{"id":"https://openalex.org/W2005687631","doi":"https://doi.org/10.1109/icassp.2010.5495122","title":"GMM-HMM acoustic model training by a two level procedure with Gaussian components determined by automatic model selection","display_name":"GMM-HMM acoustic model training by a two level procedure with Gaussian components determined by automatic model selection","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2005687631","doi":"https://doi.org/10.1109/icassp.2010.5495122","mag":"2005687631"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2010.5495122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 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/A5075183307","display_name":"Dan Su","orcid":"https://orcid.org/0000-0001-5746-9545"},"institutions":[{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dan Su","raw_affiliation_strings":["Speech and Hearing Research Center, Key Laboratory of Machine Perception Ministry of Education, Peking University, China","Speech and Hearing Research Center, Key Laboratory of Machine Perception, (Ministry of Education), Peking University, China"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception Ministry of Education, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception, (Ministry of Education), Peking University, China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084685506","display_name":"Xihong Wu","orcid":"https://orcid.org/0009-0004-5236-7469"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xihong Wu","raw_affiliation_strings":["Speech and Hearing Research Center, Key Laboratory of Machine Perception Ministry of Education, Peking University, China","Speech and Hearing Research Center, Key Laboratory of Machine Perception, (Ministry of Education), Peking University, China"],"affiliations":[{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception Ministry of Education, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception, (Ministry of Education), Peking University, China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I20231570"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069972085","display_name":"Lei Xu","orcid":"https://orcid.org/0000-0002-2752-1573"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I1327237609","display_name":"Ministry of Education of the People's Republic of China","ror":"https://ror.org/01mv9t934","country_code":"CN","type":"funder","lineage":["https://openalex.org/I1327237609","https://openalex.org/I4210127390"]},{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Xu","raw_affiliation_strings":["Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China","Speech and Hearing Research Center, Key Laboratory of Machine Perception Ministry of Education, Peking University, China","Speech and Hearing Research Center, Key Laboratory of Machine Perception, (Ministry of Education), Peking University, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception Ministry of Education, Peking University, China","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Speech and Hearing Research Center, Key Laboratory of Machine Perception, (Ministry of Education), Peking University, China","institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5075183307"],"corresponding_institution_ids":["https://openalex.org/I1327237609","https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":2.787,"has_fulltext":false,"cited_by_count":33,"citation_normalized_percentile":{"value":0.90855335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"4890","last_page":"4893"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9973999857902527,"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/T11901","display_name":"Bayesian Methods and Mixture Models","score":0.9883000254631042,"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/hidden-markov-model","display_name":"Hidden Markov model","score":0.7988001108169556},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.7551114559173584},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.6840579509735107},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.616995096206665},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5658868551254272},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5606715083122253},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4881154000759125},{"id":"https://openalex.org/keywords/mixture-theory","display_name":"Mixture theory","score":0.464703232049942},{"id":"https://openalex.org/keywords/expectation\u2013maximization-algorithm","display_name":"Expectation\u2013maximization algorithm","score":0.4633150100708008},{"id":"https://openalex.org/keywords/bayesian-probability","display_name":"Bayesian probability","score":0.4540867805480957},{"id":"https://openalex.org/keywords/model-selection","display_name":"Model selection","score":0.41424083709716797},{"id":"https://openalex.org/keywords/maximum-likelihood","display_name":"Maximum likelihood","score":0.356102854013443},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3124156892299652},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.15958276391029358},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.15620014071464539}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.7988001108169556},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.7551114559173584},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.6840579509735107},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.616995096206665},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5658868551254272},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5606715083122253},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4881154000759125},{"id":"https://openalex.org/C2779736610","wikidata":"https://www.wikidata.org/wiki/Q6884140","display_name":"Mixture theory","level":3,"score":0.464703232049942},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.4633150100708008},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.4540867805480957},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.41424083709716797},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.356102854013443},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3124156892299652},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.15958276391029358},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.15620014071464539}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icassp.2010.5495122","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2010.5495122","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Conference on Acoustics, Speech and Signal Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.185.1381","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.185.1381","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cuhk.hk/%7Elxu/papers/conf-chapters/10ICASSP-SUD.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1755985346","https://openalex.org/W1903355235","https://openalex.org/W1981735114","https://openalex.org/W2003123121","https://openalex.org/W2044139911","https://openalex.org/W2058815839","https://openalex.org/W2107617395","https://openalex.org/W2120941820","https://openalex.org/W2150907703","https://openalex.org/W2167270514","https://openalex.org/W3148637803","https://openalex.org/W4252386822","https://openalex.org/W6665272994"],"related_works":["https://openalex.org/W2548184953","https://openalex.org/W1528914981","https://openalex.org/W2473373438","https://openalex.org/W2368486525","https://openalex.org/W1598110435","https://openalex.org/W1853799209","https://openalex.org/W2108876167","https://openalex.org/W2014842417","https://openalex.org/W2536221661","https://openalex.org/W2261707252"],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,28,35,40,45,50,72,94,105,115,137,144],"Bayesian":[4],"Ying-Yang":[5,61],"(BYY)":[6],"learning":[7,91],"for":[8],"speech":[9,128],"recognition":[10,129],"via":[11],"Gaussian":[12],"mixture":[13],"models":[14,19],"(GMMs)":[15],"based":[16],"Hidden":[17],"Markov":[18,30],"(HMMs).":[20],"A":[21],"two":[22],"level":[23,31,47],"procedure":[24],"is":[25,77],"proposed":[26,55,145],"with":[27,44,114],"hidden":[29],"trained":[32,48],"still":[33],"under":[34,49],"maximum":[36],"likelihood":[37],"principle":[38],"by":[39,104],"Baum-Welch":[41,73],"algorithm":[42,63,146],"but":[43],"GMMs":[46],"BYY":[51,89],"best":[52],"harmony.":[53],"We":[54],"a":[56,68,132],"new":[57],"batch":[58],"way":[59],"EM-like":[60],"alternation":[62],"and":[64,92,109,119,126,151],"used":[65],"it":[66],"as":[67],"plug-in":[69],"block":[70],"to":[71],"algorithm.":[74],"The":[75],"advantage":[76],"that":[78,93,143],"number":[79],"of":[80,107],"GMM":[81],"components":[82],"can":[83],"be":[84],"automatically":[85],"determined":[86],"during":[87],"this":[88],"harmony":[90],"resulted":[95],"model":[96,121],"parameters":[97],"become":[98],"less":[99],"affected":[100],"than":[101],"EM-ML":[102,117],"training":[103,118],"problem":[106],"overfitting":[108],"singular":[110],"solution.":[111],"In":[112],"comparison":[113],"standard":[116],"classical":[120],"selection":[122],"criterions,":[123],"including":[124],"BIC":[125],"AIC,":[127],"experiments":[130],"in":[131],"large":[133],"vocabulary":[134],"task":[135],"on":[136],"Hub4":[138],"broadcast":[139],"news":[140],"database":[141],"shown":[142],"provides":[147],"an":[148],"improved":[149],"performance":[150],"also":[152],"good":[153],"convergence.":[154]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}