{"id":"https://openalex.org/W2913041008","doi":"https://doi.org/10.1109/slt.2018.8639587","title":"Improving Attention-Based End-to-End ASR Systems with Sequence-Based Loss Functions","display_name":"Improving Attention-Based End-to-End ASR Systems with Sequence-Based Loss Functions","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913041008","doi":"https://doi.org/10.1109/slt.2018.8639587","mag":"2913041008"},"language":"en","primary_location":{"id":"doi:10.1109/slt.2018.8639587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639587","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/A5101625242","display_name":"Jia Cui","orcid":"https://orcid.org/0000-0002-1631-0535"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jia Cui","raw_affiliation_strings":["Tencent AI Lab, Bellevue, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106404246","display_name":"Chao Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chao Weng","raw_affiliation_strings":["Tencent AI Lab, Bellevue, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085034441","display_name":"Guangsen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangsen Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110195480","display_name":"Jun Wang","orcid":"https://orcid.org/0000-0001-8932-6661"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peidong Wang","raw_affiliation_strings":["Tencent AI Lab, Bellevue, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040951732","display_name":"Chengzhu Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chengzhu Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dan Su","raw_affiliation_strings":["Tencent AI Lab, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Shenzhen, China","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[{"id":"https://openalex.org/I4210108985","display_name":"Bellevue Hospital Center","ror":"https://ror.org/01ky34z31","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1283621791","https://openalex.org/I4210086933","https://openalex.org/I4210108985"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Yu","raw_affiliation_strings":["Tencent AI Lab, Bellevue, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0275,"has_fulltext":false,"cited_by_count":14,"citation_normalized_percentile":{"value":0.90184211,"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":"353","last_page":"360"},"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":0.9986000061035156,"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":0.9973999857902527,"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":0.8063031435012817},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.5394777059555054},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.4943547248840332},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48026156425476074},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.47935372591018677},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.4787537455558777},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4742944538593292},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.4334977865219116},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42672935128211975},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31328004598617554},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1539953052997589}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8063031435012817},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.5394777059555054},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.4943547248840332},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48026156425476074},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.47935372591018677},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.4787537455558777},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4742944538593292},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.4334977865219116},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42672935128211975},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31328004598617554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1539953052997589},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt.2018.8639587","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt.2018.8639587","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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W6908809","https://openalex.org/W854541894","https://openalex.org/W1508165687","https://openalex.org/W1522301498","https://openalex.org/W1524333225","https://openalex.org/W1586532344","https://openalex.org/W1828163288","https://openalex.org/W1855892484","https://openalex.org/W1902237438","https://openalex.org/W1994606281","https://openalex.org/W2025198378","https://openalex.org/W2091432990","https://openalex.org/W2096140469","https://openalex.org/W2114016253","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2160815625","https://openalex.org/W2178654303","https://openalex.org/W2184045248","https://openalex.org/W2193413348","https://openalex.org/W2291975472","https://openalex.org/W2395416438","https://openalex.org/W2407080277","https://openalex.org/W2514741789","https://openalex.org/W2519224033","https://openalex.org/W2521999726","https://openalex.org/W2525778437","https://openalex.org/W2526425061","https://openalex.org/W2545177271","https://openalex.org/W2597757402","https://openalex.org/W2608712415","https://openalex.org/W2738463834","https://openalex.org/W2738829388","https://openalex.org/W2746192915","https://openalex.org/W2787663903","https://openalex.org/W2799800213","https://openalex.org/W2888779557","https://openalex.org/W2889163603","https://openalex.org/W2899771611","https://openalex.org/W2962824709","https://openalex.org/W2962826786","https://openalex.org/W2963212250","https://openalex.org/W2963266252","https://openalex.org/W2963729263","https://openalex.org/W2963953073","https://openalex.org/W2964121744","https://openalex.org/W3099832538","https://openalex.org/W6600284362","https://openalex.org/W6623517193","https://openalex.org/W6631190155","https://openalex.org/W6631362777","https://openalex.org/W6635078382","https://openalex.org/W6638749077","https://openalex.org/W6639156005","https://openalex.org/W6656619859","https://openalex.org/W6685711979","https://openalex.org/W6687566353","https://openalex.org/W6697040452","https://openalex.org/W6713762819","https://openalex.org/W6726109732","https://openalex.org/W6728910023","https://openalex.org/W6734588641","https://openalex.org/W6741321433","https://openalex.org/W6743477263","https://openalex.org/W6748477376","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W4205841273","https://openalex.org/W4205525690","https://openalex.org/W1732468982","https://openalex.org/W1761388607","https://openalex.org/W1997922073","https://openalex.org/W350032239","https://openalex.org/W2604685715","https://openalex.org/W2412160900","https://openalex.org/W2136453575","https://openalex.org/W1596913645"],"abstract_inverted_index":{"Acoustic":[0],"model":[1,4,106,154,168],"and":[2,47],"language":[3],"(LM)":[5],"have":[6],"been":[7,25,59],"two":[8],"major":[9],"components":[10,31],"in":[11,33,62],"conventional":[12],"speech":[13],"recognition":[14,78],"systems.":[15],"They":[16],"are":[17,85],"normally":[18],"trained":[19,87,167,175],"independently,":[20],"but":[21,169],"recently":[22],"there":[23],"has":[24,56],"a":[26,34],"trend":[27],"to":[28,99,110,186],"optimize":[29],"both":[30,146],"simultaneously":[32],"unified":[35],"end-to-end":[36],"(E2E)":[37],"framework.":[38,65],"However,":[39],"the":[40,44,48,63,70,89,123,152,163],"performance":[41],"gap":[42],"between":[43],"E2E":[45,73,102],"systems":[46,51,74,103],"traditional":[49],"hybrid":[50],"suggests":[52],"that":[53,69,145,179],"some":[54],"knowledge":[55],"not":[57],"yet":[58],"fully":[60],"utilized":[61],"new":[64],"An":[66],"observation":[67],"is":[68,117,136,170,184],"current":[71],"attention-based":[72,101],"could":[75,149],"produce":[76],"better":[77],"results":[79],"when":[80],"decoded":[81],"with":[82,88,122],"LMs":[83],"which":[84],"independently":[86],"same":[90,164],"resource.":[91],"In":[92],"this":[93],"paper,":[94],"we":[95],"focus":[96],"on":[97,141],"how":[98],"improve":[100,151],"without":[104],"increasing":[105],"complexity":[107],"or":[108],"resorting":[109],"extra":[111],"data.":[112],"A":[113],"novel":[114],"training":[115,121],"strategy":[116],"proposed":[118],"for":[119,165,173],"multi-task":[120],"connectionist":[124],"temporal":[125],"classification":[126],"(CTC)":[127],"loss.":[128],"The":[129,156],"sequence-based":[130],"minimum":[131],"Bayes":[132],"risk":[133],"(MBR)":[134],"loss":[135,147,182,192],"also":[137],"investigated.":[138],"Our":[139],"experiments":[140],"SWB":[142],"300hrs":[143],"showed":[144],"functions":[148],"significantly":[150],"baseline":[153],"performance.":[155],"additional":[157],"gain":[158],"from":[159],"joint-LM":[160],"decoding":[161],"remains":[162],"CTC":[166,181],"only":[171],"marginal":[172],"MBR":[174,191],"model.":[176],"This":[177],"implies":[178],"while":[180],"function":[183,193],"able":[185],"capture":[187],"more":[188,195],"acoustic":[189],"knowledge,":[190],"exploits":[194],"word/character":[196],"dependency.":[197]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":8}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}