{"id":"https://openalex.org/W2108661814","doi":"https://doi.org/10.1109/icassp.2004.1326108","title":"Automatic generation of non-uniform HMM structures based on variational Bayesian approach","display_name":"Automatic generation of non-uniform HMM structures based on variational Bayesian approach","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W2108661814","doi":"https://doi.org/10.1109/icassp.2004.1326108","mag":"2108661814"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 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/A5061510158","display_name":"Takatoshi Jitsuhiro","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"T. Jitsuhiro","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Kyoto, Japan","ATR Spoken Language Translation Res. Labs., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"ATR Spoken Language Translation Res. Labs., Kyoto, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080776631","display_name":"Satoshi Nakamura","orcid":"https://orcid.org/0000-0003-3492-7093"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"S. Nakamura","raw_affiliation_strings":["ATR Spoken Language Translation Research Laboratories, Kyoto, Japan","ATR Spoken Language Translation Res. Labs., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"ATR Spoken Language Translation Research Laboratories, Kyoto, Japan","institution_ids":[]},{"raw_affiliation_string":"ATR Spoken Language Translation Res. Labs., Kyoto, Japan","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5061510158"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7988,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87570813,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"805"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9894999861717224,"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":0.9886999726295471,"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":0.864189863204956},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7044705152511597},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.5314582586288452},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5290499925613403},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5156992077827454},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.4675979018211365},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.4622018337249756},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4582781493663788},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.44648152589797974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3864079415798187},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.37542667984962463},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.37311333417892456},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18117418885231018}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.864189863204956},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7044705152511597},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.5314582586288452},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5290499925613403},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5156992077827454},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.4675979018211365},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.4622018337249756},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4582781493663788},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.44648152589797974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3864079415798187},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.37542667984962463},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.37311333417892456},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18117418885231018},{"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/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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},{"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/icassp.2004.1326108","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326108","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2004 IEEE International Conference on Acoustics, Speech, and Signal Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W42776112","https://openalex.org/W102093577","https://openalex.org/W1618600317","https://openalex.org/W2068970468","https://openalex.org/W2105658140","https://openalex.org/W2108075847","https://openalex.org/W2138265553","https://openalex.org/W2145826596","https://openalex.org/W2158069733","https://openalex.org/W6636504819","https://openalex.org/W6675968574","https://openalex.org/W6680294134"],"related_works":["https://openalex.org/W2136763963","https://openalex.org/W2109705048","https://openalex.org/W2940588515","https://openalex.org/W1909151225","https://openalex.org/W3184123547","https://openalex.org/W2160030256","https://openalex.org/W1521297879","https://openalex.org/W4253235840","https://openalex.org/W3151937861","https://openalex.org/W2488941600"],"abstract_inverted_index":{"We":[0,71,93],"propose":[1],"using":[2],"the":[3,61,68,73,77,95,116,134],"variational":[4],"Bayesian":[5],"(VB)":[6],"approach":[7,63,75],"for":[8,91,131],"automatically":[9,120],"creating":[10],"nonuniform,":[11],"context-dependent":[12],"HMM":[13,28],"topologies":[14],"in":[15,67],"speech":[16],"recognition.":[17],"The":[18],"maximum":[19],"likelihood":[20],"(ML)":[21],"criterion":[22],"is":[23],"generally":[24],"used":[25,40],"to":[26,41,51,57,76],"create":[27,85,121],"topologies.":[29],"However,":[30],"it":[31],"has":[32,64],"an":[33],"over-fitting":[34],"problem.":[35],"Information":[36],"criteria":[37],"have":[38],"been":[39,65],"overcome":[42],"this":[43],"problem,":[44],"but":[45],"theoretically":[46],"they":[47],"cannot":[48],"be":[49],"applied":[50],"complicated":[52],"models":[53],"like":[54],"HMM.":[55,92],"Recently,":[56],"avoid":[58],"these":[59],"problems,":[60],"VB":[62,74],"developed":[66],"machine-learning":[69],"field.":[70],"introduce":[72],"successive":[78],"state":[79],"splitting":[80],"(SSS)":[81],"algorithm,":[82],"which":[83],"can":[84,119],"both":[86],"contextual":[87],"and":[88,97,101,109,126],"temporal":[89],"variations":[90],"define":[94],"prior":[96],"posterior":[98],"probability":[99],"densities":[100],"free":[102],"energy":[103],"with":[104],"latent":[105],"variables":[106],"as":[107],"split":[108],"stop":[110],"criteria.":[111],"Experimental":[112],"results":[113],"show":[114],"that":[115],"proposed":[117],"method":[118],"a":[122],"more":[123],"efficient":[124],"model":[125],"obtain":[127],"better":[128],"performance,":[129],"especially":[130],"vowels,":[132],"than":[133],"original":[135],"method.":[136]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}