{"id":"https://openalex.org/W2884852625","doi":"https://doi.org/10.1109/slt.2018.8639528","title":"Multi-Scale Alignment and Contextual History for Attention Mechanism in Sequence-to-Sequence Model","display_name":"Multi-Scale Alignment and Contextual History for Attention Mechanism in Sequence-to-Sequence Model","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2884852625","doi":"https://doi.org/10.1109/slt.2018.8639528","mag":"2884852625"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","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/A5038296765","display_name":"Andros Tjandra","orcid":"https://orcid.org/0000-0003-1246-5908"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Andros Tjandra","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040108974","display_name":"Sakriani Sakti","orcid":"https://orcid.org/0000-0001-5509-8963"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sakriani Sakti","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020994673","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0001-6956-3803"},"institutions":[{"id":"https://openalex.org/I75917431","display_name":"Nara Institute of Science and Technology","ror":"https://ror.org/05bhada84","country_code":"JP","type":"education","lineage":["https://openalex.org/I75917431"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Satoshi Nakamura","raw_affiliation_strings":["Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Nara Institute of Science and Technology, Japan","institution_ids":["https://openalex.org/I75917431"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038296765"],"corresponding_institution_ids":["https://openalex.org/I75917431"],"apc_list":null,"apc_paid":null,"fwci":1.9546,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89507746,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9995999932289124,"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":0.9986000061035156,"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/sequence","display_name":"Sequence (biology)","score":0.7865920662879944},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7592201232910156},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6599076390266418},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5852282643318176},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5026659965515137},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4247223436832428}],"concepts":[{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7865920662879944},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7592201232910156},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6599076390266418},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5852282643318176},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5026659965515137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4247223436832428},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639528","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.46000000834465027}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W854541894","https://openalex.org/W1514535095","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1710082047","https://openalex.org/W1902237438","https://openalex.org/W1921523184","https://openalex.org/W2024490156","https://openalex.org/W2130942839","https://openalex.org/W2133564696","https://openalex.org/W2144499799","https://openalex.org/W2191779130","https://openalex.org/W2327501763","https://openalex.org/W2526425061","https://openalex.org/W2605141709","https://openalex.org/W2747920239","https://openalex.org/W2767601419","https://openalex.org/W2962699523","https://openalex.org/W2962759037","https://openalex.org/W2962826786","https://openalex.org/W2963312585","https://openalex.org/W2963609956","https://openalex.org/W2963796886","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W6623517193","https://openalex.org/W6630875275","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6640185926","https://openalex.org/W6679434410","https://openalex.org/W6679436768","https://openalex.org/W6735706088","https://openalex.org/W6745177358","https://openalex.org/W6745543685"],"related_works":["https://openalex.org/W4390516098","https://openalex.org/W2181948922","https://openalex.org/W2384362569","https://openalex.org/W4205302943","https://openalex.org/W2561132942","https://openalex.org/W2142795561","https://openalex.org/W3155418658","https://openalex.org/W4243199227","https://openalex.org/W2379948177","https://openalex.org/W2107949441"],"abstract_inverted_index":{"A":[0],"sequence-to-sequence":[1,16,53,98],"model":[2,17,39,54],"is":[3,27],"a":[4,117],"neural":[5],"network":[6],"module":[7],"for":[8,97],"mapping":[9],"two":[10,49],"sequences":[11],"of":[12,66],"different":[13],"lengths.":[14],"The":[15,104],"has":[18],"three":[19],"core":[20],"modules:":[21],"encoder,":[22],"decoder,":[23],"and":[24,34,37,69,101],"attention.":[25],"Attention":[26],"the":[28,32,58,64,67,70,88],"bridge":[29],"that":[30,107],"connects":[31],"encoder":[33],"decoder":[35,90],"modules":[36],"improves":[38],"performance":[40,55,113],"in":[41],"many":[42],"tasks.":[43],"In":[44],"this":[45],"paper,":[46],"we":[47,62,78],"propose":[48],"ideas":[50],"to":[51,87,116],"improve":[52,112],"by":[56],"enhancing":[57],"attention":[59,85,119],"module.":[60],"First,":[61],"maintain":[63],"history":[65],"location":[68],"expected":[71],"context":[72],"from":[73,82],"several":[74,83],"previous":[75,84],"time-steps.":[76],"Second,":[77],"apply":[79],"multiscale":[80],"convolution":[81],"vectors":[86],"current":[89],"state.":[91],"We":[92],"utilized":[93],"our":[94,108],"proposed":[95,109],"framework":[96],"speech":[99],"recognition":[100],"text-to-speech":[102],"systems.":[103],"results":[105],"reveal":[106],"extension":[110],"can":[111],"significantly":[114],"compared":[115],"standard":[118],"baseline.":[120]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"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"}