{"id":"https://openalex.org/W2096040352","doi":"https://doi.org/10.1109/icassp.2003.1198736","title":"Hybrid modeling of PHMM and HMM for speech recognition","display_name":"Hybrid modeling of PHMM and HMM for speech recognition","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2096040352","doi":"https://doi.org/10.1109/icassp.2003.1198736","mag":"2096040352"},"language":"en","primary_location":{"id":"doi:10.1109/icassp.2003.1198736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198736","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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/A5087632404","display_name":"Tetsuji Ogawa","orcid":"https://orcid.org/0000-0002-7316-2073"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"T. Ogawa","raw_affiliation_strings":["Department EECE, Waseda University, Shinjuku, Tokyo, Japan","Dept.EECE, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department EECE, Waseda University, Shinjuku, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Dept.EECE, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074595893","display_name":"Tetsuo Kobayashi","orcid":"https://orcid.org/0000-0002-4008-454X"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T. Kobayashi","raw_affiliation_strings":["Department EECE, Waseda University, Shinjuku, Tokyo, Japan","Dept.EECE, Waseda University, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Department EECE, Waseda University, Shinjuku, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]},{"raw_affiliation_string":"Dept.EECE, Waseda University, Tokyo, Japan","institution_ids":["https://openalex.org/I150744194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5087632404"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.23526474,"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":"140"},"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/T10860","display_name":"Speech and Audio Processing","score":0.9994000196456909,"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/T11309","display_name":"Music and Audio Processing","score":0.9939000010490417,"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":0.9554873108863831},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6310964226722717},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6268280148506165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5987281203269958},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.5383777022361755},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.46409764885902405},{"id":"https://openalex.org/keywords/basis","display_name":"Basis (linear algebra)","score":0.4493713974952698},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2532408535480499}],"concepts":[{"id":"https://openalex.org/C23224414","wikidata":"https://www.wikidata.org/wiki/Q176769","display_name":"Hidden Markov model","level":2,"score":0.9554873108863831},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6310964226722717},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6268280148506165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5987281203269958},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.5383777022361755},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.46409764885902405},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.4493713974952698},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2532408535480499},{"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.2003.1198736","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp.2003.1198736","pdf_url":null,"source":{"id":"https://openalex.org/S4363608982","display_name":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":"2003 IEEE International Conference on Acoustics, Speech, and Signal Processing, 2003. Proceedings. (ICASSP '03).","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":0.75}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W146926017","https://openalex.org/W1521340514","https://openalex.org/W1521741510","https://openalex.org/W2072788898","https://openalex.org/W2091670016","https://openalex.org/W2096837052","https://openalex.org/W2108608770","https://openalex.org/W2151485937","https://openalex.org/W2154794291","https://openalex.org/W2166388645","https://openalex.org/W6605918199","https://openalex.org/W6631254342","https://openalex.org/W6631312538"],"related_works":["https://openalex.org/W2364370872","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/W2536059291","https://openalex.org/W4253235840","https://openalex.org/W3151937861"],"abstract_inverted_index":{"A":[0],"hybrid":[1],"acoustic":[2,29,71],"model":[3,8,72,151],"of":[4,28,76,92,120,132,138,162,179,193],"partly":[5],"hidden":[6],"Markov":[7],"(PHMM)":[9],"and":[10,33,49,82,95],"HMM":[11,63],"is":[12,105,152,165,182],"proposed.":[13],"PHMM":[14,112,156],"was":[15],"proposed":[16,150,195],"in":[17,46,78],"our":[18],"previous":[19],"work":[20],"to":[21,130,145],"deal":[22],"with":[23,59,205],"the":[24,74,80,89,118,139,149,158,175,191,194,199],"complicated":[25],"temporal":[26],"changes":[27],"features":[30],"(Ogawa,":[31],"T.":[32],"Kobayashi,":[34],"T,":[35],"Proc.":[36],"ICSLP2002,":[37],"p.2673-6,":[38],"2002).":[39],"It":[40,52],"can":[41],"realized":[42],"observation":[43,81],"dependent":[44],"behaviors":[45],"both":[47],"observations":[48],"state":[50,83],"transitions.":[51],"achieved":[53],"good":[54],"performance":[55],"but":[56,168,186],"some":[57],"errors":[58,127,201],"different":[60],"trends":[61],"from":[62],"still":[64],"remained.":[65],"We":[66],"have":[67],"designed":[68],"a":[69,102,107,122],"new":[70],"on":[73],"basis":[75],"PHMM,":[77,163],"which":[79,164,181],"transition":[84],"probabilities":[85],"are":[86,128,172],"defined":[87],"by":[88,110,174,202],"geometric":[90],"means":[91],"PHMM-based":[93],"ones":[94],"HMM-based":[96],"ones.":[97],"In":[98],"this":[99,142],"framework,":[100],"if":[101],"word":[103,200],"hypothesis":[104],"given":[106],"low":[108],"score":[109],"either":[111],"or":[113],"HMM,":[114,180],"it":[115,197],"almost":[116],"loses":[117],"possibility":[119],"being":[121],"probable":[123],"candidate.":[124],"Since":[125],"many":[126],"due":[129],"high-scores":[131],"incorrect":[133],"categories":[134],"rather":[135],"than":[136,155],"low-score":[137],"correct":[140],"category,":[141],"property":[143],"contributes":[144],"reducing":[146],"errors.":[147],"Moreover,":[148],"more":[153],"stable":[154],"because":[157],"higher":[159],"order":[160,177],"statistics":[161,178],"generally":[166],"accurate":[167],"sometimes":[169],"less":[170],"reliable,":[171],"smoothed":[173],"lower":[176],"not":[183],"so":[184],"accurate,":[185],"robust.":[187],"Experimental":[188],"results":[189],"show":[190],"effectiveness":[192],"model:":[196],"reduces":[198],"25%":[203],"compared":[204],"HMM.":[206]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}