{"id":"https://openalex.org/W2400718301","doi":"https://doi.org/10.21437/interspeech.2013-47","title":"A scalable approach to using DNN-derived features in GMM-HMM based acoustic modeling for LVCSR","display_name":"A scalable approach to using DNN-derived features in GMM-HMM based acoustic modeling for LVCSR","publication_year":2013,"publication_date":"2013-08-25","ids":{"openalex":"https://openalex.org/W2400718301","doi":"https://doi.org/10.21437/interspeech.2013-47","mag":"2400718301"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2013-47","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-47","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/A5061850214","display_name":"Zhijie Yan","orcid":"https://orcid.org/0000-0001-8065-0748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhi-Jie Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039662070","display_name":"Qiang Huo","orcid":"https://orcid.org/0000-0003-2464-6482"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiang Huo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5085728168","display_name":"Jian Xu","orcid":"https://orcid.org/0000-0001-5590-8540"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jian Xu","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":6.4066,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97649806,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"104","last_page":"108"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9973000288009644,"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/T11309","display_name":"Music and Audio Processing","score":0.9952999949455261,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.8986406326293945},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7843877673149109},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7379204034805298},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.653627336025238},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5675771236419678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5432509183883667},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.524550199508667},{"id":"https://openalex.org/keywords/nist","display_name":"NIST","score":0.4984776973724365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48012614250183105},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4695259630680084},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4342077672481537},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.42066651582717896},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.41256043314933777}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8986406326293945},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7843877673149109},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7379204034805298},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.653627336025238},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5675771236419678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5432509183883667},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.524550199508667},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.4984776973724365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48012614250183105},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4695259630680084},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4342077672481537},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.42066651582717896},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.41256043314933777},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2013-47","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2013-47","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","score":0.800000011920929,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W345765952","https://openalex.org/W1218987319","https://openalex.org/W1599512239","https://openalex.org/W1987238397","https://openalex.org/W2002342963","https://openalex.org/W2003123121","https://openalex.org/W2025198378","https://openalex.org/W2046588080","https://openalex.org/W2047832382","https://openalex.org/W2062164080","https://openalex.org/W2080400971","https://openalex.org/W2114529642","https://openalex.org/W2123237149","https://openalex.org/W2125610823","https://openalex.org/W2126160986","https://openalex.org/W2147768505","https://openalex.org/W2160373860","https://openalex.org/W2160815625","https://openalex.org/W2164115090","https://openalex.org/W2165712214","https://openalex.org/W2166637769","https://openalex.org/W2168231600","https://openalex.org/W2394932179","https://openalex.org/W2400691855","https://openalex.org/W2403195671"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738","https://openalex.org/W2098529290","https://openalex.org/W2026402306","https://openalex.org/W2032826752"],"abstract_inverted_index":{"We":[0],"present":[1],"a":[2,39,71,83,88,101,113,131,142],"new":[3],"scalable":[4,59],"approach":[5,129],"to":[6,44,64,81,123],"using":[7,57],"deep":[8],"neural":[9],"network":[10],"(DNN)":[11],"derived":[12],"features":[13],"in":[14],"Gaussian":[15],"mixture":[16],"density":[17],"hidden":[18],"Markov":[19],"model":[20],"(GMM-HMM)":[21],"based":[22,104,137],"acoustic":[23],"modeling":[24],"for":[25],"large":[26],"vocabulary":[27],"continuous":[28],"speech":[29],"recognition":[30],"(LVCSR).":[31],"The":[32],"DNN-based":[33],"feature":[34,114],"extractor":[35,115],"is":[36,110,121,140],"trained":[37,55],"from":[38],"subset":[40],"of":[41,49,93,133,144],"training":[42,60,68,79,119],"data":[43,80,120],"mitigate":[45],"the":[46,66,107,125],"scalability":[47],"issue":[48],"DNN":[50,84,109],"training,":[51],"while":[52],"GMM-HMMs":[53],"are":[54],"by":[56,100],"state-of-the-art":[58],"methods":[61],"and":[62,116],"tools":[63],"leverage":[65],"whole":[67],"set.":[69],"In":[70],"benchmark":[72],"evaluation,":[73],"we":[74],"used":[75,111,122],"309-hour":[76],"Switchboard-I":[77],"(SWB)":[78],"train":[82,124],"first,":[85],"which":[86],"achieves":[87,130],"word":[89],"error":[90],"rate":[91],"(WER)":[92],"15.4%":[94],"on":[95],"NIST-2000":[96],"Hub5":[97],"evaluation":[98],"set":[99],"traditional":[102],"DNN-HMM":[103],"approach.":[105],"When":[106],"same":[108],"as":[112],"2,000-hour":[117],"\u201cSWB+Fisher\u201d":[118],"GMM-HMMs,":[126],"our":[127],"DNN-GMM-HMM":[128],"WER":[132,143],"13.8%.":[134],"If":[135],"per-conversation-side":[136],"unsupervised":[138],"adaptation":[139],"performed,":[141],"13.1%":[145],"can":[146],"be":[147],"achieved.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":16}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}