],"paper":[79],"proposes":[80],"joint":[82],"decoding":[83],"algorithm":[84],"ASR":[87,108,124],"with":[88],"hybrid":[90],"CTC/attention":[91],"architecture,":[92],"which":[93],"effectively":[94],"utilizes":[95],"both":[96],"advantages":[97],"in":[98],"decoding.":[99],"We":[100],"have":[101],"applied":[102],"proposed":[104],"method":[105],"benchmarks":[109],"(spontaneous":[110],"Japanese":[111],"Mandarin":[113],"Chinese),":[114],"showing":[116],"comparable":[118],"performance":[119],"state-of-the-art":[122],"without":[126],"resources.":[128]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":13},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":16},{"year":2022,"cited_by_count":18},{"year":2021,"cited_by_count":25},{"year":2020,"cited_by_count":16},{"year":2019,"cited_by_count":21},{"year":2018,"cited_by_count":10},{"year":2017,"cited_by_count":4}],"updated_date":"2026-07-19T07:52:34.831488","created_date":"2025-10-10T00:00:00"}