{"id":"https://openalex.org/W1566481915","doi":"https://doi.org/10.1109/icassp.2004.1326110","title":"Automatic determination of acoustic model topology using variational Bayesian estimation and clustering","display_name":"Automatic determination of acoustic model topology using variational Bayesian estimation and clustering","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W1566481915","doi":"https://doi.org/10.1109/icassp.2004.1326110","mag":"1566481915"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2004.1326110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326110","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/A5101607489","display_name":"Takao Watanabe","orcid":"https://orcid.org/0000-0002-7929-1781"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"T. Watanabe","raw_affiliation_strings":["Speech Open Laboratory, NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan"],"affiliations":[{"raw_affiliation_string":"Speech Open Laboratory, NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Commun. Sci. Lab., NTT Corp., Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080338744","display_name":"L. Sako","orcid":null},"institutions":[{"id":"https://openalex.org/I103390050","display_name":"Ryukoku University","ror":"https://ror.org/012tqgb57","country_code":"JP","type":"education","lineage":["https://openalex.org/I103390050"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"L. Sako","raw_affiliation_strings":["Department of Science and Technology, Ryukoku University, Otsu, Shiga, Japan","[Department of Science and Technology, Ryukoku University, Otsu, Shiga, Japan]"],"affiliations":[{"raw_affiliation_string":"Department of Science and Technology, Ryukoku University, Otsu, Shiga, Japan","institution_ids":["https://openalex.org/I103390050"]},{"raw_affiliation_string":"[Department of Science and Technology, Ryukoku University, Otsu, Shiga, Japan]","institution_ids":["https://openalex.org/I103390050"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007200758","display_name":"Fumihiko Nakamura","orcid":"https://orcid.org/0000-0001-6285-3963"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"F. Nakamura","raw_affiliation_strings":["Speech Open Laboratory, NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","[Speech Open Laboratory, NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan]"],"affiliations":[{"raw_affiliation_string":"Speech Open Laboratory, NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"[Speech Open Laboratory, NTT Communication Science Laboratories, NTT Corporation, Soraku-gun, Kyoto, Japan]","institution_ids":["https://openalex.org/I2251713219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101607489"],"corresponding_institution_ids":["https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":2.6982,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90367933,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":null,"biblio":{"volume":"1","issue":null,"first_page":"I","last_page":"813"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987999796867371,"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":0.9987999796867371,"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":0.9962999820709229,"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":0.9861999750137329,"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/mixture-model","display_name":"Mixture model","score":0.7267376184463501},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6232671737670898},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6140837073326111},{"id":"https://openalex.org/keywords/posterior-probability","display_name":"Posterior probability","score":0.5897996425628662},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5434837341308594},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.5383303165435791},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5162456035614014},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.47727078199386597},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.45845240354537964},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4477531611919403},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.44341400265693665},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4116942286491394},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3792802691459656},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30207014083862305},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.14424487948417664}],"concepts":[{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7267376184463501},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6232671737670898},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6140837073326111},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.5897996425628662},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5434837341308594},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.5383303165435791},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5162456035614014},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.47727078199386597},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.45845240354537964},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4477531611919403},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.44341400265693665},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4116942286491394},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3792802691459656},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30207014083862305},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.14424487948417664},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2004.1326110","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2004.1326110","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.7699999809265137}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1564719928","https://openalex.org/W1618600317","https://openalex.org/W1724524793","https://openalex.org/W1963627370","https://openalex.org/W2068970468","https://openalex.org/W2138265553","https://openalex.org/W2164250771","https://openalex.org/W6636504819","https://openalex.org/W6637600633"],"related_works":["https://openalex.org/W1952261593","https://openalex.org/W2990323019","https://openalex.org/W2014494654","https://openalex.org/W2032094637","https://openalex.org/W2040227828","https://openalex.org/W4244110343","https://openalex.org/W2060045818","https://openalex.org/W2131935101","https://openalex.org/W856257623","https://openalex.org/W2892315154"],"abstract_inverted_index":{"We":[0,30],"describe":[1],"the":[2,44,56,67,84,91,96,112],"automatic":[3],"determination":[4],"of":[5,60],"an":[6,32,107],"acoustic":[7],"model":[8,36,109],"for":[9,27,63,95],"speech":[10,28],"recognition,":[11],"which":[12],"is":[13,88],"very":[14],"complicated":[15],"and":[16,25,87],"includes":[17],"latent":[18],"variables,":[19],"using":[20],"VBEC:":[21],"variational":[22],"Bayesian":[23],"estimation":[24],"clustering":[26],"recognition.":[29],"propose":[31],"efficient":[33],"Gaussian":[34,80],"mixture":[35],"(GMM)":[37],"based":[38],"phonetic":[39],"decision":[40,69],"tree":[41,70],"construction":[42],"within":[43],"VBEC":[45,104],"framework.":[46],"The":[47,99],"proposed":[48],"method":[49,71],"features":[50],"a":[51,73],"novel":[52],"approach":[53],"to":[54,72],"reduce":[55],"unrealistically":[57],"large":[58],"number":[59],"computations":[61],"needed":[62],"iterative":[64],"calculations":[65],"in":[66],"GMM-based":[68],"practical":[74],"level":[75],"by":[76,90],"assuming":[77],"that":[78,103],"each":[79],"per":[81],"state":[82],"has":[83],"same":[85,92],"occupancy":[86],"represented":[89],"posterior":[93],"distribution":[94],"covariance":[97],"parameter.":[98],"experimental":[100],"results":[101],"confirmed":[102],"automatically":[105],"provided":[106],"optimum":[108],"topology":[110],"with":[111],"highest":[113],"performance":[114],"level.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}