{"id":"https://openalex.org/W2101589014","doi":"https://doi.org/10.1109/icassp.2008.4518573","title":"Random-forests-based phonetic decision trees for conversational speech recognition","display_name":"Random-forests-based phonetic decision trees for conversational speech recognition","publication_year":2008,"publication_date":"2008-03-01","ids":{"openalex":"https://openalex.org/W2101589014","doi":"https://doi.org/10.1109/icassp.2008.4518573","mag":"2101589014"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2008.4518573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","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/A5100763213","display_name":"Jian Xue","orcid":"https://orcid.org/0000-0002-9460-802X"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jian Xue","raw_affiliation_strings":["Department of Computer Science, University of Missouri, Columbia, MO, USA","[Department of Computer Science, University of Missouri, Columbia, MO]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"[Department of Computer Science, University of Missouri, Columbia, MO]","institution_ids":["https://openalex.org/I76835614"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033518479","display_name":"Yunxin Zhao","orcid":"https://orcid.org/0000-0001-5511-3692"},"institutions":[{"id":"https://openalex.org/I76835614","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06","country_code":"US","type":"education","lineage":["https://openalex.org/I76835614"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunxin Zhao","raw_affiliation_strings":["Department of Computer Science, University of Missouri, Columbia, MO, USA","[Department of Computer Science, University of Missouri, Columbia, MO]"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]},{"raw_affiliation_string":"[Department of Computer Science, University of Missouri, Columbia, MO]","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I76835614"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.13465605,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"4169","last_page":"4172"},"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/T11309","display_name":"Music and Audio Processing","score":0.9990000128746033,"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/computer-science","display_name":"Computer science","score":0.7772653102874756},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.6617739200592041},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.6524561643600464},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.6514655351638794},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.531568706035614},{"id":"https://openalex.org/keywords/acoustic-model","display_name":"Acoustic model","score":0.529190182685852},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.4789493680000305},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.47717633843421936},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.45609796047210693},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43685242533683777},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4110192060470581},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3512860834598541},{"id":"https://openalex.org/keywords/speech-processing","display_name":"Speech processing","score":0.31489452719688416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.0945909321308136}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7772653102874756},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6617739200592041},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.6524561643600464},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.6514655351638794},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.531568706035614},{"id":"https://openalex.org/C155635449","wikidata":"https://www.wikidata.org/wiki/Q4674699","display_name":"Acoustic model","level":3,"score":0.529190182685852},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.4789493680000305},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.47717633843421936},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.45609796047210693},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43685242533683777},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4110192060470581},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3512860834598541},{"id":"https://openalex.org/C61328038","wikidata":"https://www.wikidata.org/wiki/Q3358061","display_name":"Speech processing","level":2,"score":0.31489452719688416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0945909321308136},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2008.4518573","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2008.4518573","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":"1520-6149","issn":["1520-6149","2379-190X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2008 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1534477342","https://openalex.org/W1543659151","https://openalex.org/W1605688901","https://openalex.org/W2045902811","https://openalex.org/W2049633694","https://openalex.org/W2103248292","https://openalex.org/W2108446915","https://openalex.org/W2132051730","https://openalex.org/W2140051273","https://openalex.org/W2148428486","https://openalex.org/W2158069733","https://openalex.org/W2159322479","https://openalex.org/W2160237783","https://openalex.org/W2335925837","https://openalex.org/W2911964244","https://openalex.org/W2912934387","https://openalex.org/W4212883601","https://openalex.org/W6676666668"],"related_works":["https://openalex.org/W2047632477","https://openalex.org/W2121652828","https://openalex.org/W2126322296","https://openalex.org/W1992088235","https://openalex.org/W2163537793","https://openalex.org/W4386794561","https://openalex.org/W2916997151","https://openalex.org/W2781555308","https://openalex.org/W3021690593","https://openalex.org/W2992378684"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3,43],"present":[4],"a":[5,28,107],"novel":[6],"technique":[7,117],"of":[8,30,79,91],"constructing":[9],"phonetic":[10],"decision":[11],"trees":[12],"(PDTs)":[13],"for":[14,32,72],"acoustic":[15,39,54],"modeling":[16],"in":[17,60,122],"conversational":[18],"speech":[19],"recognition.":[20],"We":[21,52],"use":[22],"random":[23],"forests":[24],"(RF)":[25],"to":[26,49,67,96,119],"train":[27],"set":[29],"PDTs":[31],"each":[33],"phone-state":[34],"unit":[35],"and":[36,42],"obtain":[37,97],"multiple":[38],"models":[40],"accordingly,":[41],"extend":[44],"the":[45,57,69,80,98,114],"PDT-based":[46],"state":[47],"tying":[48],"RF-based":[50],"state-tying.":[51],"combine":[53],"scores":[55,90],"at":[56],"model":[58,73],"level":[59],"decoding":[61],"search.":[62],"Several":[63],"methods":[64],"are":[65],"investigated":[66],"estimate":[68],"weight":[70],"parameters":[71],"combination,":[74],"including":[75],"maximum":[76],"likelihood":[77],"estimation":[78],"weights":[81,99],"from":[82,101],"training":[83],"data,":[84],"as":[85,87],"well":[86],"using":[88],"confidence":[89],"P-value":[92],"or":[93],"relative":[94],"entropy":[95],"dynamically":[100],"online":[102],"data.":[103],"Experimental":[104],"results":[105],"on":[106],"telemedicine":[108],"automatic":[109],"captioning":[110],"task":[111],"demonstrate":[112],"that":[113],"proposed":[115],"RF-PDT":[116],"leads":[118],"significant":[120],"improvements":[121],"word":[123],"recognition":[124],"accuracy.":[125]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}