{"id":"https://openalex.org/W4210638180","doi":"https://doi.org/10.1109/asru51503.2021.9687953","title":"Warped Ensembles: A Novel Technique for Improving CTC Based End-to-End Speech Recognition","display_name":"Warped Ensembles: A Novel Technique for Improving CTC Based End-to-End Speech Recognition","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4210638180","doi":"https://doi.org/10.1109/asru51503.2021.9687953"},"language":"en","primary_location":{"id":"doi:10.1109/asru51503.2021.9687953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687953","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","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/A5011249075","display_name":"Kiran Praveen","orcid":"https://orcid.org/0000-0002-7489-417X"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Kiran Praveen","raw_affiliation_strings":["Samsung R&D Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912143","display_name":"Hardik B. Sailor","orcid":"https://orcid.org/0000-0001-6872-5153"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Hardik Sailor","raw_affiliation_strings":["Samsung R&D Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021662681","display_name":"Abhishek Pandey","orcid":"https://orcid.org/0000-0003-0618-2362"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Abhishek Pandey","raw_affiliation_strings":["Samsung R&D Institute,Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R&D Institute,Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5011249075"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.1257,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.41241354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"457","last_page":"464"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9990000128746033,"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":0.9983000159263611,"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":0.7985386848449707},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6328220963478088},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6319261789321899},{"id":"https://openalex.org/keywords/connectionism","display_name":"Connectionism","score":0.6057924032211304},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5275794267654419},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5101714134216309},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5051038861274719},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4888762831687927},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.479801207780838},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.41798287630081177},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2561708986759186},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10189500451087952},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07684817910194397}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7985386848449707},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6328220963478088},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6319261789321899},{"id":"https://openalex.org/C8521452","wikidata":"https://www.wikidata.org/wiki/Q203790","display_name":"Connectionism","level":3,"score":0.6057924032211304},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5275794267654419},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5101714134216309},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5051038861274719},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4888762831687927},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.479801207780838},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.41798287630081177},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2561708986759186},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10189500451087952},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07684817910194397},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru51503.2021.9687953","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru51503.2021.9687953","pdf_url":null,"source":{"id":"https://openalex.org/S4363606113","display_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W143647774","https://openalex.org/W173561343","https://openalex.org/W1494198834","https://openalex.org/W1904457459","https://openalex.org/W1969153299","https://openalex.org/W1993721840","https://openalex.org/W2062164080","https://openalex.org/W2127141656","https://openalex.org/W2128160875","https://openalex.org/W2130942839","https://openalex.org/W2150884987","https://openalex.org/W2158441306","https://openalex.org/W2395106899","https://openalex.org/W2616139854","https://openalex.org/W2799800213","https://openalex.org/W2936774411","https://openalex.org/W2962780374","https://openalex.org/W2962826786","https://openalex.org/W2963250244","https://openalex.org/W2972539100","https://openalex.org/W3015522062","https://openalex.org/W3027839759","https://openalex.org/W3082041631","https://openalex.org/W3094780479","https://openalex.org/W3144486013","https://openalex.org/W3162138321","https://openalex.org/W4212883601","https://openalex.org/W4226302796","https://openalex.org/W4385245566","https://openalex.org/W6607114211","https://openalex.org/W6679436768","https://openalex.org/W6683036876","https://openalex.org/W6711850222"],"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/W2021128377","https://openalex.org/W2604685715","https://openalex.org/W350032239","https://openalex.org/W2412160900","https://openalex.org/W2944691285"],"abstract_inverted_index":{"Combining":[0],"outputs":[1,112],"from":[2,35],"predictive":[3],"models":[4],"trained":[5,18,89],"for":[6,23,85,102],"similar":[7],"tasks":[8],"generally":[9],"perform":[10],"better":[11],"than":[12],"using":[13,90,113,116],"a":[14,65,81,98,117],"single":[15],"model.":[16],"Models":[17],"on":[19,129],"different":[20],"domains":[21],"could":[22,43],"example":[24],"help":[25,32],"in":[26,40,55,75,121,158,176,194],"improving":[27],"the":[28,31,41,50,70,76,111,134,146,155,159,164],"performance":[29,147],"with":[30],"of":[33,72,148,170,190],"information":[34],"complementary":[36],"domains.":[37],"The":[38],"weights":[39,114],"ensemble":[42],"also":[44],"be":[45],"adjusted":[46],"to":[47,69,163,184],"best":[48,156,165],"suit":[49],"desired":[51],"target":[52],"domain.":[53],"However,":[54],"End-to-End":[56],"(E2E)":[57],"based":[58],"speech":[59],"recognition":[60],"solutions,":[61],"this":[62],"is":[63],"not":[64],"simple":[66],"task":[67],"owing":[68],"lack":[71],"time":[73],"alignments":[74],"outputs.":[77],"This":[78],"work":[79],"presents":[80],"novel":[82],"ensembling":[83],"technique":[84,101,119],"E2E":[86],"ASR":[87],"systems":[88],"Connectionist":[91],"Temporal":[92],"Classification":[93],"(CTC)":[94],"loss,":[95],"which":[96],"uses":[97],"multi-sequence":[99],"alignment":[100],"synchronising":[103],"output":[104],"time-frames":[105],"across":[106],"models,":[107],"and":[108,133,143,154,172,179,192,196],"then":[109],"combines":[110],"obtained":[115],"calibration":[118],"introduced":[120],"our":[122],"earlier":[123],"work.":[124],"Several":[125],"experiments":[126,181],"are":[127,141,174],"conducted":[128],"multi-accent":[130],"English":[131],"data":[132],"Librispeech":[135],"corpus.":[136],"Word":[137],"Error":[138],"Rates":[139],"(WER)":[140],"evaluated":[142],"compared":[144,162],"against":[145],"ROVER":[149,185],"(a":[150],"system":[151],"combination":[152],"technique),":[153],"model":[157],"system.":[160],"When":[161],"model,":[166],"average":[167,187],"relative":[168,188],"improvements":[169,189],"6.46%":[171],"8.94%":[173],"observed":[175],"unadapted":[177],"in-domain":[178,195],"out-of-domain":[180,197],"respectively.":[182],"Comparison":[183],"shows":[186],"19.29%":[191],"9.21%":[193],"experiments.":[198]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-02T03:55:41.653505","created_date":"2025-10-10T00:00:00"}