{"id":"https://openalex.org/W2148632119","doi":"https://doi.org/10.21437/interspeech.2010-35","title":"Deep-structured hidden conditional random fields for phonetic recognition","display_name":"Deep-structured hidden conditional random fields for phonetic recognition","publication_year":2010,"publication_date":"2010-09-26","ids":{"openalex":"https://openalex.org/W2148632119","doi":"https://doi.org/10.21437/interspeech.2010-35","mag":"2148632119"},"language":"en","primary_location":{"id":"doi:10.21437/interspeech.2010-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","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/A5034476404","display_name":"Dong Yu","orcid":"https://orcid.org/0000-0003-0520-6844"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Dong Yu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5100671324","display_name":"Li Deng","orcid":"https://orcid.org/0000-0002-1014-0790"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"L. Deng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5034476404"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":8.5699,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.97725407,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2986","last_page":"2989"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9991000294685364,"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":0.9977999925613403,"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/conditional-random-field","display_name":"Conditional random field","score":0.9712153673171997},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.7780337929725647},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7366642951965332},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.7318844795227051},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.7267120480537415},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.684933066368103},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5310314893722534},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.506571888923645},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5059220194816589},{"id":"https://openalex.org/keywords/random-field","display_name":"Random field","score":0.48600658774375916},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42347317934036255},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.4135594964027405},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.41180533170700073},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3840619623661041},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1581968069076538},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08261996507644653}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.9712153673171997},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.7780337929725647},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7366642951965332},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7318844795227051},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.7267120480537415},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.684933066368103},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5310314893722534},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.506571888923645},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5059220194816589},{"id":"https://openalex.org/C130402806","wikidata":"https://www.wikidata.org/wiki/Q5361768","display_name":"Random field","level":2,"score":0.48600658774375916},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42347317934036255},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.4135594964027405},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.41180533170700073},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3840619623661041},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1581968069076538},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08261996507644653}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21437/interspeech.2010-35","is_oa":false,"landing_page_url":"https://doi.org/10.21437/interspeech.2010-35","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Interspeech 2010","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.699999988079071}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W197206975","https://openalex.org/W1802969839","https://openalex.org/W1981678206","https://openalex.org/W2077804127","https://openalex.org/W2096199223","https://openalex.org/W2100474170","https://openalex.org/W2110017413","https://openalex.org/W2115439799","https://openalex.org/W2116284136","https://openalex.org/W2123131857","https://openalex.org/W2130179707","https://openalex.org/W2131646590","https://openalex.org/W2135013272","https://openalex.org/W2141778357","https://openalex.org/W2143908786","https://openalex.org/W2145823193","https://openalex.org/W2156615793","https://openalex.org/W2165119652","https://openalex.org/W2168013545","https://openalex.org/W2184887056"],"related_works":["https://openalex.org/W2341138520","https://openalex.org/W2963644502","https://openalex.org/W2137657024","https://openalex.org/W2208878950","https://openalex.org/W2369173857","https://openalex.org/W4295602020","https://openalex.org/W3084940491","https://openalex.org/W197206975","https://openalex.org/W2165500456","https://openalex.org/W2162267467"],"abstract_inverted_index":{"We":[0,19],"extend":[1],"our":[2],"earlier":[3],"work":[4],"on":[5,131],"deep-structured":[6,13],"conditional":[7,15,45,55],"random":[8,16,46,56],"field":[9,17,47],"(DCRF)":[10],"and":[11,49,61,104,122,158],"develop":[12],"hidden":[14,44,166],"(DHCRF).":[18],"investigate":[20],"the":[21,39,50,65,81,87,92,94,101,105,119,127,132,155,162],"use":[22],"of":[23,89,142],"this":[24,70],"new":[25],"sequential":[26],"deep-learning":[27],"model":[28,36,168],"for":[29,118,126],"phonetic":[30],"recognition.":[31],"DHCRF":[32,66,145,157],"is":[33,42,84,97,108,112],"a":[34,43,143,147],"hierarchical":[35],"in":[37,64,69],"which":[38],"final":[40,102,128],"layer":[41,76,78,103],"(HCRF)":[48],"intermediate":[51,120],"layers":[52,121],"are":[53,67,73,151,159],"zero-th-order":[54],"fields":[57],"(CRFs).":[58],"Parameter":[59],"estimation":[60],"sequence":[62],"inference":[63],"developed":[68],"work.":[71],"They":[72],"carried":[74],"out":[75],"by":[77,114],"so":[79],"that":[80],"time":[82],"complexity":[83],"linear":[85],"to":[86,161],"number":[88],"layers.":[90],"In":[91],"DHCRF,":[93],"training":[95],"label":[96],"available":[98],"only":[99],"at":[100],"state":[106],"boundary":[107],"unknown.":[109],"This":[110],"difficulty":[111],"addressed":[113],"using":[115,170],"unsupervised":[116],"learning":[117,125],"lattice-based":[123],"supervised":[124],"layer.":[129],"Experiments":[130],"standard":[133],"TIMIT":[134],"phone":[135],"recognition":[136],"task":[137],"show":[138],"small":[139],"performance":[140],"improvement":[141],"three-layer":[144],"over":[146],"two-layer":[148],"DHCRF;":[149],"both":[150],"significantly":[152],"better":[153],"than":[154],"single-layer":[156],"superior":[160],"discriminatively":[163],"trained":[164],"tri-phone":[165],"Markov":[167],"(HMM)":[169],"identical":[171],"input":[172],"features.":[173]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":6},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}