{"id":"https://openalex.org/W2937972951","doi":"https://doi.org/10.1109/icassp.2019.8683302","title":"Token-wise Training for Attention Based End-to-end Speech Recognition","display_name":"Token-wise Training for Attention Based End-to-end Speech Recognition","publication_year":2019,"publication_date":"2019-04-17","ids":{"openalex":"https://openalex.org/W2937972951","doi":"https://doi.org/10.1109/icassp.2019.8683302","mag":"2937972951"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2019.8683302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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/A5062250845","display_name":"Peidong Wang","orcid":"https://orcid.org/0000-0002-7042-0209"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Peidong Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Ohio State University, Columbus, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","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"],"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"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Tencent AI Lab, Bellevue, USA","institution_ids":["https://openalex.org/I4210108985"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5062250845"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.28,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.6384576,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"6276","last_page":"6280"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9973000288009644,"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":0.9965000152587891,"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/security-token","display_name":"Security token","score":0.8294566869735718},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8134305477142334},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7322957515716553},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.729680061340332},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6954333782196045},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6670974493026733},{"id":"https://openalex.org/keywords/dependency","display_name":"Dependency (UML)","score":0.6330525875091553},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5979263782501221},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5686429738998413},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5600298643112183},{"id":"https://openalex.org/keywords/beam-search","display_name":"Beam search","score":0.42700842022895813},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4142637252807617},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.16755664348602295},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.10408493876457214},{"id":"https://openalex.org/keywords/search-algorithm","display_name":"Search algorithm","score":0.0757666826248169}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8294566869735718},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8134305477142334},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7322957515716553},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.729680061340332},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6954333782196045},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6670974493026733},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.6330525875091553},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5979263782501221},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5686429738998413},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5600298643112183},{"id":"https://openalex.org/C19889080","wikidata":"https://www.wikidata.org/wiki/Q2835852","display_name":"Beam search","level":3,"score":0.42700842022895813},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4142637252807617},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.16755664348602295},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.10408493876457214},{"id":"https://openalex.org/C125583679","wikidata":"https://www.wikidata.org/wiki/Q755673","display_name":"Search algorithm","level":2,"score":0.0757666826248169},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2019.8683302","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2019.8683302","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":35,"referenced_works":["https://openalex.org/W648786980","https://openalex.org/W854541894","https://openalex.org/W1646152356","https://openalex.org/W2008937008","https://openalex.org/W2104917081","https://openalex.org/W2131342762","https://openalex.org/W2143564602","https://openalex.org/W2180816288","https://openalex.org/W2327501763","https://openalex.org/W2525778437","https://openalex.org/W2607793981","https://openalex.org/W2608712415","https://openalex.org/W2625454625","https://openalex.org/W2738463834","https://openalex.org/W2739883972","https://openalex.org/W2799800213","https://openalex.org/W2889163603","https://openalex.org/W2892124901","https://openalex.org/W2899771611","https://openalex.org/W2913041008","https://openalex.org/W2927078315","https://openalex.org/W2932074147","https://openalex.org/W2962784628","https://openalex.org/W2963211739","https://openalex.org/W2963212250","https://openalex.org/W2963747784","https://openalex.org/W2963970535","https://openalex.org/W3001763377","https://openalex.org/W3017692244","https://openalex.org/W6621543089","https://openalex.org/W6623517193","https://openalex.org/W6636774829","https://openalex.org/W6686002079","https://openalex.org/W6741321433","https://openalex.org/W6756040250"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W4386269615","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4389471172","https://openalex.org/W4307932641","https://openalex.org/W2903036216","https://openalex.org/W2088056149"],"abstract_inverted_index":{"In":[0,34],"attention":[1],"based":[2],"end-to-end":[3],"(A-E2E)":[4],"speech":[5],"recognition":[6],"systems,":[7],"the":[8,79,87,93],"dependency":[9],"between":[10],"output":[11,32],"tokens":[12],"is":[13,50],"typically":[14],"formulated":[15],"as":[16],"an":[17],"input-output":[18],"mapping":[19],"in":[20,72],"decoder.":[21],"Due":[22],"to":[23,64],"such":[24],"dependency,":[25],"decoding":[26],"errors":[27],"can":[28,53],"easily":[29],"propagate":[30],"along":[31],"sequence.":[33],"this":[35],"paper,":[36],"we":[37,67],"propose":[38,68],"a":[39,57,69],"token-wise":[40],"training":[41,75,90],"(TWT)":[42],"method":[43,49],"for":[44],"A-E2E":[45],"models.":[46],"The":[47],"new":[48],"flexible":[51],"and":[52],"be":[54],"combined":[55],"with":[56],"variety":[58],"of":[59],"loss":[60],"functions.":[61],"Applying":[62],"TWT":[63,71],"multiple":[65],"hypotheses,":[66],"novel":[70],"beam":[73],"(TWTiB)":[74],"scheme.":[76],"Trained":[77],"on":[78,92],"benchmark":[80],"Switchboard":[81],"(SWBD)":[82],"300h":[83],"corpus,":[84],"TWTiB":[85],"outperforms":[86],"previous":[88],"best":[89],"scheme":[91],"SWBD":[94],"evaluation":[95],"subset.":[96]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}