{"id":"https://openalex.org/W2296748324","doi":"https://doi.org/10.21437/interspeech.2012-10","title":"Application of pretrained deep neural networks to large vocabulary speech recognition","display_name":"Application of pretrained deep neural networks to large vocabulary speech recognition","publication_year":2012,"publication_date":"2012-09-09","ids":{"openalex":"https://openalex.org/W2296748324","doi":"https://doi.org/10.21437/interspeech.2012-10","mag":"2296748324"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2012-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","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/A5112445699","display_name":"Navdeep Jaitly","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Navdeep Jaitly","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111455517","display_name":"Patrick Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patrick Nguyen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079708487","display_name":"Andrew Senior","orcid":"https://orcid.org/0000-0002-2401-5691"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew Senior","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5013813527","display_name":"Vincent Vanhoucke","orcid":"https://orcid.org/0000-0003-0544-2791"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vincent Vanhoucke","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5112445699"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":54.3651,"has_fulltext":false,"cited_by_count":249,"citation_normalized_percentile":{"value":0.99911855,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"2578","last_page":"2581"},"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/T11309","display_name":"Music and Audio Processing","score":0.998199999332428,"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/T10860","display_name":"Speech and Audio Processing","score":0.9980000257492065,"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":0.7657384276390076},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.6981536149978638},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6756604909896851},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5379000902175903},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5211513042449951},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4792325794696808},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.22654125094413757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7657384276390076},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.6981536149978638},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6756604909896851},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5379000902175903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5211513042449951},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4792325794696808},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.22654125094413757},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.21437/interspeech.2012-10","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2012-10","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2012","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.258.8500","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.258.8500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://research.google.com/pubs/archive/38130.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W137106866","https://openalex.org/W587794757","https://openalex.org/W1993882792","https://openalex.org/W2025768430","https://openalex.org/W2100495367","https://openalex.org/W2103359087","https://openalex.org/W2106051978","https://openalex.org/W2106554350","https://openalex.org/W2114016253","https://openalex.org/W2125234026","https://openalex.org/W2136922672","https://openalex.org/W2147768505","https://openalex.org/W2151660570","https://openalex.org/W2156373089","https://openalex.org/W2173213060","https://openalex.org/W2394932179","https://openalex.org/W2569190383"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W1979153711","https://openalex.org/W4292238148","https://openalex.org/W2137671468","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W766546768","https://openalex.org/W3192589309"],"abstract_inverted_index":{"The":[0],"use":[1,19],"of":[2,20,41],"Deep":[3],"Belief":[4],"Networks":[5,10],"(DBN)":[6],"to":[7,14],"pretrain":[8],"Neural":[9,22],"has":[11],"recently":[12],"led":[13],"a":[15,42],"resurgence":[16],"in":[17],"the":[18],"Artificial":[21],"Network-":[23],"Hidden":[24],"Markov":[25],"Model":[26],"(ANN/HMM)":[27],"hybrid":[28],"systems":[29],"for":[30],"Automatic":[31],"Speech":[32],"Recognition":[33],"(ASR).":[34],"In":[35],"this":[36],"paper":[37],"we":[38],"report":[39],"results":[40],"DBN-pretrained":[43,60],"context-dependent":[44],"ANN/HMM":[45,61],"system":[46],"trained":[47],"on":[48],"two":[49],"datasets":[50],"that":[51],"are":[52],"much":[53],"larger":[54],"than":[55],"any":[56],"reported":[57],"previously":[58],"with":[59]},"counts_by_year":[{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":20},{"year":2019,"cited_by_count":15},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":17},{"year":2015,"cited_by_count":32},{"year":2014,"cited_by_count":53},{"year":2013,"cited_by_count":33},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
