{"id":"https://openalex.org/W2114071612","doi":"https://doi.org/10.1109/icassp.2009.4960622","title":"Semi-tied covariance matrices for acoustic models based on random forests of phonetic decision trees","display_name":"Semi-tied covariance matrices for acoustic models based on random forests of phonetic decision trees","publication_year":2009,"publication_date":"2009-04-01","ids":{"openalex":"https://openalex.org/W2114071612","doi":"https://doi.org/10.1109/icassp.2009.4960622","mag":"2114071612"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2009.4960622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal 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/A5100763213","display_name":"Jian Xue","orcid":"https://orcid.org/0000-0002-9460-802X"},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jian Xue","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112879292","display_name":"Lili Che","orcid":null},"institutions":[{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lili Che","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA"],"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]}]},{"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"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Missouri, Columbia, MO, USA","institution_ids":["https://openalex.org/I76835614"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100763213"],"corresponding_institution_ids":["https://openalex.org/I4210114115"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11882626,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"16","issue":null,"first_page":"4469","last_page":"4472"},"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/T11309","display_name":"Music 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/T10181","display_name":"Natural Language Processing Techniques","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6741104125976562},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.6648707985877991},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5661489963531494},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5054152011871338},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.48151835799217224},{"id":"https://openalex.org/keywords/hidden-markov-model","display_name":"Hidden Markov model","score":0.4718755781650543},{"id":"https://openalex.org/keywords/covariance-intersection","display_name":"Covariance intersection","score":0.4259433150291443},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.425446480512619},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4163963496685028},{"id":"https://openalex.org/keywords/covariance-matrix","display_name":"Covariance matrix","score":0.41456758975982666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3880668878555298},{"id":"https://openalex.org/keywords/covariance-function","display_name":"Covariance function","score":0.31689220666885376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20069792866706848},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.18131402134895325},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.13364297151565552}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6741104125976562},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.6648707985877991},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5661489963531494},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5054152011871338},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.48151835799217224},{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.4718755781650543},{"id":"https://openalex.org/C83042196","wikidata":"https://www.wikidata.org/wiki/Q5178898","display_name":"Covariance intersection","level":4,"score":0.4259433150291443},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.425446480512619},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4163963496685028},{"id":"https://openalex.org/C185142706","wikidata":"https://www.wikidata.org/wiki/Q1134404","display_name":"Covariance matrix","level":2,"score":0.41456758975982666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3880668878555298},{"id":"https://openalex.org/C137250428","wikidata":"https://www.wikidata.org/wiki/Q5178897","display_name":"Covariance function","level":3,"score":0.31689220666885376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20069792866706848},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.18131402134895325},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.13364297151565552},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2009.4960622","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2009.4960622","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309568","display_name":"University of Missouri","ror":"https://ror.org/02ymw8z06"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W165056846","https://openalex.org/W1560013842","https://openalex.org/W2022627111","https://openalex.org/W2103248292","https://openalex.org/W2106554350","https://openalex.org/W2108446915","https://openalex.org/W2138955903","https://openalex.org/W2148428486","https://openalex.org/W2158069733"],"related_works":["https://openalex.org/W2022823194","https://openalex.org/W2572601863","https://openalex.org/W1987404909","https://openalex.org/W2018001152","https://openalex.org/W2109377650","https://openalex.org/W2554071524","https://openalex.org/W4309794518","https://openalex.org/W4311761947","https://openalex.org/W4282813214","https://openalex.org/W274661425"],"abstract_inverted_index":{"In":[0,66],"this":[1],"paper,":[2],"we":[3,69],"investigate":[4],"combining":[5],"semi-tied":[6,51,86,123],"covariance":[7,52,87,124],"matrices":[8,53,88,125],"and":[9,40],"random":[10],"forests":[11],"(RFs)":[12],"based":[13,133],"phonetic":[14],"decision":[15],"trees":[16],"(PDTs)":[17],"for":[18,35,79],"acoustic":[19,45,58,77,103,134],"modeling":[20],"in":[21],"conversational":[22],"speech":[23,81],"recognition.":[24],"We":[25,48],"first":[26],"use":[27],"the":[28,71,75,99,109,128,131],"RF":[29],"method":[30],"to":[31,54,60,64],"train":[32],"multiple":[33,42,76],"PDTs":[34],"each":[36,55,80],"phone":[37],"state":[38],"unit,":[39],"generate":[41],"sets":[43],"of":[44,57,85,101,112,115,130],"models":[46,59,78,104,135],"accordingly.":[47],"then":[49],"apply":[50],"set":[56],"improve":[61],"their":[62,96],"fit":[63],"data.":[65],"decoding":[67],"search":[68],"combine":[70],"likelihood":[72],"scores":[73],"from":[74,95],"frame.":[82],"The":[83],"viability":[84],"with":[89],"different":[90],"tying":[91],"classes":[92],"are":[93],"studied":[94],"effects":[97],"on":[98,108],"diversity":[100,129],"RF-based":[102],"as":[105,107,136,138],"well":[106,137],"word":[110,140],"accuracy":[111],"our":[113],"task":[114],"telehealth":[116],"automatic":[117],"captioning.":[118],"Experimental":[119],"results":[120],"indicate":[121],"that":[122],"help":[126],"enhance":[127],"RFs-PDTs":[132],"increase":[139],"accuracy.":[141]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}