{"id":"https://openalex.org/W4399800606","doi":"https://doi.org/10.1109/taslp.2024.3416687","title":"TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASR","display_name":"TeLeS: Temporal Lexeme Similarity Score to Estimate Confidence in End-to-End ASR","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4399800606","doi":"https://doi.org/10.1109/taslp.2024.3416687"},"language":"en","primary_location":{"id":"doi:10.1109/taslp.2024.3416687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3416687","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-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/A5086894915","display_name":"Nagarathna Ravi","orcid":"https://orcid.org/0000-0003-0355-6832"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Nagarathna Ravi","raw_affiliation_strings":["IIT Kanpur, Kanpur, India"],"affiliations":[{"raw_affiliation_string":"IIT Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093673328","display_name":"Thishyan Raj T","orcid":null},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Thishyan Raj T","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011121139","display_name":"Vipul Arora","orcid":"https://orcid.org/0000-0002-1207-1258"},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vipul Arora","raw_affiliation_strings":["Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Indian Institute of Technology Kanpur, Kanpur, India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086894915"],"corresponding_institution_ids":["https://openalex.org/I94234084"],"apc_list":null,"apc_paid":null,"fwci":1.4548,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.8414554,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"32","issue":null,"first_page":"4399","last_page":"4408"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9409000277519226,"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/T10028","display_name":"Topic Modeling","score":0.9409000277519226,"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/lexeme","display_name":"Lexeme","score":0.8965363502502441},{"id":"https://openalex.org/keywords/end-to-end-principle","display_name":"End-to-end principle","score":0.6748522520065308},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.644526481628418},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4258425831794739},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36608678102493286},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.32487785816192627},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.26886796951293945},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.18761596083641052},{"id":"https://openalex.org/keywords/philosophy","display_name":"Philosophy","score":0.07246121764183044}],"concepts":[{"id":"https://openalex.org/C2775837122","wikidata":"https://www.wikidata.org/wiki/Q111352","display_name":"Lexeme","level":2,"score":0.8965363502502441},{"id":"https://openalex.org/C74296488","wikidata":"https://www.wikidata.org/wiki/Q2527392","display_name":"End-to-end principle","level":2,"score":0.6748522520065308},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.644526481628418},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4258425831794739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36608678102493286},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32487785816192627},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.26886796951293945},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.18761596083641052},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.07246121764183044},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taslp.2024.3416687","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taslp.2024.3416687","pdf_url":null,"source":{"id":"https://openalex.org/S4210169297","display_name":"IEEE/ACM Transactions on Audio Speech and Language Processing","issn_l":"2329-9290","issn":["2329-9290","2329-9304"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.4000000059604645}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W34303869","https://openalex.org/W1795658042","https://openalex.org/W2028825255","https://openalex.org/W2127141656","https://openalex.org/W2791556425","https://openalex.org/W2937523352","https://openalex.org/W2963505832","https://openalex.org/W2972551158","https://openalex.org/W2972981900","https://openalex.org/W3015634748","https://openalex.org/W3015870704","https://openalex.org/W3026041220","https://openalex.org/W3095350795","https://openalex.org/W3096077898","https://openalex.org/W3097777922","https://openalex.org/W3110501021","https://openalex.org/W3150122400","https://openalex.org/W3160557590","https://openalex.org/W3161324588","https://openalex.org/W3163169798","https://openalex.org/W3191159189","https://openalex.org/W3196548933","https://openalex.org/W3197451691","https://openalex.org/W3198094329","https://openalex.org/W3203388655","https://openalex.org/W4210300569","https://openalex.org/W4210424357","https://openalex.org/W4288724891","https://openalex.org/W4288726319","https://openalex.org/W4319790622","https://openalex.org/W4320802161","https://openalex.org/W4382202628","https://openalex.org/W6679855610","https://openalex.org/W6728622933","https://openalex.org/W6739651123","https://openalex.org/W6739901393","https://openalex.org/W6771467084","https://openalex.org/W6785465039"],"related_works":["https://openalex.org/W2948851395","https://openalex.org/W2803243557","https://openalex.org/W2906140093","https://openalex.org/W2906069764","https://openalex.org/W4388958626","https://openalex.org/W2897126588","https://openalex.org/W2237982552","https://openalex.org/W3167765522","https://openalex.org/W3085329230","https://openalex.org/W4388958663"],"abstract_inverted_index":{"Confidence":[0,42],"estimation":[1],"of":[2,34,75,128,150,191],"predictions":[3],"from":[4],"an":[5],"End-to-End":[6],"(<monospace":[7,13,45,52,113,200,222],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[8,14,19,37,46,53,62,106,108,111,114,121,134,160,181,201,211,223,228],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">E2E</monospace>)":[9],"Automatic":[10],"Speech":[11],"Recognition":[12],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ASR</monospace>)":[15],"model":[16],"benefits":[17],"<monospace":[18,36,61,120,133,159,180,210,227],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ASR</monospace>\u2019s":[20],"downstream":[21],"and":[22,84,86,146,170],"upstream":[23],"tasks.":[24],"Class-probability-based":[25],"confidence":[26,116],"scores":[27,59,130],"do":[28,69],"not":[29,70],"accurately":[30],"represent":[31],"the":[32,49,66,72,88,125,148,189,192,218],"quality":[33],"overconfident":[35],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">ASR</monospace>":[38,161],"predictions.":[39,50],"An":[40],"ancillary":[41],"Estimation":[43],"Model":[44],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CEM</monospace>)":[47],"calibrates":[48],"State-of-the-art":[51],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SOTA</monospace>)":[54],"solutions":[55],"use":[56,137],"binary":[57,67],"target":[58,129],"for":[60,204],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CEM</monospace>":[63],"training.":[64],"However,":[65],"labels":[68],"reveal":[71],"granular":[73],"information":[74],"predicted":[76,89],"words,":[77],"such":[78],"as":[79],"temporal":[80],"alignment":[81],"between":[82],"reference":[83],"hypothesis":[85],"whether":[87],"word":[90],"is":[91],"entirely":[92],"incorrect":[93],"or":[94],"contains":[95],"spelling":[96],"errors.":[97],"Addressing":[98],"this":[99],"issue,":[100],"we":[101,136,195],"propose":[102],"a":[103,197,214],"novel":[104],"<bold":[105,110],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">Te</b>mporal-<bold":[107],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">L</b>exeme":[109],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">S</b>imilarity":[112],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">TeLeS</monospace>)":[115],"score":[117],"to":[118,140,226],"train":[119],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CEM</monospace>.":[122],"To":[123,187],"address":[124],"data":[126,144,153,175],"imbalance":[127],"while":[131],"training":[132,174],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">CEM</monospace>,":[135],"shrinkage":[138],"loss":[139],"focus":[141],"on":[142],"hard-to-learn":[143],"points":[145],"minimise":[147],"impact":[149],"easily":[151],"learned":[152],"points.":[154],"We":[155],"conduct":[156],"experiments":[157],"with":[158,172],"models":[162],"trained":[163],"in":[164,207,217],"three":[165],"languages,":[166],"namely":[167],"Hindi,":[168],"Tamil,":[169],"Kannada,":[171],"varying":[173],"sizes.":[176],"Experiments":[177],"show":[178],"that":[179],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">TeLeS</monospace>":[182],"generalises":[183],"well":[184],"across":[185],"domains.":[186],"demonstrate":[188],"applicability":[190],"proposed":[193],"method,":[194],"formulate":[196],"TeLeS-based":[198],"Acquisition":[199],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">TeLeS-A</monospace>)":[202],"function":[203],"sampling":[205],"uncertainty":[206],"active":[208],"learning.":[209],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">TeLeS-A</monospace>":[212],"achieves":[213],"significant":[215],"reduction":[216],"Word":[219],"Error":[220],"Rate":[221],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">WER</monospace>)":[224],"compared":[225],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">SOTA</monospace>":[229],"methods.":[230]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}