{"id":"https://openalex.org/W2892209435","doi":"https://doi.org/10.1109/icassp.2018.8461929","title":"Sampled Connectionist Temporal Classification","display_name":"Sampled Connectionist Temporal Classification","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2892209435","doi":"https://doi.org/10.1109/icassp.2018.8461929","mag":"2892209435"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2018.8461929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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/A5040131037","display_name":"Ehsan Variani","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ehsan Variani","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024261917","display_name":"Tom Bagby","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tom Bagby","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039890022","display_name":"Kamel Lahouel","orcid":"https://orcid.org/0000-0002-4339-5749"},"institutions":[{"id":"https://openalex.org/I145311948","display_name":"Johns Hopkins University","ror":"https://ror.org/00za53h95","country_code":"US","type":"education","lineage":["https://openalex.org/I145311948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kamel Lahouel","raw_affiliation_strings":["Johns Hopkins Univ., Baltimore, MD, USA"],"affiliations":[{"raw_affiliation_string":"Johns Hopkins Univ., Baltimore, MD, USA","institution_ids":["https://openalex.org/I145311948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030109648","display_name":"Erik McDermott","orcid":null},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Erik McDermott","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049614700","display_name":"Michiel Bacchiani","orcid":"https://orcid.org/0000-0003-4527-0197"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michiel Bacchiani","raw_affiliation_strings":["Google Inc., USA"],"affiliations":[{"raw_affiliation_string":"Google Inc., USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5040131037"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":null,"apc_paid":null,"fwci":0.8144,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.79823562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4959","last_page":"4963"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994999766349792,"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/T11309","display_name":"Music and Audio Processing","score":0.9987999796867371,"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":0.6540035605430603},{"id":"https://openalex.org/keywords/logarithm","display_name":"Logarithm","score":0.6253652572631836},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.6099898219108582},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.552510678768158},{"id":"https://openalex.org/keywords/minification","display_name":"Minification","score":0.5248130559921265},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4900861978530884},{"id":"https://openalex.org/keywords/upper-and-lower-bounds","display_name":"Upper and lower bounds","score":0.485012024641037},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.4813162088394165},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.46148887276649475},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.43070682883262634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3978952467441559},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3977903723716736},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.3606073260307312},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33264249563217163},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.27176570892333984},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.22678449749946594},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1600182056427002}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6540035605430603},{"id":"https://openalex.org/C39927690","wikidata":"https://www.wikidata.org/wiki/Q11197","display_name":"Logarithm","level":2,"score":0.6253652572631836},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.6099898219108582},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.552510678768158},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5248130559921265},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4900861978530884},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.485012024641037},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4813162088394165},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.46148887276649475},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.43070682883262634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3978952467441559},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3977903723716736},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.3606073260307312},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33264249563217163},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.27176570892333984},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.22678449749946594},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1600182056427002},{"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2018.8461929","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2018.8461929","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 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":22,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1533416326","https://openalex.org/W1924770834","https://openalex.org/W2048305092","https://openalex.org/W2056786202","https://openalex.org/W2064675550","https://openalex.org/W2125838338","https://openalex.org/W2127141656","https://openalex.org/W2193413348","https://openalex.org/W2271840356","https://openalex.org/W2291513470","https://openalex.org/W2404856031","https://openalex.org/W2464072665","https://openalex.org/W2515439472","https://openalex.org/W2746440465","https://openalex.org/W2748584437","https://openalex.org/W2748816379","https://openalex.org/W6629052376","https://openalex.org/W6640212811","https://openalex.org/W6687566353","https://openalex.org/W6694517276","https://openalex.org/W6718912158"],"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":{"This":[0],"article":[1],"introduces":[2],"and":[3,53,131],"evaluates":[4],"Sampled":[5],"Connectionist":[6],"Temporal":[7],"Classification":[8],"(CTC)":[9],"which":[10],"connects":[11],"the":[12,16,26,29,32,40,45,49,60,73,79,85,88,92,98,103,111,144,153,157],"CTC":[13,42,62,74,81,93,100,120,124,137,146,158],"criterion":[14],"to":[15,84,110],"Cross":[17],"Entropy":[18],"(CE)":[19],"objective":[20,63,101],"through":[21],"sampling.":[22],"Instead":[23],"of":[24,28,31,68,78,87,91,97,143,152,156],"computing":[25],"logarithm":[27],"sum":[30],"alignment":[33,51],"path":[34,52],"likelihoods,":[35],"at":[36],"each":[37],"training":[38,154],"step":[39],"sampled":[41,50,61,80,99,119,136],"only":[43],"computes":[44],"CE":[46],"loss":[47],"between":[48],"model":[54],"posteriors.":[55],"It":[56],"is":[57,64,82,107,121,133],"shown":[58,134],"that":[59,105,135],"an":[65,69],"unbiased":[66],"estimator":[67],"upper":[70,89],"bound":[71,90],"for":[72],"loss,":[75],"thus":[76],"minimization":[77,86],"equivalent":[83],"objective.":[94],"The":[95,118],"definition":[96],"has":[102],"advantage":[104],"it":[106,132],"scalable":[108],"computationally":[109],"massive":[112],"datasets":[113],"using":[114],"accelerated":[115],"computation":[116],"machines.":[117],"compared":[122],"with":[123],"in":[125,148],"two":[126],"large-scale":[127],"speech":[128],"recognition":[129],"tasks":[130],"can":[138],"achieve":[139],"similar":[140],"WER":[141],"performance":[142],"best":[145],"baseline":[147],"about":[149],"one":[150],"fourth":[151],"time":[155],"baseline.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}