{"id":"https://openalex.org/W2294692935","doi":"https://doi.org/10.21437/interspeech.2014-431","title":"Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models","display_name":"Autoregressive product of multi-frame predictions can improve the accuracy of hybrid models","publication_year":2014,"publication_date":"2014-09-14","ids":{"openalex":"https://openalex.org/W2294692935","doi":"https://doi.org/10.21437/interspeech.2014-431","mag":"2294692935"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2014-431","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-431","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/A5112445699","display_name":"Navdeep Jaitly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Navdeep Jaitly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5108093963","display_name":"Geoffrey E. Hinton","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geoffrey Hinton","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1905","last_page":"1909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.996399998664856,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.996399998664856,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9807999730110168,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9797999858856201,"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/softmax-function","display_name":"Softmax function","score":0.8602849245071411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8025993704795837},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7719002962112427},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7395637035369873},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.6370124816894531},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6210474967956543},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.6029977798461914},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.565211296081543},{"id":"https://openalex.org/keywords/autoregressive-model","display_name":"Autoregressive model","score":0.5536834597587585},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5285607576370239},{"id":"https://openalex.org/keywords/dropout","display_name":"Dropout (neural networks)","score":0.5229873657226562},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4942207634449005},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4712161123752594},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.46219876408576965},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44505488872528076},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2897002696990967},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11037492752075195}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8602849245071411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8025993704795837},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7719002962112427},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7395637035369873},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.6370124816894531},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6210474967956543},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.6029977798461914},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.565211296081543},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.5536834597587585},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5285607576370239},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.5229873657226562},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4942207634449005},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4712161123752594},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.46219876408576965},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44505488872528076},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2897002696990967},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11037492752075195},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2014-431","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2014-431","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1524333225","https://openalex.org/W1904365287","https://openalex.org/W1978741356","https://openalex.org/W2005708641","https://openalex.org/W2010291496","https://openalex.org/W2024490156","https://openalex.org/W2036242736","https://openalex.org/W2100495367","https://openalex.org/W2110871230","https://openalex.org/W2111306781","https://openalex.org/W2114016253","https://openalex.org/W2136922672","https://openalex.org/W2155273149","https://openalex.org/W2161329381","https://openalex.org/W2188183693","https://openalex.org/W2396030159","https://openalex.org/W2619993508"],"related_works":["https://openalex.org/W3134920593","https://openalex.org/W2143247386","https://openalex.org/W1990589093","https://openalex.org/W2092523626","https://openalex.org/W2501000458","https://openalex.org/W1578749070","https://openalex.org/W2146842779","https://openalex.org/W2915887922","https://openalex.org/W2903939003","https://openalex.org/W2340308015"],"abstract_inverted_index":{"We":[0],"describe":[1],"a":[2,27,43,62,113,126,136,144],"simple":[3],"but":[4],"effective":[5],"way":[6],"of":[7,15,39,49,60,69,82,106,130,147],"using":[8,42,112,135],"multi-frame":[9],"targets":[10],"to":[11,34,56,64,79,143],"improve":[12,80],"the":[13,36,50,57,67,70,83,90,96,107,150],"accuracy":[14,81],"Artificial":[16],"Neural":[17,29,117],"NetworkHidden":[18],"Markov":[19],"Model":[20],"(ANN-HMM)":[21],"hybrid":[22],"systems.":[23],"In":[24],"this":[25,75],"approach":[26],"Deep":[28,116],"Network":[30,118],"(DNN)":[31],"is":[32,53,76,100],"trained":[33],"predict":[35,65],"forced-alignment":[37],"state":[38,68,105],"multiple":[40],"frames":[41],"separate":[44],"softmax":[45],"unit":[46],"for":[47,92],"each":[48,93],"frames.":[51],"This":[52],"in":[54],"contrast":[55],"usual":[58],"method":[59],"training":[61],"DNN":[63],"only":[66],"central":[71],"frame.":[72],"By":[73],"itself":[74],"not":[77],"sufficient":[78],"system":[84,140],"significantly.":[85],"However,":[86],"if":[87],"we":[88,103],"average":[89],"predictions":[91],"frame":[94],"from":[95],"different":[97],"contexts":[98],"it":[99,141],"associated":[101],"with":[102],"achieve":[104],"art":[108],"results":[109],"on":[110,149,156],"TIMIT":[111],"fully":[114],"connected":[115],"without":[119],"convolutional":[120],"architectures":[121],"or":[122],"dropout":[123],"training.":[124],"On":[125],"14":[127],"hour":[128],"subset":[129],"Wall":[131],"Street":[132],"Journal":[133],"(WSJ)":[134],"context":[137],"dependent":[138],"DNN-HMM":[139],"leads":[142],"relative":[145],"improvement":[146],"6.4%":[148],"dev":[151],"set":[152,158],"(testdev93)":[153],"and":[154],"9.3%":[155],"test":[157],"(test-eval92).":[159]},"counts_by_year":[{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":8},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}