{"id":"https://openalex.org/W2294962864","doi":"https://doi.org/10.21437/interspeech.2014-473","title":"A big data approach to acoustic model training corpus selection","display_name":"A big data approach to acoustic model training corpus selection","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2294962864","doi":"https://doi.org/10.21437/interspeech.2014-473","mag":"2294962864"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-473","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},"type":"conference-paper","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/A5003453269","display_name":"Olga Kapralova","orcid":"https://orcid.org/0000-0001-9130-4875"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Olga Kapralova","raw_affiliation_strings":["VIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VIT University","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003872603","display_name":"John Sahaya Rani Alex","orcid":"https://orcid.org/0000-0003-0373-976X"},"institutions":[{"id":"https://openalex.org/I876193797","display_name":"Vellore Institute of Technology University","ror":"https://ror.org/00qzypv28","country_code":"IN","type":"education","lineage":["https://openalex.org/I876193797"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"John Alex","raw_affiliation_strings":["VIT University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VIT University","institution_ids":["https://openalex.org/I876193797"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058585526","display_name":"Eugene Weinstein","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eugene Weinstein","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039108749","display_name":"Pedro J. Garc\u00eda\u2010Moreno","orcid":"https://orcid.org/0000-0002-9793-1826"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pedro J. Moreno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5005881531","display_name":"Olivier Siohan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Siohan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2083","last_page":"2087"},"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":0.9991999864578247,"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":0.9979000091552734,"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":0.8406685590744019},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6647211909294128},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6557830572128296},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6213282346725464},{"id":"https://openalex.org/keywords/dictation","display_name":"Dictation","score":0.5738948583602905},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5282829403877258},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5049853920936584},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.4981808662414551},{"id":"https://openalex.org/keywords/transcription","display_name":"Transcription (linguistics)","score":0.49484485387802124},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.46452295780181885},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.451058954000473},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4474569857120514},{"id":"https://openalex.org/keywords/speech-corpus","display_name":"Speech corpus","score":0.4447915554046631},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.44342225790023804},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43975839018821716},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4285309314727783},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.4273430407047272},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4230459928512573},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.40605926513671875},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.3560831546783447},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.08162304759025574}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8406685590744019},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6647211909294128},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6557830572128296},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6213282346725464},{"id":"https://openalex.org/C2779077324","wikidata":"https://www.wikidata.org/wiki/Q1087138","display_name":"Dictation","level":2,"score":0.5738948583602905},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5282829403877258},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5049853920936584},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.4981808662414551},{"id":"https://openalex.org/C179926584","wikidata":"https://www.wikidata.org/wiki/Q207714","display_name":"Transcription (linguistics)","level":2,"score":0.49484485387802124},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.46452295780181885},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.451058954000473},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4474569857120514},{"id":"https://openalex.org/C91863865","wikidata":"https://www.wikidata.org/wiki/Q4349497","display_name":"Speech corpus","level":3,"score":0.4447915554046631},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.44342225790023804},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43975839018821716},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4285309314727783},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.4273430407047272},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4230459928512573},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.40605926513671875},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.3560831546783447},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.08162304759025574},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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":2,"locations":[{"id":"doi:10.21437/interspeech.2014-473","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-473","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2014","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.674.7716","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.674.7716","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://static.googleusercontent.com/media/research.google.com/en/us/pubs/archive/43230.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W81442308","https://openalex.org/W82886505","https://openalex.org/W217970951","https://openalex.org/W1975113979","https://openalex.org/W2033256038","https://openalex.org/W2034537249","https://openalex.org/W2035424729","https://openalex.org/W2095098834","https://openalex.org/W2109664771","https://openalex.org/W2139453310","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2168231600","https://openalex.org/W2189391786","https://openalex.org/W2296748324","https://openalex.org/W2899506040"],"related_works":["https://openalex.org/W2025104565","https://openalex.org/W4200068392","https://openalex.org/W22934434","https://openalex.org/W2772686614","https://openalex.org/W2036933852","https://openalex.org/W2152945827","https://openalex.org/W2574073913","https://openalex.org/W114226241","https://openalex.org/W2015513221","https://openalex.org/W301864623"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"have":[4],"recently":[5],"become":[6],"the":[7,10,76],"state":[8],"of":[9,43,47,71,78,103,115,120],"art":[11],"technology":[12],"in":[13,154],"speech":[14,39,53,72,104,121],"recognition":[15],"systems.":[16],"In":[17],"this":[18,138],"pa-per":[19],"we":[20,107],"propose":[21],"a":[22,60],"new":[23],"approach":[24,139],"to":[25,32,74,96,117,122,125],"constructing":[26],"large":[27,37,155,171],"high":[28],"qual-ity":[29],"unsupervised":[30,172],"sets":[31,113],"train":[33,126],"DNN":[34],"models":[35,73,128,141],"for":[36,67,83,161],"vocabulary":[38,156],"recognition.":[40],"The":[41],"core":[42],"our":[44,56],"technique":[45],"consists":[46],"two":[48],"steps.":[49],"We":[50,135],"first":[51],"redecode":[52],"logged":[54],"by":[55],"production":[57],"rec-ognizer":[58],"with":[59,142],"very":[61],"accurate":[62],"(and":[63],"hence":[64],"too":[65],"slow":[66],"real-time":[68],"usage)":[69],"set":[70],"improve":[75],"quality":[77],"ground":[79],"truth":[80],"transcripts":[81],"used":[82,124],"training":[84,111,173],"alignments.":[85],"Using":[86],"confidence":[87],"scores,":[88],"transcript":[89,92],"length":[90],"and":[91,158,166],"flattening":[93],"heuristics":[94],"de-signed":[95],"cull":[97],"salient":[98],"utterances":[99],"from":[100],"three":[101],"decades":[102],"per":[105],"language,":[106],"then":[108],"carefully":[109],"select":[110],"data":[112,175],"consist-ing":[114],"up":[116],"15K":[118],"hours":[119],"be":[123],"acoustic":[127],"without":[129],"any":[130],"reliance":[131],"on":[132],"manual":[133],"transcription.":[134],"show":[136],"that":[137,148],"yields":[140],"approximately":[143],"18K":[144],"con-text":[145],"dependent":[146],"states":[147],"achieve":[149],"10":[150],"%":[151],"relative":[152],"improvement":[153],"dictation":[157],"voice-search":[159],"systems":[160],"Brazil-ian":[162],"Portuguese,":[163],"French,":[164],"Italian":[165],"Russian":[167],"languages.":[168],"Index":[169],"Terms:":[170],"sets,":[174],"selection,":[176]},"counts_by_year":[{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}