{"id":"https://openalex.org/W1964863507","doi":"https://doi.org/10.1109/iscslp.2014.6936637","title":"Decision tree based state tying for speech recognition using DNN derived embeddings","display_name":"Decision tree based state tying for speech recognition using DNN derived embeddings","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W1964863507","doi":"https://doi.org/10.1109/iscslp.2014.6936637","mag":"1964863507"},"language":"en","primary_location":{"id":"doi:10.1109/iscslp.2014.6936637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","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/A5081173423","display_name":"Xiangang Li","orcid":"https://orcid.org/0000-0002-7810-1077"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiangang Li","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing","Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Speech and Hearing Research Center, Peking University, Beijing","Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Peking University, Beijing","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception (Ministry of Education), Peking University, Beijing, 100871, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081173423"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":1.227,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.83630902,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"123","last_page":"127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9997000098228455,"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":0.9997000098228455,"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":0.9987000226974487,"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":0.9916999936103821,"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":0.8923782110214233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582008838653564},{"id":"https://openalex.org/keywords/tying","display_name":"Tying","score":0.7447847127914429},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7030575275421143},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6577052474021912},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5954807996749878},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5684017539024353},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.5555155277252197},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5122169852256775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4867963492870331},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4802268147468567},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.4489183723926544},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13191434741020203}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8923782110214233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582008838653564},{"id":"https://openalex.org/C2780938662","wikidata":"https://www.wikidata.org/wiki/Q973710","display_name":"Tying","level":2,"score":0.7447847127914429},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7030575275421143},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6577052474021912},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5954807996749878},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5684017539024353},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.5555155277252197},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5122169852256775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4867963492870331},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4802268147468567},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.4489183723926544},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13191434741020203},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscslp.2014.6936637","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscslp.2014.6936637","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The 9th International Symposium on Chinese Spoken Language Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.8299999833106995}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W83522546","https://openalex.org/W1553004968","https://openalex.org/W1571745681","https://openalex.org/W1631260214","https://openalex.org/W1993882792","https://openalex.org/W2019973879","https://openalex.org/W2035424729","https://openalex.org/W2118716571","https://openalex.org/W2144792281","https://openalex.org/W2147768505","https://openalex.org/W2154423186","https://openalex.org/W2157844668","https://openalex.org/W2158069733","https://openalex.org/W2160815625","https://openalex.org/W2166993553","https://openalex.org/W2180711486","https://openalex.org/W2294543795","https://openalex.org/W2296748324","https://openalex.org/W2394932179","https://openalex.org/W2411442511","https://openalex.org/W2799061466","https://openalex.org/W4302161581","https://openalex.org/W6636811518","https://openalex.org/W6655718583","https://openalex.org/W6696912008"],"related_works":["https://openalex.org/W4324119469","https://openalex.org/W2164868312","https://openalex.org/W2160650576","https://openalex.org/W4285282705","https://openalex.org/W2150890698","https://openalex.org/W2401394187","https://openalex.org/W4245698648","https://openalex.org/W2405257913","https://openalex.org/W3133710586","https://openalex.org/W2125964738"],"abstract_inverted_index":{"Recently,":[0],"context":[1,116],"dependent":[2],"(CD)-deep":[3],"neural":[4],"network":[5],"(DNN)-hidden":[6],"Markov":[7],"model":[8],"(HMM)":[9],"obtains":[10],"significant":[11],"improvements":[12],"in":[13,69],"many":[14],"automatic":[15],"speech":[16,143],"recognition":[17],"(ASR)":[18],"tasks.":[19],"In":[20,56],"the":[21,27,42,48,52,71,83,87,96,109,122,131,146,150,161],"standard":[22],"training":[23,43,104],"procedure":[24,105],"for":[25,54,98,106,115],"CD-DNN-HMM,":[26,107],"Gaussian":[28],"mixture":[29],"models":[30],"(GMM)":[31],"based":[32,65,153,163],"ASR":[33],"system":[34],"has":[35],"to":[36,40,46,81,94,129,160],"be":[37],"firstly":[38],"built":[39],"pre-segment":[41],"data":[44],"and":[45,79,121,145],"define":[47,95,130],"CD":[49],"states":[50],"as":[51],"targets":[53,97],"DNN.":[55],"this":[57],"paper,":[58],"we":[59,101],"propose":[60],"a":[61,91,103,138],"novel":[62],"decision":[63],"tree":[64],"state":[66,72,124,154],"tying":[67,125,155],"procedure,":[68],"which,":[70],"embeddings":[73],"derived":[74],"from":[75],"DNN":[76,152],"are":[77],"used":[78,114],"clustered":[80],"minimize":[82],"sum-of-squared":[84],"error.":[85],"Thus,":[86],"GMM":[88,162],"is":[89,113,127],"not":[90],"necessary":[92],"part":[93],"CD-DNN.":[99],"Besides,":[100],"introduce":[102],"where,":[108],"forward":[110],"backward":[111],"algorithm":[112],"independent":[117],"(CI)":[118],"DNN-HMM":[119],"training,":[120],"proposed":[123,151],"approach":[126,156],"applied":[128],"CD-DNN":[132],"targets.":[133],"Experiments":[134],"were":[135],"conducted":[136],"on":[137],"30-hour":[139],"Chinese":[140],"broadcast":[141],"news":[142],"database":[144],"results":[147],"demonstrate":[148],"that":[149],"yielded":[157],"comparable":[158],"performance":[159],"one.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}