{"id":"https://openalex.org/W2131646590","doi":"https://doi.org/10.1109/asru.2009.5373329","title":"Hidden Conditional Random Fields for phone recognition","display_name":"Hidden Conditional Random Fields for phone recognition","publication_year":2009,"publication_date":"2009-12-01","ids":{"openalex":"https://openalex.org/W2131646590","doi":"https://doi.org/10.1109/asru.2009.5373329","mag":"2131646590"},"language":"en","primary_location":{"id":"doi:10.1109/asru.2009.5373329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","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/A5113807382","display_name":"Yun-Hsuan Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yun-Hsuan Sung","raw_affiliation_strings":["Electrical Engineering, University of Stanford, USA","[Electrical engineering, Stanford University, USA]"],"affiliations":[{"raw_affiliation_string":"Electrical Engineering, University of Stanford, USA","institution_ids":["https://openalex.org/I97018004"]},{"raw_affiliation_string":"[Electrical engineering, Stanford University, USA]","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087088138","display_name":"Dan Jurafsky","orcid":"https://orcid.org/0000-0002-6459-7745"},"institutions":[{"id":"https://openalex.org/I1344076864","display_name":"Center for Applied Linguistics","ror":"https://ror.org/020pekv35","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I1344076864"]},{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dan Jurafsky","raw_affiliation_strings":["Linguistics, University of Stanford, USA","Linguistics, Stanford University, USA"],"affiliations":[{"raw_affiliation_string":"Linguistics, University of Stanford, USA","institution_ids":["https://openalex.org/I1344076864"]},{"raw_affiliation_string":"Linguistics, Stanford University, USA","institution_ids":["https://openalex.org/I97018004"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5113807382"],"corresponding_institution_ids":["https://openalex.org/I97018004"],"apc_list":null,"apc_paid":null,"fwci":7.7006,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.97345551,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"17","issue":null,"first_page":"107","last_page":"112"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9998000264167786,"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/T10860","display_name":"Speech and Audio Processing","score":0.9983999729156494,"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":0.9368863105773926},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.8266481161117554},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.7885360717773438},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.718957781791687},{"id":"https://openalex.org/keywords/timit","display_name":"TIMIT","score":0.6797741651535034},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.639944851398468},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.6235647201538086},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5979128479957581},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5261970162391663},{"id":"https://openalex.org/keywords/word-error-rate","display_name":"Word error rate","score":0.5218576192855835},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5211601257324219},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.5131273865699768},{"id":"https://openalex.org/keywords/sequence-labeling","display_name":"Sequence labeling","score":0.47962555289268494},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4570278525352478},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45185011625289917},{"id":"https://openalex.org/keywords/crfs","display_name":"CRFS","score":0.44596847891807556},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3214843273162842},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1714487075805664},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.07629510760307312}],"concepts":[{"id":"https://openalex.org/C152565575","wikidata":"https://www.wikidata.org/wiki/Q1124538","display_name":"Conditional random field","level":2,"score":0.9368863105773926},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.8266481161117554},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.7885360717773438},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718957781791687},{"id":"https://openalex.org/C2778724510","wikidata":"https://www.wikidata.org/wiki/Q7670405","display_name":"TIMIT","level":3,"score":0.6797741651535034},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.639944851398468},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.6235647201538086},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5979128479957581},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5261970162391663},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.5218576192855835},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5211601257324219},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.5131273865699768},{"id":"https://openalex.org/C35639132","wikidata":"https://www.wikidata.org/wiki/Q7452468","display_name":"Sequence labeling","level":3,"score":0.47962555289268494},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4570278525352478},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45185011625289917},{"id":"https://openalex.org/C2775953691","wikidata":"https://www.wikidata.org/wiki/Q5013874","display_name":"CRFS","level":3,"score":0.44596847891807556},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3214843273162842},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1714487075805664},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07629510760307312},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/asru.2009.5373329","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asru.2009.5373329","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE Workshop on Automatic Speech Recognition & Understanding","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.75,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W70249898","https://openalex.org/W1766290689","https://openalex.org/W1977697308","https://openalex.org/W2022951240","https://openalex.org/W2077804127","https://openalex.org/W2100474170","https://openalex.org/W2100870848","https://openalex.org/W2115439799","https://openalex.org/W2126599445","https://openalex.org/W2133924365","https://openalex.org/W2145823193","https://openalex.org/W2147880316","https://openalex.org/W2150907703","https://openalex.org/W2156615793","https://openalex.org/W2158188757","https://openalex.org/W2163614729","https://openalex.org/W6637989529","https://openalex.org/W6674791529","https://openalex.org/W6681525777","https://openalex.org/W6682082992","https://openalex.org/W6682398751","https://openalex.org/W6683226453","https://openalex.org/W6683915439"],"related_works":["https://openalex.org/W2962906565","https://openalex.org/W2798423868","https://openalex.org/W3015678144","https://openalex.org/W2076440176","https://openalex.org/W2140585957","https://openalex.org/W2054134081","https://openalex.org/W2061027419","https://openalex.org/W1675450783","https://openalex.org/W189110383","https://openalex.org/W2404235285"],"abstract_inverted_index":{"We":[0,37,57,109],"apply":[1],"Hidden":[2],"Conditional":[3],"Random":[4],"Fields":[5],"(HCRFs)":[6],"to":[7,46,52,117,120],"the":[8],"task":[9],"of":[10,31],"TIMIT":[11],"phone":[12,47,55,70,84,103],"recognition.":[13,138],"HCRFs":[14,81],"are":[15,29],"discriminatively":[16],"trained":[17,90,97,105],"sequence":[18],"models":[19,125],"that":[20,28,111,132],"augment":[21],"conditional":[22],"random":[23],"fields":[24],"with":[25,49],"hidden":[26,77],"states":[27],"capable":[30],"representing":[32],"subphones":[33],"and":[34,72,101,126],"mixture":[35],"components.":[36],"extend":[38],"HCRFs,":[39],"which":[40],"had":[41],"previously":[42],"only":[43],"been":[44],"applied":[45],"classification":[48],"known":[50],"boundaries,":[51],"recognize":[53],"continuous":[54],"sequences.":[56],"use":[58],"an":[59],"N-best":[60],"inference":[61],"algorithm":[62],"in":[63],"both":[64],"learning":[65],"(to":[66,74],"approximate":[67],"all":[68],"competitor":[69],"sequences)":[71],"decoding":[73],"marginalize":[75],"over":[76],"states).":[78],"Our":[79],"monophone":[80],"achieve":[82],"28.3%":[83],"error":[85,104],"rate,":[86],"outperforming":[87],"maximum":[88,94],"likelihood":[89],"HMMs":[91,98,106],"by":[92,99,107],"3.6%,":[93],"mutual":[95],"information":[96],"2.5%,":[100],"minimum":[102],"2.2%.":[108],"show":[110],"this":[112],"win":[113],"is":[114],"partially":[115],"due":[116],"HCRFs'":[118],"ability":[119],"simultaneously":[121],"optimize":[122],"discriminative":[123],"language":[124],"acoustic":[127],"models,":[128],"a":[129],"powerful":[130],"property":[131],"has":[133],"important":[134],"implications":[135],"for":[136],"speech":[137]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":9},{"year":2012,"cited_by_count":8}],"updated_date":"2026-03-10T16:38:18.471706","created_date":"2025-10-10T00:00:00"}