{"id":"https://openalex.org/W2962759037","doi":"https://doi.org/10.1109/asru.2017.8268951","title":"Attention-based Wav2Text with feature transfer learning","display_name":"Attention-based Wav2Text with feature transfer learning","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2962759037","doi":"https://doi.org/10.1109/asru.2017.8268951","mag":"2962759037"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268951","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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":["Graduate School of Information Science, Nara Institute of Science and Technology, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science, 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":2.9254,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.93138219,"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":"309","last_page":"315"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9994000196456909,"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":0.812048614025116},{"id":"https://openalex.org/keywords/waveform","display_name":"Waveform","score":0.6998571157455444},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6797623634338379},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6377077102661133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5532377362251282},{"id":"https://openalex.org/keywords/transfer-of-learning","display_name":"Transfer of learning","score":0.5186249613761902},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.5100517868995667},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5083031058311462},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4809962213039398},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4769945740699768},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4563712179660797},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.45235636830329895},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42372697591781616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812048614025116},{"id":"https://openalex.org/C197424946","wikidata":"https://www.wikidata.org/wiki/Q1165717","display_name":"Waveform","level":3,"score":0.6998571157455444},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6797623634338379},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6377077102661133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5532377362251282},{"id":"https://openalex.org/C150899416","wikidata":"https://www.wikidata.org/wiki/Q1820378","display_name":"Transfer of learning","level":2,"score":0.5186249613761902},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.5100517868995667},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5083031058311462},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4809962213039398},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4769945740699768},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4563712179660797},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.45235636830329895},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42372697591781616},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"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/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268951","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268951","pdf_url":null,"source":{"id":"https://openalex.org/S4306498158","display_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4099999964237213}],"awards":[],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W950853366","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1634752325","https://openalex.org/W1710082047","https://openalex.org/W1799366690","https://openalex.org/W1902237438","https://openalex.org/W2012897754","https://openalex.org/W2024490156","https://openalex.org/W2064675550","https://openalex.org/W2072349636","https://openalex.org/W2123045220","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2142416747","https://openalex.org/W2143612262","https://openalex.org/W2147800946","https://openalex.org/W2149933564","https://openalex.org/W2163922914","https://openalex.org/W2168249605","https://openalex.org/W2193413348","https://openalex.org/W2327501763","https://openalex.org/W2398826216","https://openalex.org/W2399016933","https://openalex.org/W2400718301","https://openalex.org/W2508048623","https://openalex.org/W2520160253","https://openalex.org/W2526425061","https://openalex.org/W2962826786","https://openalex.org/W2963382180","https://openalex.org/W2964121744","https://openalex.org/W2964308564","https://openalex.org/W4205130185","https://openalex.org/W4299518610","https://openalex.org/W6631362777","https://openalex.org/W6682132143","https://openalex.org/W6687566353","https://openalex.org/W6712560600","https://openalex.org/W6712686019","https://openalex.org/W6712963495"],"related_works":["https://openalex.org/W2053269318","https://openalex.org/W2364370872","https://openalex.org/W1974895211","https://openalex.org/W2176409448","https://openalex.org/W2129841057","https://openalex.org/W2097963413","https://openalex.org/W3040712279","https://openalex.org/W2364769705","https://openalex.org/W2025614924","https://openalex.org/W2294335174"],"abstract_inverted_index":{"Conventional":[0],"automatic":[1],"speech":[2,15,21,124],"recognition":[3,9],"(ASR)":[4],"typically":[5],"performs":[6],"multi-level":[7],"pattern":[8],"tasks":[10],"that":[11,28,158],"map":[12],"the":[13,32,38,42,51,61,65,75,86,97,113,127,132,139,143,159,176],"acoustic":[14],"waveform":[16,63,92,125,167],"into":[17],"a":[18,55,150,170],"hierarchy":[19],"of":[20,44,53,142],"units.":[22],"But,":[23],"it":[24],"is":[25],"widely":[26],"known":[27],"information":[29],"loss":[30],"in":[31,50,78,89,173],"earlier":[33],"stage":[34],"can":[35],"propagate":[36],"through":[37],"later":[39],"stages.":[40],"After":[41],"resurgence":[43],"deep":[45,99],"learning,":[46],"interest":[47],"has":[48],"emerged":[49],"possibility":[52],"developing":[54],"purely":[56],"end-to-end":[57,79,115,144],"ASR":[58],"system":[59],"from":[60,122],"raw":[62,91,123,166],"to":[64,119,126,148],"transcription":[66],"without":[67],"any":[68],"predefined":[69],"alignments":[70],"and":[71],"hand-engineered":[72],"models.":[73],"However,":[74],"successful":[76,87],"attempts":[77,88],"architecture":[80],"still":[81,94],"used":[82],"spectral-based":[83],"features,":[84],"while":[85],"using":[90],"were":[93],"based":[95],"on":[96,181],"hybrid":[98],"neural":[100],"network":[101],"-":[102],"Hidden":[103],"Markov":[104],"model":[105,118,133,163,179],"(DNN-HMM)":[106],"framework.":[107],"In":[108],"this":[109],"paper,":[110],"we":[111,146],"construct":[112],"first":[114],"attention-based":[116],"encoder-decoder":[117,178],"process":[120,141],"directly":[121,164],"text":[128],"transcription.":[129],"We":[130],"called":[131],"as":[134],"Attention-based":[135,161],"Wav2Text.":[136],"To":[137],"assist":[138],"training":[140],"model,":[145],"propose":[147],"utilize":[149],"feature":[151],"transfer":[152],"learning.":[153],"Experimental":[154],"results":[155],"also":[156],"reveal":[157],"proposed":[160],"Wav2Text":[162],"with":[165,175],"could":[168],"achieve":[169],"better":[171],"result":[172],"comparison":[174],"attentional":[177],"trained":[180],"standard":[182],"front-end":[183],"filterbank":[184],"features.":[185]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}