{"id":"https://openalex.org/W1981735114","doi":"https://doi.org/10.1109/icassp.2002.5743877","title":"Efficient reduction of Gaussian components using MDL criterion for HMM-based speech recognition","display_name":"Efficient reduction of Gaussian components using MDL criterion for HMM-based speech recognition","publication_year":2002,"publication_date":"2002-05-01","ids":{"openalex":"https://openalex.org/W1981735114","doi":"https://doi.org/10.1109/icassp.2002.5743877","mag":"1981735114"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2002.5743877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743877","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"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":"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/A5081629487","display_name":"Koichi Shinoda","orcid":"https://orcid.org/0000-0003-1095-3203"},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]},{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koichi Shinoda","raw_affiliation_strings":["Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","Mutimedia Research, NEC Corporation Limited, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"Mutimedia Research, NEC Corporation Limited, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109220146","display_name":"Ken-ichi Iso","orcid":null},"institutions":[{"id":"https://openalex.org/I118347220","display_name":"NEC (Japan)","ror":"https://ror.org/04jndar25","country_code":"JP","type":"company","lineage":["https://openalex.org/I118347220"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ken-ichi Iso","raw_affiliation_strings":["Mutimedia Research, NEC Corporation Limited, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Mutimedia Research, NEC Corporation Limited, Kawasaki, Japan","institution_ids":["https://openalex.org/I118347220"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5081629487"],"corresponding_institution_ids":["https://openalex.org/I118347220","https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":1.7754,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.85571979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"3","issue":null,"first_page":"I","last_page":"869"},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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":0.995199978351593,"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":0.8612543344497681},{"id":"https://openalex.org/keywords/minimum-description-length","display_name":"Minimum description length","score":0.7753552198410034},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.7386988401412964},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6254251003265381},{"id":"https://openalex.org/keywords/gaussian-process","display_name":"Gaussian process","score":0.549351155757904},{"id":"https://openalex.org/keywords/probability-density-function","display_name":"Probability density function","score":0.5216079950332642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49046871066093445},{"id":"https://openalex.org/keywords/mixture-model","display_name":"Mixture model","score":0.4801151752471924},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4543950855731964},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.45069390535354614},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.4445195496082306},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.4327981173992157},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40759730339050293},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3944048285484314},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.32252639532089233},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.07037121057510376}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.8612543344497681},{"id":"https://openalex.org/C87465248","wikidata":"https://www.wikidata.org/wiki/Q1417790","display_name":"Minimum description length","level":2,"score":0.7753552198410034},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.7386988401412964},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6254251003265381},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.549351155757904},{"id":"https://openalex.org/C197055811","wikidata":"https://www.wikidata.org/wiki/Q207522","display_name":"Probability density function","level":2,"score":0.5216079950332642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49046871066093445},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.4801151752471924},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4543950855731964},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.45069390535354614},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4445195496082306},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.4327981173992157},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40759730339050293},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3944048285484314},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.32252639532089233},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.07037121057510376},{"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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp.2002.5743877","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2002.5743877","pdf_url":null,"source":{"id":"https://openalex.org/S4363607879","display_name":"IEEE International Conference on Acoustics Speech and Signal Processing","issn_l":null,"issn":null,"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":"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","score":0.75,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W18856025","https://openalex.org/W25204975","https://openalex.org/W151735098","https://openalex.org/W1503019348","https://openalex.org/W1537395006","https://openalex.org/W1564719928","https://openalex.org/W1963627370","https://openalex.org/W2125057358","https://openalex.org/W2132119275","https://openalex.org/W2289240870","https://openalex.org/W6600764288","https://openalex.org/W6601039578","https://openalex.org/W6632180603","https://openalex.org/W6633810192","https://openalex.org/W6678650179"],"related_works":["https://openalex.org/W4298831272","https://openalex.org/W2962916388","https://openalex.org/W2086694237","https://openalex.org/W2095614499","https://openalex.org/W2489956408","https://openalex.org/W1853799209","https://openalex.org/W1992295166","https://openalex.org/W2153309934","https://openalex.org/W2143508933","https://openalex.org/W4312179141"],"abstract_inverted_index":{"A":[0],"method":[1,23,105],"is":[2,55,85],"proposed":[3,104],"to":[4,87],"reduce":[5],"the":[6,22,31,58,62,65,73,81,89,103,108],"number":[7,91,109],"of":[8,33,52,64,92,110],"Gaussian":[9,36,53,59,93,111],"components":[10,32,54,94,112],"in":[11,29,80,119],"continuous":[12],"density":[13,39],"hidden":[14],"Markov":[15],"models":[16,79],"(HMMs).":[17],"As":[18],"its":[19],"initial":[20],"model,":[21],"employs":[24],"a":[25,44,50],"well-trained,":[26],"large-sized":[27],"HMM":[28],"which":[30],"each":[34,48],"state's":[35],"mixture":[37],"probability":[38],"function":[40],"are":[41],"clustered":[42],"into":[43],"binary":[45],"tree.":[46],"For":[47],"state,":[49],"subset":[51],"chosen":[56],"from":[57],"tree":[60],"on":[61],"basis":[63],"minimum":[66],"description":[67],"length":[68],"(MDL)":[69],"criterion.":[70],"By":[71],"varying":[72],"penalty":[74],"coefficient":[75],"for":[76,96],"large":[77],"size":[78],"MDL":[82],"criterion,":[83],"it":[84],"possible":[86],"obtain":[88],"total":[90],"desired":[95],"smaller":[97],"models.":[98],"In":[99],"our":[100],"experimental":[101],"evaluations,":[102],"successfully":[106],"reduced":[107],"by":[113],"75%,":[114],"with":[115],"only":[116],"1%":[117],"degradation":[118],"recognition":[120],"accuracy.":[121]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}