{"id":"https://openalex.org/W3134568462","doi":"https://doi.org/10.1109/slt48900.2021.9383536","title":"Efficient Large Scale Semi-Supervised Learning for CTC Based Acoustic Models","display_name":"Efficient Large Scale Semi-Supervised Learning for CTC Based Acoustic Models","publication_year":2021,"publication_date":"2021-01-19","ids":{"openalex":"https://openalex.org/W3134568462","doi":"https://doi.org/10.1109/slt48900.2021.9383536","mag":"3134568462"},"language":"en","primary_location":{"id":"doi:10.1109/slt48900.2021.9383536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 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/A5061375051","display_name":"Prakhar Swarup","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Prakhar Swarup","raw_affiliation_strings":["Amazon Alexa, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001163027","display_name":"Debmalya Chakrabarty","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Debmalya Chakrabarty","raw_affiliation_strings":["Amazon Alexa, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087537788","display_name":"Ashtosh Sapru","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ashtosh Sapru","raw_affiliation_strings":["Amazon Alexa, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065684433","display_name":"Hitesh Tulsiani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hitesh Tulsiani","raw_affiliation_strings":["Amazon Alexa, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa, Bangalore, India","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080360704","display_name":"Harish Arsikere","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Harish Arsikere","raw_affiliation_strings":["Amazon Alexa, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa, Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110389578","display_name":"Sri Garimella","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sri Garimella","raw_affiliation_strings":["Amazon Alexa, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Amazon Alexa, Bangalore, India","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5061375051"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03095269,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"148","last_page":"155"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"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":0.7741433382034302},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7304615378379822},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.683263897895813},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.593345582485199},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.5418052077293396},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5416863560676575},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5098547339439392},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4969969093799591},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4675038754940033},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4604637324810028},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.44248121976852417},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4417797923088074},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.4412662088871002},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4370800256729126},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42938125133514404},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32643184065818787},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31738579273223877},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08263269066810608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7741433382034302},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7304615378379822},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.683263897895813},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.593345582485199},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.5418052077293396},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5416863560676575},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5098547339439392},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4969969093799591},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4675038754940033},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4604637324810028},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.44248121976852417},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4417797923088074},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.4412662088871002},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4370800256729126},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42938125133514404},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32643184065818787},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31738579273223877},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08263269066810608},{"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/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/slt48900.2021.9383536","is_oa":false,"landing_page_url":"https://doi.org/10.1109/slt48900.2021.9383536","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Spoken Language Technology Workshop (SLT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W1489125746","https://openalex.org/W1495749136","https://openalex.org/W1533416326","https://openalex.org/W1821462560","https://openalex.org/W1993660824","https://openalex.org/W2079735306","https://openalex.org/W2114016253","https://openalex.org/W2124558353","https://openalex.org/W2127141656","https://openalex.org/W2127499922","https://openalex.org/W2291513470","https://openalex.org/W2475988411","https://openalex.org/W2508418541","https://openalex.org/W2512655038","https://openalex.org/W2587275078","https://openalex.org/W2711861986","https://openalex.org/W2747909401","https://openalex.org/W2802248956","https://openalex.org/W2888930363","https://openalex.org/W2892008152","https://openalex.org/W2913178639","https://openalex.org/W2962907457","https://openalex.org/W2963920996","https://openalex.org/W2964038834","https://openalex.org/W2972611633","https://openalex.org/W2972619908","https://openalex.org/W2972981900","https://openalex.org/W2973040747","https://openalex.org/W3097484451","https://openalex.org/W6629052376","https://openalex.org/W6629638798","https://openalex.org/W6638523607","https://openalex.org/W6725680917"],"related_works":["https://openalex.org/W2365028544","https://openalex.org/W4309984931","https://openalex.org/W4282977123","https://openalex.org/W2949671220","https://openalex.org/W2013810580","https://openalex.org/W2186210338","https://openalex.org/W4206276646","https://openalex.org/W2168489430","https://openalex.org/W121244246","https://openalex.org/W4312390859"],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1],"(SSL)":[2],"is":[3,63],"an":[4],"active":[5],"area":[6],"of":[7,19,31,38,54,60,74,108,115,125],"research":[8],"which":[9],"aims":[10],"to":[11,15,77,111,146,156],"utilize":[12],"unlabeled":[13,61,109],"data":[14,62,101,110,153],"improve":[16],"the":[17,24,29,70,113,126,157],"accuracy":[18],"speech":[20],"recognition":[21],"systems.":[22],"While":[23],"previous":[25],"studies":[26],"have":[27],"established":[28],"efficacy":[30],"various":[32],"SSL":[33,45,90,121,158],"methods":[34],"on":[35],"varying":[36],"amounts":[37,107],"data,":[39],"this":[40],"paper":[41,71],"presents":[42],"largest":[43],"ASR":[44],"experiment":[46],"ever":[47],"conducted":[48],"till":[49],"date":[50],"where":[51],"75K":[52],"hours":[53,59],"labeled":[55],"and":[56,98],"1.2":[57],"million":[58],"used":[64],"for":[65,92,104],"model":[66,128],"training.":[67,135,159],"In":[68],"addition,":[69],"introduces":[72],"couple":[73],"novel":[75],"techniques":[76],"facilitate":[78],"such":[79,149],"a":[80,85,150],"large":[81,151],"scale":[82],"experiment:":[83],"1)":[84],"simple":[86],"scalable":[87],"Teacher-Student":[88],"based":[89],"method":[91],"connectionist":[93],"temporal":[94],"classification":[95],"(CTC)":[96],"objective":[97],"2)":[99],"effective":[100],"selection":[102],"mechanisms":[103],"leveraging":[105],"massive":[106],"boost":[112],"performance":[114],"student":[116],"models.":[117],"Further,":[118],"we":[119],"apply":[120],"in":[122,148],"all":[123],"stages":[124],"acoustic":[127],"training,":[129],"including":[130],"final":[131],"stage":[132],"sequence":[133],"discriminative":[134],"Our":[136],"experiments":[137],"indicate":[138],"encouraging":[139],"word":[140],"error":[141],"rate":[142],"(WER)":[143],"gains":[144],"up":[145],"14%":[147],"transcribed":[152],"regime":[154],"due":[155]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}