{"id":"https://openalex.org/W2787663903","doi":"https://doi.org/10.1109/asru.2017.8268948","title":"Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition","display_name":"Multi-level language modeling and decoding for open vocabulary end-to-end speech recognition","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2787663903","doi":"https://doi.org/10.1109/asru.2017.8268948","mag":"2787663903"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2017.8268948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268948","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/A5087554069","display_name":"Takaaki Hori","orcid":"https://orcid.org/0000-0003-4560-8039"},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Takaaki Hori","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"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/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shinji Watanabe","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112763337","display_name":"John R. Hershey","orcid":null},"institutions":[{"id":"https://openalex.org/I4210159266","display_name":"Mitsubishi Electric (United States)","ror":"https://ror.org/053jnhe44","country_code":"US","type":"company","lineage":["https://openalex.org/I1306287861","https://openalex.org/I4210133125","https://openalex.org/I4210159266"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John R. Hershey","raw_affiliation_strings":["Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA"],"affiliations":[{"raw_affiliation_string":"Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, USA","institution_ids":["https://openalex.org/I4210159266"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5087554069"],"corresponding_institution_ids":["https://openalex.org/I4210159266"],"apc_list":null,"apc_paid":null,"fwci":6.4356,"has_fulltext":false,"cited_by_count":52,"citation_normalized_percentile":{"value":0.97268834,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"287","last_page":"293"},"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":0.9990000128746033,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/computer-science","display_name":"Computer science","score":0.8151437044143677},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7037218809127808},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.693505585193634},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6375437378883362},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6094839572906494},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.564436137676239},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5639678239822388},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5143042802810669},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.509739339351654},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5060552954673767},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4989614486694336},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4959731996059418},{"id":"https://openalex.org/keywords/word-recognition","display_name":"Word recognition","score":0.46488046646118164},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.46256834268569946},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4617021679878235},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4127238690853119},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.3147326111793518},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27766498923301697},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.19872283935546875},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0764114260673523}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8151437044143677},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7037218809127808},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.693505585193634},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6375437378883362},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6094839572906494},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.564436137676239},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5639678239822388},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5143042802810669},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.509739339351654},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5060552954673767},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4989614486694336},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4959731996059418},{"id":"https://openalex.org/C150856459","wikidata":"https://www.wikidata.org/wiki/Q8034367","display_name":"Word recognition","level":3,"score":0.46488046646118164},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.46256834268569946},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4617021679878235},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4127238690853119},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.3147326111793518},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27766498923301697},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.19872283935546875},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0764114260673523},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2017.8268948","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2017.8268948","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":[{"score":0.8600000143051147,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1488211819","https://openalex.org/W1501139663","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1600744878","https://openalex.org/W1686810756","https://openalex.org/W1815076433","https://openalex.org/W2046932483","https://openalex.org/W2102113734","https://openalex.org/W2127141656","https://openalex.org/W2144499799","https://openalex.org/W2327501763","https://openalex.org/W2408623794","https://openalex.org/W2514741789","https://openalex.org/W2514969556","https://openalex.org/W2526425061","https://openalex.org/W2530486890","https://openalex.org/W2530876040","https://openalex.org/W2577366047","https://openalex.org/W2578686723","https://openalex.org/W2608712415","https://openalex.org/W2627092829","https://openalex.org/W2739883972","https://openalex.org/W2952288254","https://openalex.org/W2962826786","https://openalex.org/W2963211739","https://openalex.org/W2963403664","https://openalex.org/W6623517193","https://openalex.org/W6631362777","https://openalex.org/W6675365184","https://openalex.org/W6702097088","https://openalex.org/W6728030952","https://openalex.org/W6728811460","https://openalex.org/W6731979058","https://openalex.org/W6739366949"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2916997151","https://openalex.org/W1980930823","https://openalex.org/W2949174760","https://openalex.org/W2148167314"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,24,29,54,78,97,122,145],"combination":[3],"of":[4,82,85,92],"character-based":[5,25,55,64,119,138],"and":[6,49,110,168],"word-based":[7,134],"language":[8],"models":[9],"in":[10,47],"an":[11],"end-to-end":[12,101,179],"automatic":[13],"speech":[14],"recognition":[15,40],"(ASR)":[16],"architecture.":[17,35],"In":[18,144],"our":[19],"prior":[20],"work,":[21],"we":[22,152],"combined":[23],"LSTM":[26],"RNN-LM":[27],"with":[28,77,104,117],"hybrid":[30],"attention/connectionist":[31],"temporal":[32],"classification":[33],"(CTC)":[34],"The":[36],"character":[37,109],"LMs":[38,65,71,105],"improved":[39],"accuracy":[41],"to":[42,69],"rival":[43],"state-of-the-art":[44],"DNN/HMM":[45],"systems":[46,181],"Japanese":[48],"Mandarin":[50],"Chinese":[51],"tasks.":[52],"Although":[53],"architecture":[56],"can":[57],"provide":[58],"for":[59,72,100,141,157,178],"open":[60],"vocabulary":[61],"recognition,":[62],"the":[63,83,108,118,133,137,158,164,174],"generally":[66],"under-perform":[67],"relative":[68],"word":[70,111,123],"languages":[73],"such":[74],"as":[75],"English":[76],"small":[79],"alphabet,":[80],"because":[81],"difficulty":[84],"modeling":[86],"Linguistic":[87],"constraints":[88],"across":[89],"long":[90],"sequences":[91],"characters.":[93],"This":[94],"paper":[95],"presents":[96],"novel":[98],"method":[99],"ASR":[102,180],"decoding":[103],"at":[106],"both":[107],"level.":[112],"Hypotheses":[113],"are":[114,129],"first":[115],"scored":[116],"LM":[120,139],"until":[121],"boundary":[124],"is":[125,173],"encountered.":[126],"Known":[127],"words":[128],"then":[130],"re-scored":[131],"using":[132,162],"LM,":[135],"while":[136],"provides":[140],"out-of-vocabulary":[142],"scores.":[143],"standard":[146],"Wall":[147],"Street":[148],"Journal":[149],"(WSJ)":[150],"task,":[151],"achieved":[153],"5.6":[154],"%":[155],"WER":[156],"Eval'92":[159],"test":[160],"set":[161,167],"only":[163],"SI284":[165],"training":[166],"WSJ":[169],"text":[170],"data,":[171],"which":[172],"best":[175],"score":[176],"reported":[177],"on":[182],"this":[183],"benchmark.":[184]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}