{"id":"https://openalex.org/W2396030159","doi":"https://doi.org/10.21437/interspeech.2013-432","title":"Using an autoencoder with deformable templates to discover features for automated speech recognition","display_name":"Using an autoencoder with deformable templates to discover features for automated speech recognition","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2396030159","doi":"https://doi.org/10.21437/interspeech.2013-432","mag":"2396030159"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","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/A5112445699","display_name":"Navdeep Jaitly","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Navdeep Jaitly","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Geoffrey E. Hinton","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1737","last_page":"1740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9991999864578247,"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":0.7895060777664185},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.761618971824646},{"id":"https://openalex.org/keywords/spectrogram","display_name":"Spectrogram","score":0.7455494403839111},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.7315827012062073},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.6824474334716797},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6665558815002441},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6006631255149841},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5886249542236328},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5702263712882996},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5251533389091492},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.4773300290107727},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.42340517044067383},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.4137507975101471},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.19953685998916626}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895060777664185},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.761618971824646},{"id":"https://openalex.org/C45273575","wikidata":"https://www.wikidata.org/wiki/Q578970","display_name":"Spectrogram","level":2,"score":0.7455494403839111},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.7315827012062073},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.6824474334716797},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6665558815002441},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6006631255149841},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5886249542236328},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5702263712882996},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5251533389091492},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.4773300290107727},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.42340517044067383},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4137507975101471},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.19953685998916626},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-432","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-432","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2013","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5199999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1553004968","https://openalex.org/W1665214252","https://openalex.org/W1904365287","https://openalex.org/W1993882792","https://openalex.org/W2132037657","https://openalex.org/W2136922672","https://openalex.org/W2164931619","https://openalex.org/W2184045248"],"related_works":["https://openalex.org/W80423236","https://openalex.org/W2530685530","https://openalex.org/W4375868962","https://openalex.org/W2011227383","https://openalex.org/W3013693939","https://openalex.org/W2092523626","https://openalex.org/W1980604799","https://openalex.org/W2727244960","https://openalex.org/W2039305110","https://openalex.org/W2588273498"],"abstract_inverted_index":{"In":[0],"this":[1,52,63,157],"paper":[2],"we":[3,6,96,125],"show":[4],"how":[5,28],"can":[7],"discover":[8],"non-linear":[9],"features":[10,72],"of":[11,13,31,54,102,135],"frames":[12],"spectrograms":[14,66],"using":[15,119,159],"a":[16,22,29,44,48,76,130,160],"novel":[17],"autoencoder.":[18],"The":[19,71],"autoencoder":[20],"uses":[21],"neural":[23],"network":[24],"encoder":[25],"that":[26,46,50],"predicts":[27],"set":[30,140],"prototypes":[32,56],"called":[33],"templates":[34],"need":[35],"to":[36,39,99,128,148],"be":[37],"transformed":[38],"reconstruct":[40],"the":[41,59,68,91,111,114,120,138,144,152],"data,":[42],"and":[43,57,141],"decoder":[45],"is":[47,151],"function":[49],"performs":[51],"operation":[53],"transforming":[55],"reconstructing":[58],"input.":[60],"We":[61],"demonstrate":[62],"method":[64],"on":[65,137,143,156],"from":[67],"TIMIT":[69,92],"database.":[70],"are":[73],"used":[74],"in":[75],"Deep":[77],"Neural":[78],"Network":[79],"Hidden":[80],"Markov":[81],"Model":[82],"(DNN-HMM)":[83],"hybrid":[84,161],"system":[85],"for":[86],"automatic":[87],"speech":[88],"recognition.":[89],"On":[90],"monophone":[93],"recognition":[94],"task":[95,158],"were":[97,126],"able":[98,127],"achieve":[100,129],"gains":[101],"0.5%":[103],"over":[104],"Mel":[105],"log":[106],"spectra,":[107],"by":[108],"augmenting":[109],"traditional":[110],"spectra":[112],"with":[113],"predicted":[115],"transformation":[116],"parameters.":[117],"Further,":[118],"recently":[121],"discovered":[122],"\u2018dropout\u2019":[123],"training,":[124],"phone":[131],"error":[132],"rate":[133],"(PER)":[134],"17.9%":[136],"dev":[139],"19.5%":[142],"test":[145],"set,":[146],"which,":[147],"our":[149],"knowledge":[150],"best":[153],"reported":[154],"number":[155],"system.":[162]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}