{"id":"https://openalex.org/W3012521265","doi":"https://doi.org/10.1109/iscslp.2016.7918455","title":"Lattice based transcription loss for end-to-end speech recognition","display_name":"Lattice based transcription loss for end-to-end speech recognition","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W3012521265","doi":"https://doi.org/10.1109/iscslp.2016.7918455","mag":"3012521265"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2016.7918455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","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/A5049139590","display_name":"Jian Kang","orcid":"https://orcid.org/0000-0003-3797-256X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jian Kang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100692904","display_name":"Wei-Qiang Zhang","orcid":"https://orcid.org/0000-0003-3841-1959"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei-Qiang Zhang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100409741","display_name":"Jia Liu","orcid":"https://orcid.org/0000-0003-0383-0934"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jia Liu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.1941,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56553794,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"2","issue":null,"first_page":"1","last_page":"5"},"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/T11309","display_name":"Music and Audio Processing","score":0.9975000023841858,"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":0.9965000152587891,"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":0.7404929995536804},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.7119408249855042},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7009933590888977},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6505457162857056},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5453575849533081},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.47082334756851196},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.4676119089126587},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.46406468749046326},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4600747227668762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4423346519470215},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4242277145385742},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3280421793460846}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7404929995536804},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.7119408249855042},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7009933590888977},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6505457162857056},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5453575849533081},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.47082334756851196},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.4676119089126587},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.46406468749046326},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4600747227668762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4423346519470215},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4242277145385742},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3280421793460846},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2016.7918455","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2016.7918455","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 10th International Symposium on Chinese Spoken Language Processing (ISCSLP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.6399999856948853,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W179875071","https://openalex.org/W1525636403","https://openalex.org/W1533416326","https://openalex.org/W1586532344","https://openalex.org/W1600744878","https://openalex.org/W1710082047","https://openalex.org/W1922655562","https://openalex.org/W2005708641","https://openalex.org/W2064675550","https://openalex.org/W2102113734","https://openalex.org/W2114016253","https://openalex.org/W2143612262","https://openalex.org/W2147768505","https://openalex.org/W2150907703","https://openalex.org/W2160306971","https://openalex.org/W2180816288","https://openalex.org/W2193413348","https://openalex.org/W2291513470","https://openalex.org/W2293634267","https://openalex.org/W2394932179","https://openalex.org/W2403524927","https://openalex.org/W2403787182","https://openalex.org/W2407648438","https://openalex.org/W2963211739","https://openalex.org/W2963920996"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W2167155152","https://openalex.org/W2150890698","https://openalex.org/W2162582511","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306"],"abstract_inverted_index":{"End-to-end":[0],"speech":[1,125,138,196],"recognition":[2,126,139],"systems":[3,23],"have":[4,9],"been":[5],"successfully":[6],"implemented":[7],"and":[8,39,134,154,179,191],"become":[10],"competitive":[11],"replacements":[12],"for":[13,195],"hybrid":[14],"systems.":[15],"A":[16],"common":[17],"loss":[18,91],"function":[19,92],"to":[20,93,101,167],"train":[21],"end-to-end":[22],"is":[24,55,60,70,77,188],"connectionist":[25],"temporal":[26],"classification":[27],"(CTC).":[28],"This":[29],"method":[30,107],"maximizes":[31],"the":[32,36,40,57,63,67,74,102,109,113,128,141],"log":[33,71],"likelihood":[34],"between":[35],"feature":[37],"sequence":[38],"associated":[41],"transcription":[42,90,114],"sequence.":[43],"However":[44],"there":[45],"are":[46],"some":[47,168],"weaknesses":[48],"with":[49],"CTC":[50,98,103,152],"training.":[51,99],"The":[52],"main":[53],"weakness":[54],"that":[56,146,185],"training":[58,68,170],"criterion":[59,69,76],"different":[61],"from":[62],"test":[64,75],"criterion,":[65,153],"since":[66],"likelihood,":[72],"while":[73],"word":[78,181],"error":[79,182],"rate.":[80],"In":[81,160],"this":[82,95,118],"work,":[83],"we":[84,162],"introduce":[85],"a":[86,123,135,150],"new":[87,106,119,165],"lattice":[88],"based":[89],"address":[94],"deficiency":[96],"of":[97],"Compared":[100],"function,":[104],"our":[105,147,164,186],"optimizes":[108],"model":[110],"directly":[111],"using":[112],"loss.":[115],"We":[116],"evaluate":[117],"algorithm":[120,148,166,187],"in":[121],"both":[122],"small":[124],"task,":[127,140],"Wall":[129],"Street":[130],"Journal":[131],"(WSJ)":[132],"dataset":[133],"large":[136],"vocabulary":[137],"Switchboard":[142],"dataset.":[143],"Results":[144],"demonstrate":[145],"outperforms":[149],"traditional":[151],"achieving":[155],"7%":[156],"WER":[157],"relative":[158],"reduction.":[159],"addition,":[161],"compare":[163],"discriminative":[169],"algorithms,":[171],"such":[172],"as":[173],"state-level":[174],"minimum":[175,180],"Bayes":[176],"risk":[177],"(SMBR)":[178],"(MWE),":[183],"showing":[184],"more":[189,193],"convenient":[190],"contains":[192],"varieties":[194],"recognition.":[197]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}