{"id":"https://openalex.org/W2165119652","doi":"https://doi.org/10.1109/asru.2009.5373263","title":"An exploration of large vocabulary tools for small vocabulary phonetic recognition","display_name":"An exploration of large vocabulary tools for small vocabulary phonetic recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2165119652","doi":"https://doi.org/10.1109/asru.2009.5373263","mag":"2165119652"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5070513394","display_name":"Tara N. Sainath","orcid":"https://orcid.org/0000-0002-4126-6556"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tara N. Sainath","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071715737","display_name":"Bhuvana Ramabhadran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bhuvana Ramabhadran","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034529775","display_name":"Michael Picheny","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Picheny","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5070513394"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":8.2873,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.97719207,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"359","last_page":"364"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":1.0,"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":1.0,"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":0.9987999796867371,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9980000257492065,"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":0.8929259777069092},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.8516524434089661},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.8213918209075928},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6983780860900879},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6858841180801392},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6644548177719116},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6370609998703003},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6295346021652222},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.535959780216217},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5226309299468994},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.42726975679397583},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.42437541484832764},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.0806167721748352}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8929259777069092},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.8516524434089661},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.8213918209075928},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6983780860900879},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6858841180801392},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6644548177719116},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6370609998703003},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6295346021652222},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.535959780216217},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5226309299468994},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.42726975679397583},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.42437541484832764},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0806167721748352},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/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/asru.2009.5373263","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373263","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.6600000262260437}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W186915233","https://openalex.org/W1562289873","https://openalex.org/W1647054946","https://openalex.org/W1877154798","https://openalex.org/W2002342963","https://openalex.org/W2007878933","https://openalex.org/W2014641584","https://openalex.org/W2044223162","https://openalex.org/W2077804127","https://openalex.org/W2100474170","https://openalex.org/W2110871230","https://openalex.org/W2114016253","https://openalex.org/W2115439799","https://openalex.org/W2125234026","https://openalex.org/W2127095586","https://openalex.org/W2127375207","https://openalex.org/W2147467930","https://openalex.org/W2167622093","https://openalex.org/W4233347982","https://openalex.org/W4299513203","https://openalex.org/W6639145008","https://openalex.org/W6676981579","https://openalex.org/W6678457041"],"related_works":["https://openalex.org/W2167155152","https://openalex.org/W2155033763","https://openalex.org/W3134920593","https://openalex.org/W1990589093","https://openalex.org/W2994894110","https://openalex.org/W4377862891","https://openalex.org/W2501000458","https://openalex.org/W2150890698","https://openalex.org/W1578749070","https://openalex.org/W2146842779"],"abstract_inverted_index":{"While":[0],"research":[1,19,21,68,100,224],"in":[2,22,128,179],"large":[3,34],"vocabulary":[4,73,77,105],"continuous":[5],"speech":[6],"recognition":[7,139,207],"(LVCSR)":[8],"has":[9],"sparked":[10],"the":[11,17,33,124,136,153,189,194,203,214,220],"development":[12],"of":[13,16,32,36,170,187,210,216],"many":[14],"state":[15],"art":[18],"ideas,":[20],"this":[23,116,217],"domain":[24],"suffers":[25],"from":[26],"two":[27],"main":[28],"drawbacks.":[29],"First,":[30],"because":[31],"number":[35],"parameters":[37],"and":[38,65,85,88,132,173,225],"poorly":[39],"labeled":[40],"transcriptions,":[41],"gaining":[42],"insight":[43],"into":[44],"further":[45],"improvements":[46],"based":[47],"on":[48,112,193],"error":[49,185,208],"analysis":[50],"is":[51],"very":[52],"difficult.":[53],"Second,":[54],"LVCSR":[55,113,130,180,243],"systems":[56,131],"often":[57],"take":[58],"a":[59,82,90,143,232],"significantly":[60],"longer":[61],"time":[62],"to":[63,71,94,135,146,162,197,202,235,242],"train":[64],"test":[66,92],"new":[67],"ideas":[69,101,237],"compared":[70],"small":[72,76,104],"tasks.":[74],"A":[75],"task":[78,196],"like":[79],"TIMIT":[80,137,195],"provides":[81,142],"phonetically":[83],"rich":[84],"hand-labeled":[86],"corpus":[87],"offers":[89],"good":[91,233],"bed":[93],"study":[95],"algorithmic":[96],"improvements.":[97],"However,":[98],"oftentimes":[99],"explored":[102],"for":[103,222],"tasks":[106],"do":[107],"not":[108],"always":[109],"provide":[110],"gains":[111],"systems.":[114,166,244],"In":[115],"paper,":[117],"we":[118,182],"address":[119],"these":[120],"issues":[121],"by":[122],"taking":[123,168],"standard":[125,144],"\"recipe\"":[126],"used":[127,178],"typical":[129],"applying":[133],"it":[134,228],"phonetic":[138,206],"corpus,":[140],"which":[141],"benchmark":[145],"compare":[147],"methods.":[148],"We":[149,212],"find":[150],"that":[151,227,238],"at":[152],"speaker-independent":[154],"(SI)":[155],"level,":[156],"our":[157],"results":[158,191],"offer":[159],"comparable":[160],"performance":[161],"other":[163],"SI":[164],"HMM":[165],"By":[167],"advantage":[169],"speaker":[171],"adaptation":[172],"discriminative":[174],"training":[175],"techniques":[176],"commonly":[177],"systems,":[181],"achieve":[183],"an":[184],"rate":[186,209],"20%,":[188],"best":[190],"reported":[192,205],"date,":[198],"moving":[199],"us":[200],"closer":[201],"human":[204],"15%.":[211],"propose":[213],"use":[215],"system":[218],"as":[219,231],"baseline":[221],"future":[223],"believe":[226],"will":[229,239],"serve":[230],"framework":[234],"explore":[236],"carry":[240],"over":[241]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}