{"id":"https://openalex.org/W2963590118","doi":"https://doi.org/10.21437/interspeech.2018-1655","title":"Multi-Head Decoder for End-to-End Speech Recognition","display_name":"Multi-Head Decoder for End-to-End Speech Recognition","publication_year":2018,"publication_date":"2018-08-28","ids":{"openalex":"https://openalex.org/W2963590118","doi":"https://doi.org/10.21437/interspeech.2018-1655","mag":"2963590118"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2018-1655","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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/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":true,"raw_author_name":"Tomoki Hayashi","raw_affiliation_strings":["Nagoya University,"],"affiliations":[{"raw_affiliation_string":"Nagoya University,","institution_ids":["https://openalex.org/I60134161"]}]},{"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/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Johns Hopkins University"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins University","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"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 Toda","raw_affiliation_strings":["Nagoya University,"],"affiliations":[{"raw_affiliation_string":"Nagoya University,","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042118446","display_name":"Kazuya Takeda","orcid":"https://orcid.org/0000-0002-0330-1787"},"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":"Kazuya Takeda","raw_affiliation_strings":["Nagoya University,"],"affiliations":[{"raw_affiliation_string":"Nagoya University,","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078778981"],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":2.2802,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.9119274,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"801","last_page":"805"},"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/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/T10028","display_name":"Topic Modeling","score":0.9990000128746033,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8509687185287476},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6942356824874878},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6466822624206543},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5807732939720154},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.49147140979766846},{"id":"https://openalex.org/keywords/head","display_name":"Head (geology)","score":0.4723820686340332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4536232352256775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.130816251039505}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8509687185287476},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6942356824874878},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6466822624206543},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5807732939720154},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.49147140979766846},{"id":"https://openalex.org/C2780312720","wikidata":"https://www.wikidata.org/wiki/Q5689100","display_name":"Head (geology)","level":2,"score":0.4723820686340332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4536232352256775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.130816251039505},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114793014","wikidata":"https://www.wikidata.org/wiki/Q52109","display_name":"Geomorphology","level":1,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2018-1655","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2018-1655","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2018","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":22,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W37526647","https://openalex.org/W179875071","https://openalex.org/W854541894","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1736701665","https://openalex.org/W1902237438","https://openalex.org/W1990005915","https://openalex.org/W2102113734","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2150355110","https://openalex.org/W2157331557","https://openalex.org/W2193413348","https://openalex.org/W2293634267","https://openalex.org/W2327501763","https://openalex.org/W2545177271","https://openalex.org/W2606974598","https://openalex.org/W2766219058","https://openalex.org/W3173163413","https://openalex.org/W4385245566"],"related_works":["https://openalex.org/W3179968364","https://openalex.org/W1999612375","https://openalex.org/W3203142394","https://openalex.org/W2938107654","https://openalex.org/W4390516098","https://openalex.org/W2151749779","https://openalex.org/W2161474341","https://openalex.org/W3008587939","https://openalex.org/W4302615923","https://openalex.org/W2181948922"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"a":[3,18,36,65],"new":[4],"network":[5],"architecture":[6],"called":[7],"multihead":[8],"decoder":[9],"for":[10,56,84],"end-to-end":[11],"speech":[12],"recognition":[13,93],"as":[14,127],"an":[15,96,108],"extension":[16],"of":[17,43,91,102,113],"multi-head":[19,23,130],"attention":[20,24,48,58,80,131],"model.In":[21],"the":[22,39,44,47,76,89,92,100,123,142],"model,":[25],"multiple":[26,54],"attentions":[27],"are":[28,33,82],"calculated,":[29],"and":[30,59,129,133],"then,":[31],"they":[32],"integrated":[34],"into":[35],"single":[37],"attention.On":[38],"other":[40],"hand,":[41],"instead":[42],"integration":[45],"in":[46,68],"level,":[49],"our":[50,103,119],"proposed":[51,104,120],"method":[52,121],"uses":[53],"decoders":[55],"each":[57,72,85],"integrates":[60],"their":[61],"outputs":[62],"to":[63,70,74,88],"generate":[64],"final":[66],"output.Furthermore,":[67],"order":[69],"make":[71],"head":[73],"capture":[75,137],"different":[77,79,138],"modalities,":[78],"functions":[81],"used":[83],"head,":[86],"leading":[87],"improvement":[90],"performance":[94],"with":[95],"ensemble":[97],"effect.To":[98],"evaluate":[99],"effectiveness":[101],"method,":[105],"we":[106],"conduct":[107],"experimental":[109],"evaluation":[110],"using":[111],"Corpus":[112],"Spontaneous":[114],"Japanese.Experimental":[115],"results":[116],"demonstrate":[117],"that":[118,134],"outperforms":[122],"conventional":[124],"methods":[125],"such":[126],"locationbased":[128],"models,":[132],"it":[135],"can":[136],"speech/linguistic":[139],"contexts":[140],"within":[141],"attention-based":[143],"encoder-decoder":[144],"framework.":[145]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}