{"id":"https://openalex.org/W2890197052","doi":"https://doi.org/10.1109/icassp.2018.8462576","title":"Acoustic-to-Word Attention-Based Model Complemented with Character-Level CTC-Based Model","display_name":"Acoustic-to-Word Attention-Based Model Complemented with Character-Level CTC-Based Model","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2890197052","doi":"https://doi.org/10.1109/icassp.2018.8462576","mag":"2890197052"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8462576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103835523","display_name":"Sei Ueno","orcid":"https://orcid.org/0000-0002-2255-3154"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Sei Ueno","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040282669","display_name":"Hirofumi Inaguma","orcid":"https://orcid.org/0000-0003-0610-1251"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hirofumi Inaguma","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102851028","display_name":"Masato Mimura","orcid":"https://orcid.org/0000-0002-2403-0680"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masato Mimura","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5038044080","display_name":"Tatsuya Kawahara","orcid":"https://orcid.org/0000-0002-2686-2296"},"institutions":[{"id":"https://openalex.org/I22299242","display_name":"Kyoto University","ror":"https://ror.org/02kpeqv85","country_code":"JP","type":"education","lineage":["https://openalex.org/I22299242"]},{"id":"https://openalex.org/I39012071","display_name":"Kyoto College of Graduate Studies for Informatics","ror":"https://ror.org/05mzj8a56","country_code":"JP","type":"education","lineage":["https://openalex.org/I39012071"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tatsuya Kawahara","raw_affiliation_strings":["Graduate School of Informatics, Kyoto University, Kyoto, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Informatics, Kyoto University, Kyoto, Japan","institution_ids":["https://openalex.org/I39012071","https://openalex.org/I22299242"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":47,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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":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/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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9983000159263611,"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":0.8473392128944397},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.7105449438095093},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6701640486717224},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6539127230644226},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.6181012392044067},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6129883527755737},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5955672264099121},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5886727571487427},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5613495707511902},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5324526429176331},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4914323091506958},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4427463710308075},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35826295614242554},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.33034420013427734},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0822068452835083}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8473392128944397},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.7105449438095093},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6701640486717224},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6539127230644226},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.6181012392044067},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6129883527755737},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5955672264099121},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5886727571487427},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5613495707511902},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5324526429176331},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4914323091506958},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4427463710308075},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35826295614242554},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.33034420013427734},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0822068452835083},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8462576","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8462576","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7699999809265137,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W37526647","https://openalex.org/W854541894","https://openalex.org/W1489125746","https://openalex.org/W1522301498","https://openalex.org/W1586532344","https://openalex.org/W2005522781","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2291513470","https://openalex.org/W2327501763","https://openalex.org/W2519224033","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2749514303","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963266252","https://openalex.org/W2963303028","https://openalex.org/W6601563604","https://openalex.org/W6623517193","https://openalex.org/W6635078382","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6728910023","https://openalex.org/W6735390525"],"related_works":["https://openalex.org/W2159208002","https://openalex.org/W2150890698","https://openalex.org/W2974142481","https://openalex.org/W2058877998","https://openalex.org/W2038107365","https://openalex.org/W2162248568","https://openalex.org/W1489815656","https://openalex.org/W2101346879","https://openalex.org/W2953291251","https://openalex.org/W4290682478"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"end-to-end":[3,127],"speech":[4],"recognition":[5],"which":[6],"directly":[7],"maps":[8],"acoustic":[9],"features":[10],"to":[11,100],"a":[12,61,65,182,187],"word":[13],"sequence.":[14],"The":[15,40],"acoustic-to-word":[16,150],"model":[17,28,73,77,97,152,162],"is":[18,46,98,163],"attractive":[19],"since":[20],"it":[21,91],"does":[22],"not":[23,107],"require":[24],"an":[25,30],"external":[26],"language":[27],"and":[29,37,87,122,165],"elaborate":[31],"decoder,":[32],"resulting":[33],"in":[34,125],"extremely":[35],"simple":[36],"fast":[38],"decoding.":[39],"apparent":[41],"drawback":[42],"of":[43,48,70,81,84,117,142,189],"this":[44,57],"modeling":[45],"sparseness":[47],"training":[49,69],"data,":[50],"particularly":[51],"for":[52,134],"less":[53],"frequent":[54],"words.":[55],"In":[56],"paper,":[58],"we":[59,129],"propose":[60],"framework":[62],"complemented":[63],"with":[64,74,159,181],"character-level":[66,76,96,160],"model.":[67,112],"Joint":[68],"the":[71,75,79,95,110,126,135,140,149,167,177],"word-level":[72,111],"enhances":[78],"generality":[80],"deep":[82],"learning":[83,157],"feature":[85],"extraction":[86],"classification":[88,120],"processes,":[89],"preventing":[90],"from":[92],"overfitting.":[93],"Moreover,":[94],"used":[99],"decode":[101],"out-of-vocabulary":[102],"(OOV)":[103],"words":[104],"that":[105,147],"are":[106,115],"covered":[108],"by":[109,186],"Since":[113],"there":[114],"choices":[116],"connectionist":[118],"temporal":[119],"(CTC)":[121],"attention-based":[123,151],"models":[124],"recognition,":[128],"also":[130],"explore":[131],"optimal":[132],"combination":[133],"hybrid":[136,168],"system.":[137],"Evaluations":[138],"on":[139],"Corpus":[141],"Spontaneous":[143],"Japanese":[144],"(CSJ)":[145],"show":[146],"(1)":[148],"outperforms":[153],"CTC,":[154],"(2)":[155],"multitask":[156],"(MTL)":[158],"CTC":[161],"effective,":[164],"(3)":[166],"system":[169,180],"achieves":[170],"comparable":[171],"or":[172],"even":[173],"better":[174],"accuracy":[175],"than":[176],"standard":[178],"DNN-HMM":[179],"decoding":[183],"speed":[184],"faster":[185],"factor":[188],"25.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":6}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}