{"id":"https://openalex.org/W2134950286","doi":"https://doi.org/10.1109/icassp.2005.1415087","title":"Training LVCSR Systems on Thousands of Hours of Data","display_name":"Training LVCSR Systems on Thousands of Hours of Data","publication_year":2006,"publication_date":"2006-10-11","ids":{"openalex":"https://openalex.org/W2134950286","doi":"https://doi.org/10.1109/icassp.2005.1415087","mag":"2134950286"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2005.1415087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","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/A5009755231","display_name":"G. Evermann","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"G. Evermann","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110325576","display_name":"Ho Yin Chan","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"H.Y. Chan","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050766679","display_name":"Mark Gales","orcid":"https://orcid.org/0000-0002-5311-8219"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"M.J.F. Gales","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091325862","display_name":"Bill Jia","orcid":"https://orcid.org/0000-0002-1138-3217"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"B. Jia","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023148684","display_name":"David Mrva","orcid":null},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"D. Mrva","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002191410","display_name":"Philip C. Woodland","orcid":"https://orcid.org/0000-0001-9069-0225"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"P.C. Woodland","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043098653","display_name":"Kai Yu","orcid":"https://orcid.org/0000-0002-7102-9826"},"institutions":[{"id":"https://openalex.org/I241749","display_name":"University of Cambridge","ror":"https://ror.org/013meh722","country_code":"GB","type":"education","lineage":["https://openalex.org/I241749"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"K. Yu","raw_affiliation_strings":["Engineering Department, University of Cambridge, Cambridge, UK","Dept. of Eng., Cambridge Univ., UK#TAB#"],"affiliations":[{"raw_affiliation_string":"Engineering Department, University of Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I241749"]},{"raw_affiliation_string":"Dept. of Eng., Cambridge Univ., UK#TAB#","institution_ids":["https://openalex.org/I241749"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5009755231"],"corresponding_institution_ids":["https://openalex.org/I241749"],"apc_list":null,"apc_paid":null,"fwci":8.5845,"has_fulltext":false,"cited_by_count":59,"citation_normalized_percentile":{"value":0.97588812,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"1","issue":null,"first_page":"209","last_page":"212"},"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":0.9998999834060669,"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":0.9988999962806702,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.8886438608169556},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8578926920890808},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.7594479322433472},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.735774040222168},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6918107271194458},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.6915960311889648},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6403038501739502},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5937882661819458},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5412184596061707},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.47885653376579285},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4630257189273834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4593392610549927},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.449628621339798},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4271283447742462}],"concepts":[{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.8886438608169556},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8578926920890808},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.7594479322433472},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.735774040222168},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6918107271194458},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.6915960311889648},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6403038501739502},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5937882661819458},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5412184596061707},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.47885653376579285},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4630257189273834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4593392610549927},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.449628621339798},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4271283447742462},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","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},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2005.1415087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2005.1415087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8199999928474426,"display_name":"Quality Education"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332178","display_name":"National Institute of Standards and Technology","ror":"https://ror.org/05xpvk416"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W11314411","https://openalex.org/W80013458","https://openalex.org/W1797288984","https://openalex.org/W2094971681","https://openalex.org/W2115407392","https://openalex.org/W2153745209","https://openalex.org/W2163295968","https://openalex.org/W6638218882"],"related_works":["https://openalex.org/W2150907703","https://openalex.org/W2148603752","https://openalex.org/W2094971681","https://openalex.org/W2003123121","https://openalex.org/W2049633694","https://openalex.org/W2076094076","https://openalex.org/W2046932483","https://openalex.org/W1970689298","https://openalex.org/W179875071","https://openalex.org/W1560013842","https://openalex.org/W101286142","https://openalex.org/W2156615793","https://openalex.org/W2146871184","https://openalex.org/W2140409019","https://openalex.org/W2132339004","https://openalex.org/W2125838338","https://openalex.org/W2125529971","https://openalex.org/W1877570817","https://openalex.org/W1498436455","https://openalex.org/W1487784522"],"abstract_inverted_index":{"Typical":[0],"systems":[1],"for":[2,29,44],"large":[3,58],"vocabulary":[4],"conversational":[5,31],"speech":[6,33],"recognition":[7],"(LVCSR)":[8],"have":[9],"been":[10],"trained":[11,36],"on":[12,37,74,105],"a":[13,57],"few":[14],"hundred":[15],"hours":[16,41],"of":[17,42,53],"carefully":[18],"transcribed":[19],"acoustic":[20,76],"training":[21,86,98],"data.":[22],"The":[23,51,72],"paper":[24],"describes":[25],"an":[26],"LVCSR":[27],"system":[28,69],"the":[30,62,66,85,97,101,106],"telephone":[32],"(CTS)":[34],"task":[35],"more":[38],"than":[39],"2000":[40],"data":[43,59,87],"which":[45],"only":[46],"approximate":[47],"transcriptions":[48],"were":[49],"available.":[50],"challenges":[52],"dealing":[54],"with":[55],"such":[56],"set":[60,110],"and":[61,77,95],"accuracy":[63],"improvements":[64],"over":[65],"small":[67],"baseline":[68],"are":[70],"discussed.":[71],"effect":[73],"both":[75],"language":[78],"modelling":[79],"performance":[80],"is":[81],"studied.":[82],"Overall,":[83],"increasing":[84],"size":[88],"from":[89],"360":[90],"h":[91,94],"to":[92],"2200":[93],"optimising":[96],"procedure":[99],"reduced":[100],"word":[102],"error":[103],"rate":[104],"DARPA/NIST":[107],"2003":[108],"evaluation":[109],"by":[111],"about":[112],"20%":[113],"relative.":[114]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
