{"id":"https://openalex.org/W3006806348","doi":"https://doi.org/10.1109/asru46091.2019.9004018","title":"Character-Aware Attention-Based End-to-End Speech Recognition","display_name":"Character-Aware Attention-Based End-to-End Speech Recognition","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3006806348","doi":"https://doi.org/10.1109/asru46091.2019.9004018","mag":"3006806348"},"language":"en","primary_location":{"id":"doi:10.1109/asru46091.2019.9004018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004018","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 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":"2019 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/A5101749753","display_name":"Zhong Meng","orcid":"https://orcid.org/0000-0001-7814-5929"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Zhong Meng","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034136587","display_name":"Yashesh Gaur","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yashesh Gaur","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100365053","display_name":"Jinyu Li","orcid":"https://orcid.org/0000-0002-1089-9748"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jinyu Li","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077401426","display_name":"Yifan Gong","orcid":"https://orcid.org/0000-0001-8786-3391"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yifan Gong","raw_affiliation_strings":["Microsoft Corporation, Redmond, WA, USA"],"affiliations":[{"raw_affiliation_string":"Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101749753"],"corresponding_institution_ids":["https://openalex.org/I1290206253"],"apc_list":null,"apc_paid":null,"fwci":1.6802,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88668796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"abs 1612 2695","issue":null,"first_page":"949","last_page":"955"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9994999766349792,"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":0.9988999962806702,"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":0.7745174169540405},{"id":"https://openalex.org/keywords/recurrent-neural-network","display_name":"Recurrent neural network","score":0.7120779752731323},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6909326910972595},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.6627740859985352},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.6577108502388},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.6558013558387756},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5889530777931213},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5398203134536743},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.5343270897865295},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5093430280685425},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44932442903518677},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.4121883809566498},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06768900156021118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7745174169540405},{"id":"https://openalex.org/C147168706","wikidata":"https://www.wikidata.org/wiki/Q1457734","display_name":"Recurrent neural network","level":3,"score":0.7120779752731323},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6909326910972595},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.6627740859985352},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.6577108502388},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.6558013558387756},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5889530777931213},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5398203134536743},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.5343270897865295},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5093430280685425},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44932442903518677},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.4121883809566498},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06768900156021118},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru46091.2019.9004018","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru46091.2019.9004018","pdf_url":null,"source":{"id":"https://openalex.org/S4306498489","display_name":"2019 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":"2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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":39,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1828163288","https://openalex.org/W1924770834","https://openalex.org/W1938755728","https://openalex.org/W1984541135","https://openalex.org/W2076794394","https://openalex.org/W2095705004","https://openalex.org/W2102113734","https://openalex.org/W2121879602","https://openalex.org/W2127141656","https://openalex.org/W2133564696","https://openalex.org/W2160815625","https://openalex.org/W2296748324","https://openalex.org/W2327501763","https://openalex.org/W2577366047","https://openalex.org/W2606833507","https://openalex.org/W2608712415","https://openalex.org/W2636483419","https://openalex.org/W2899771611","https://openalex.org/W2951559648","https://openalex.org/W2962784628","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963240019","https://openalex.org/W2963970535","https://openalex.org/W2964199361","https://openalex.org/W2964308564","https://openalex.org/W2972621414","https://openalex.org/W3008008574","https://openalex.org/W3112742522","https://openalex.org/W6607333740","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6674330103","https://openalex.org/W6675365184","https://openalex.org/W6697318756","https://openalex.org/W6787533431"],"related_works":["https://openalex.org/W2937020545","https://openalex.org/W2398878249","https://openalex.org/W4286761151","https://openalex.org/W3037482496","https://openalex.org/W4291322237","https://openalex.org/W2547835662","https://openalex.org/W4327774331","https://openalex.org/W3015923889","https://openalex.org/W4385990907","https://openalex.org/W2608712415"],"abstract_inverted_index":{"Predicting":[0],"words":[1],"and":[2,43,104,125,136],"subword":[3],"units":[4],"(WSUs)":[5],"as":[6,25],"the":[7,15,29,59,84,100,102,105,117,129,134,148,157],"output":[8],"has":[9,53],"shown":[10],"to":[11,28,56,112,133,181],"be":[12],"effective":[13],"for":[14],"attention-based":[16],"encoder-decoder":[17],"(AED)":[18],"model":[19,58,74,149,194],"in":[20,46,75,131,151],"end-to-end":[21],"speech":[22],"recognition.":[23],"However,":[24],"one":[26],"input":[27],"decoder":[30,103],"recurrent":[31],"neural":[32],"network":[33,107],"(RNN),":[34],"each":[35,77],"WSU":[36,78,161],"embedding":[37,79],"is":[38,80,96],"learned":[39],"independently":[40],"through":[41,128],"context":[42],"acoustic":[44,137],"information":[45],"a":[47,69,91,109,141,152,164,172,187],"purely":[48],"data-driven":[49],"fashion.":[50],"Little":[51],"effort":[52],"been":[54],"made":[55],"explicitly":[57],"morphological":[60],"relationships":[61],"among":[62],"WSUs.":[63,114],"In":[64],"this":[65],"work,":[66],"we":[67],"propose":[68],"novel":[70],"character-aware":[71],"(CA)":[72],"AED":[73,111,154,189],"which":[76],"computed":[81],"by":[82,140,155],"summarizing":[83],"embeddings":[85,118,162],"of":[86,108,119,160,168],"its":[87],"constituent":[88],"characters":[89],"using":[90],"CA-RNN.":[92],"This":[93],"WSU-independent":[94],"CA-RNN":[95,130],"jointly":[97],"trained":[98],"with":[99,163,191],"encoder,":[101],"attention":[106],"conventional":[110],"predict":[113],"With":[115],"CA-AED,":[116],"morphologically":[120],"similar":[121],"WSUs":[122],"are":[123],"naturally":[124],"directly":[126],"correlated":[127],"addition":[132],"semantic":[135],"relations":[138],"modeled":[139],"traditional":[142,153],"AED.":[143],"Moreover,":[144],"CA-AED":[145,178],"significantly":[146],"reduces":[147],"parameters":[150],"replacing":[156],"large":[158],"pool":[159],"much":[165],"smaller":[166],"set":[167],"character":[169],"embeddings.":[170],"On":[171],"3400":[173],"hours":[174],"Microsoft":[175],"Cortana":[176],"dataset,":[177],"achieves":[179],"up":[180],"11.9%":[182],"relative":[183],"WER":[184],"improvement":[185],"over":[186],"strong":[188],"baseline":[190],"27.1%":[192],"fewer":[193],"parameters.":[195]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}