{"id":"https://openalex.org/W2169840288","doi":"https://doi.org/10.1109/icassp.2015.7178836","title":"Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying","display_name":"Building context-dependent DNN acoustic models using Kullback-Leibler divergence-based state tying","publication_year":2015,"publication_date":"2015-04-01","ids":{"openalex":"https://openalex.org/W2169840288","doi":"https://doi.org/10.1109/icassp.2015.7178836","mag":"2169840288"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2015.7178836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088559776","display_name":"G\u00e1bor Gosztolya","orcid":"https://orcid.org/0000-0002-2864-6466"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":true,"raw_author_name":"Gabor Gosztolya","raw_affiliation_strings":["MTA-SZTE Research Group on Artificial Intelligence, Szezed, Hungry"],"affiliations":[{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence, Szezed, Hungry","institution_ids":["https://openalex.org/I4210152167"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058277119","display_name":"Tam\u00e1s Gr\u00f3sz","orcid":"https://orcid.org/0000-0001-7918-9579"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Tamas Grosz","raw_affiliation_strings":["MTA-SZTE Research Group on Artificial Intelligence, Szezed, Hungry"],"affiliations":[{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence, Szezed, Hungry","institution_ids":["https://openalex.org/I4210152167"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020608163","display_name":"L\u00e1szl\u00f3 T\u00f3th","orcid":"https://orcid.org/0000-0003-0161-1375"},"institutions":[{"id":"https://openalex.org/I4210152167","display_name":"MTA-SZTE Research Group on Artificial Intelligence","ror":"https://ror.org/0507fk326","country_code":"HU","type":"facility","lineage":["https://openalex.org/I227486990","https://openalex.org/I4210152167","https://openalex.org/I7597260"]}],"countries":["HU"],"is_corresponding":false,"raw_author_name":"Laszlo Toth","raw_affiliation_strings":["MTA-SZTE Research Group on Artificial Intelligence, Szezed, Hungry"],"affiliations":[{"raw_affiliation_string":"MTA-SZTE Research Group on Artificial Intelligence, Szezed, Hungry","institution_ids":["https://openalex.org/I4210152167"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037750159","display_name":"David Imseng","orcid":null},"institutions":[{"id":"https://openalex.org/I7495430","display_name":"Idiap Research Institute","ror":"https://ror.org/05932h694","country_code":"CH","type":"facility","lineage":["https://openalex.org/I7495430"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"David Imseng","raw_affiliation_strings":["Idiap Research Institute, Martigny, Switzerland"],"affiliations":[{"raw_affiliation_string":"Idiap Research Institute, Martigny, Switzerland","institution_ids":["https://openalex.org/I7495430"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5088559776"],"corresponding_institution_ids":["https://openalex.org/I4210152167"],"apc_list":null,"apc_paid":null,"fwci":1.2943,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.85971975,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4570","last_page":"4574"},"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":0.996999979019165,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9969000220298767,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.8645427823066711},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7348554134368896},{"id":"https://openalex.org/keywords/kullback\u2013leibler-divergence","display_name":"Kullback\u2013Leibler divergence","score":0.6962504386901855},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.6594096422195435},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.6168416142463684},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5969190001487732},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5629817247390747},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5482892394065857},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5317617058753967},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49674922227859497},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4927048981189728},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4894787073135376},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4325176775455475},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4235060214996338},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1524597406387329}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8645427823066711},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7348554134368896},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.6962504386901855},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.6594096422195435},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.6168416142463684},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5969190001487732},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5629817247390747},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5482892394065857},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5317617058753967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49674922227859497},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4927048981189728},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4894787073135376},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4325176775455475},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4235060214996338},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1524597406387329},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icassp.2015.7178836","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2015.7178836","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:5980","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400436","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"K\u00f6nyv r\u00e9sze"},{"id":"pmh:oai:infoscience.tind.io:205159","is_oa":true,"landing_page_url":"http://infoscience.epfl.ch/record/205159","pdf_url":"http://infoscience.epfl.ch/record/205159","source":{"id":"https://openalex.org/S4306400487","display_name":"Infoscience (Ecole Polytechnique F\u00e9d\u00e9rale de Lausanne)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://infoscience.epfl.ch/record/205159","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:publicatio.bibl.u-szeged.hu:5980","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400436","display_name":"SZTE Publicatio Repozit\u00f3rium (University of Szeged)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I227486990","host_organization_name":"University of Szeged","host_organization_lineage":["https://openalex.org/I227486990"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"K\u00f6nyv r\u00e9sze"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8100000023841858}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W88081813","https://openalex.org/W217970951","https://openalex.org/W811578723","https://openalex.org/W840896464","https://openalex.org/W1534441687","https://openalex.org/W1553004968","https://openalex.org/W1965555277","https://openalex.org/W1987841215","https://openalex.org/W1993882792","https://openalex.org/W2004227461","https://openalex.org/W2019973879","https://openalex.org/W2097963413","https://openalex.org/W2108341231","https://openalex.org/W2126002878","https://openalex.org/W2131342762","https://openalex.org/W2147768505","https://openalex.org/W2158069733","https://openalex.org/W2898360541","https://openalex.org/W6623429063","https://openalex.org/W6679429981","https://openalex.org/W6755964870"],"related_works":["https://openalex.org/W2115685217","https://openalex.org/W2101275224","https://openalex.org/W182076448","https://openalex.org/W2584084702","https://openalex.org/W2545766074","https://openalex.org/W2982364454","https://openalex.org/W1995002252","https://openalex.org/W2138467869","https://openalex.org/W2405257913","https://openalex.org/W3133710586"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"network":[2],"(DNN)":[3],"based":[4,13,77],"speech":[5],"recognizers":[6],"have":[7,20],"recently":[8],"replaced":[9],"Gaussian":[10],"mixture":[11],"(GMM)":[12],"systems":[14,19],"as":[15],"the":[16,25,42,69,94,104,114],"state-of-the-art.":[17],"HMM/DNN":[18,129],"kept":[21],"many":[22],"refinements":[23],"of":[24,31,44,80,98,116],"HMM/GMM":[26],"framework,":[27],"even":[28,73],"though":[29,74],"some":[30],"these":[32],"may":[33],"be":[34],"suboptimal":[35],"for":[36,48,128],"them.":[37],"One":[38],"such":[39],"example":[40],"is":[41,76,125],"creation":[43],"context-dependent":[45],"tied":[46,59],"states,":[47],"which":[49],"an":[50,87],"efficient":[51],"decision":[52,105],"tree":[53],"state":[54,89,148],"tying":[55,71],"method":[56,91],"exists.":[57],"The":[58],"states":[60],"used":[61],"to":[62,102],"train":[63],"DNNs":[64],"are":[65],"usually":[66],"obtained":[67],"using":[68,146],"same":[70],"algorithm,":[72],"it":[75,124],"on":[78],"likelihoods":[79],"Gaussians.":[81],"In":[82,131],"this":[83,147],"paper,":[84],"we":[85,121,137],"investigate":[86],"alternative":[88],"clustering":[90,149],"that":[92,123],"uses":[93],"Kullback-Leibler":[95],"(KL)":[96],"divergence":[97],"DNN":[99],"output":[100],"vectors":[101],"build":[103],"tree.":[106],"It":[107],"has":[108],"already":[109],"been":[110],"successfully":[111],"applied":[112],"within":[113],"framework":[115],"KL-HMM":[117],"systems,":[118],"and":[119],"here":[120],"show":[122],"also":[126],"beneficial":[127],"hybrids.":[130],"a":[132,139],"large":[133],"vocabulary":[134],"recognition":[135],"task":[136],"report":[138],"4%":[140],"relative":[141],"word":[142],"error":[143],"rate":[144],"reduction":[145],"method.":[150]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}